Agent Substrate on GKE
Agent Substrate on GKE is generally available for GKE Standard clusters running version 1.37 or later.
The Deploy Log | Free, no signup
Tools and products
1914 rows in Tools and products in The Deploy Log, newest first. They are listed from to , each by its publisher's date or, where the record carries none, its edition's date. Every item sourced to the publisher's own page.
Anthropic Go SDK v2.8.0
Adds claude-fable-5-2 and claude-mythos-5-2 model names, webhook events, and usage report filtering.
Anthropic Java SDK v3.7.0
Adds claude-fable-5-2 and claude-mythos-5-2 model names, webhook events, and usage report filtering.
Anthropic Python SDK v2.7.0
Release v2.7.0 adds claude-fable-5-2 and claude-mythos-5-2 model names and new API features.
Claude Agent SDK TypeScript v0.3.321
Release v0.3.321 fixes hooks, MCP servers, skills, plugins, and session save hangs.
Claude Code v2.1.321
Claude Fable 5.2 is now the default model with 1M context and $8/$40 per Mtok pricing.
Claude Fable 5.2
Claude Fable 5.2 is generally available in GitHub Copilot for Pro+, Max, Business, and Enterprise users.
Claude Fable 5.2 in AWS GovCloud
Claude Fable 5.2 is now available on AWS GovCloud (US).
Claude Fable 5.2 in Devin
Claude Fable 5.2 is live in Devin with a FrontierCode 2.0 score of 49.1%.
Claude Fable 5.2 on AI Gateway
Claude Fable 5.2 is available on AI Gateway with 30-day data retention and model fallbacks.
Show the other 1904 rows
Claude Fable 5.2 on AWS
Claude Fable 5.2 is now available on AWS.
Claude Mythos 5.2 in AWS GovCloud
Amazon Bedrock offers Claude Mythos 5.2 to eligible customers in AWS GovCloud (US).
Cloud Pathways
Cloud Pathways, a distributed ML runtime for accelerator fleets, is now GA on Google Kubernetes Engine.
Codex agent loop on Cloudflare Workers
An experimental Agents SDK example runs the Codex agent loop in a Cloudflare Durable Object with persistence and recovery.
Copilot CLI 1.0.108
Copilot CLI 1.0.108 adds sandbox filesystem settings, /index commands, and Grok PDF attachment fallback.
Databricks Genie for Slack
Databricks Genie app for Slack is now generally available.
Databricks Genie for Teams
Databricks Genie app in Microsoft Teams is now generally available.
Docker Agent v1.158.0
Optional config history and model catalog support, tool duration footers, and compaction overflow fix.
Edge Copilot Shopping Comparison
Microsoft Edge now offers Copilot-generated product comparisons across open tabs and Checkout Savings for coupons.
Exo agents on Cloudflare
Exo agents can now run on Cloudflare with Durable Objects coordinating conversations and Sandboxes running Linux tools.
LangSmith BYOC on AWS
LangSmith Bring Your Own Cloud is generally available on AWS across 15 regions.
Langfuse v4.77.0
Langfuse v4.77.0 adds Amazon Bedrock upstream with API key auth and custom base URLs for OpenAI and Anthropic connections.
LiteLLM v1.108.4
LiteLLM v1.108.4 is released.
Markdown for Agents analytics and tracing
Cloudflare's Markdown for Agents is generally available with analytics, logs, playground, GraphQL API, and Traces span for monitoring conversions.
Mistral Vibe v3.1.1
Mistral Vibe v3.1.1 adds vibe-acp, Vim modes, sticky prompt, and pre-agent, notification, and session-start hooks.
Muse Ember 1.0 on AI Gateway
Meta's Muse Ember 1.0 model is now available through Netlify's AI Gateway with zero configuration required.
Muse Ember on AI Gateway
Meta's Muse Ember reasoning model is available on AI Gateway with a 1M-token context window and adjustable reasoning effort.
Nanocode agent harness in Durable Objects
Nanocode coding agents can now run in Cloudflare Durable Objects with persistent session history and recovery after interruptions.
OpenAI Go SDK v3.97.0
OpenAI Go SDK v3.97.0 adds agent scheduling APIs.
OpenAI Java SDK v4.102.0
Adds agent scheduling APIs and recognizes gpt-6-rosalind in beta Responses.
OpenAI Ruby SDK v0.121.0
Ruby SDK v0.121.0 adds agent scheduling APIs and gpt-6-rosalind to beta Responses requests.
Playwright MCP v0.0.85
Adds --background flag to keep the browser in the background when connecting through the extension.
PostHog Firebase Genkit tracing
Firebase Genkit flows can send model, tool, and embedding traces to PostHog AI observability.
Qwen Code Desktop v0.27.1
Qwen Code Desktop v0.27.1 adds OpenAI-compatible provider docs and shell startup context.
Qwen Code SDK TypeScript v0.1.29
SDK TypeScript v0.1.29 published to npm, bundling CLI versions 0.26.2 through 0.26.9.
SDK TypeScript v0.1.31
SDK TypeScript release v0.1.31 bundles CLI version 0.27.1.
TPU Sync
TPU Sync, an open-source C++ library for KV cache and weight transfer on TPU, cuts KV transfer latency by over 90%.
Workflow SDK WebSocket writes
Workflow SDK 5.2.0 sends event and stream writes over WebSockets by default, replacing one HTTP request per write.
anthropic-sdk-typescript v1.7.0
SDK v1.7.0 adds claude-fable-5-2 and claude-mythos-5-2 model support.
claude-agent-sdk-python v0.2.180
Version 0.2.180 of the Claude Agent SDK for Python is on PyPI.
langchain-fireworks 1.7.3
langchain-fireworks 1.7.3 fixes default max_tokens from model profiles and refreshes model profile data.
qwen-code v0.27.1
qwen-code v0.27.1 adds configurable background execution, LSP settings, and shell naming in startup context.
CrewAI 1.15.38
CrewAI 1.15.38 makes gpt-6-luna the default model everywhere and adds spreadsheet URL reading in agent input.
Open WebUI v0.13.1
Coding agents like Claude Code, Codex and Pi appear in the model picker, and Tether desktop app is introduced.
Open WebUI v0.13.2
Open WebUI v0.13.2 fixes chat and comment loading over plain HTTP and makes the Side Chat permission switch visible independently.
Open WebUI v0.13.3
Automations can now run coding agents with a chosen terminal and folder, and chats can switch terminal or folder mid-conversation.
Qwen Code Desktop v0.27.0
Qwen Code Desktop v0.27.0 includes fixes for channels, core, and managed-agent.
Qwen SDK TypeScript v0.1.30
SDK TypeScript release v0.1.30 bundles CLI version 0.27.0.
Ultralytics 8.4.208
Prediction and tracking now default to 0.5 NMS IoU, while validation keeps 0.7.
llama.cpp b12210
CPU support for SpacemiT IME2 MXFP4 dense repack.
Vercel Tracing
Vercel Tracing is generally available on all plans, with a new Traces page, CLI search, automatic tracing for new Next.js projects, and retention of 3 days on Hobby, 14 days on Pro and Enterprise.
Vercel Schedules
Vercel Schedules is in public beta on all plans, running tasks on a recurring cadence or at a single point in time, billed at $5 per 1M runs and $10 per 1M creations on Pro and Enterprise.
Secret scanning
GitHub secret scanning adds SpaceX as a partner, detects starlink_public_api_v2_secret, and upgrades Alibaba, AWS, Google, OpenVSX, Pydantic Services, and Tencent detectors with additional false-positive filtering.
Codex rust-v0.167.0
Codex rust-v0.167.0 opens the agent command center with codex agents --no-daemon, marks unread results, and adds Google Cloud Vertex AI setup with Application Default Credentials or a credential file.
ADK Python v2.14.0
ADK Python v2.14.0 graduates execution environments, A2A, evaluation, and core runtime modules from experimental and adds multi-run evaluation.
CrewAI 1.15.37
CrewAI 1.15.37 adds spreadsheet reading for agents and standalone agent project scaffolding.
DeepSeek V4.1 Flash 1017 Ultrafast
DeepSeek V4.1 Flash 1017 Ultrafast is on AI Gateway via Fireworks with 1,000+ tokens per second and a 1M-token context window.
LiteLLM 1.108.3 (LTS)
LiteLLM 1.108.3 LTS fixes AWS Bedrock api_base failures and MCP tool results over 1 MiB.
Ultralytics 8.4.205 OCR
Ultralytics 8.4.205 adds scene-text OCR with YOLO26-Text detection and PaddleOCR or custom recognizer.
Ultralytics 8.4.206
Ultralytics 8.4.206 reads upside-down and bottom-to-top text in OCR using a text-line orientation classifier.
Ultralytics 8.4.207
Ultralytics 8.4.207 fixes PaddlePaddle export on new installs and CUDA machines.
qwen-code v0.27.0
qwen-code v0.27.0 adds FileChanged hook notifications, managed agent tool alignment, and test and CI fixes.
DeepSeek Search and Fetch
DeepSeek Search and DeepSeek Fetch are available through AI Gateway, each costing $0.75 per 1,000 billable requests, with no separate DeepSeek account required.
Claude Code v2.1.319
Claude Code v2.1.319 changes auto mode behavior with telemetry or feature flags off, adds MCP task backgrounding, and adds a /claude-api latency-optimize command.
AI Gateway provider key activity
AI Gateway shows usage activity for stored provider keys, with last-used and last-updated dates and a 90-day inactivity highlight.
Agent Framework Python 1.25.0
Agent Framework Python 1.25.0 releases 44 workspace distributions with shipping changes since python-1.24.0.
Agent Registry in AWS GovCloud
Agent Registry is generally available in AWS GovCloud (US-West) Region.
Ampersand on AI Gateway
Ampersand from Humans& is available on AI Gateway free through November 13, 2026.
BigQuery Accessor in Pandas
BigQuery DataFrames adds a .bigquery accessor for zero-shot predictions via BigQuery AI functions in pandas.
Chat SDK generative UI streaming
Chat SDK agents can now stream generative UI with json-render, converting JSON specs into native platform cards.
Claude Agent SDK Python v0.2.179
claude-agent-sdk 0.2.179 released on PyPI.
Claude Agent SDK v0.3.319
Claude Agent SDK v0.3.319 adds MCP task support in SDK sessions and updates to Claude Code v2.1.319 parity.
Copilot impact dashboard chat and agent usage
Copilot impact dashboard now tracks Copilot Chat and VS Code Agents window engagement across nine experiences.
CrewAI 1.15.36
CrewAI 1.15.36 adds experimental conversational Agent sessions and fixes async call execution for sync tools.
EC2 Capacity Blocks amortization
AWS launches support for amortization of EC2 Capacity Blocks for ML.
FLUX 3 Image Klein on Blackwell
TensorRT LLM VisualGen accelerates FLUX 3 Image Klein on NVIDIA Blackwell GPUs with up to 3.46x faster text-to-image and 4.45x faster image-to-image generation.
Flash CLI Nix flake
RunPod Flash CLI now ships a first-class Nix flake, runnable with nix run github:runpod/flash.
GAIA AGENT 0.3.4
AMD released gaia agent 0.3.4 with model-server restart recovery, a working forget command, and faster docs.
GPT Image 2.6 Flare and Sunburst
Lovable apps can now generate and edit images with GPT Image 2.6 Flare and Sunburst models.
GitHub Copilot CLI 1.0.107
Adds GPT-6.1 Terra as a selectable model, /code command, Fusion tier setting, and sandbox extensions setting.
GitHub Copilot weekly releases
Copilot is now available in JetBrains Air and Xcode's coding assistant, with updates for pull requests, settings, and agent sessions.
Google Cloud Z4M instances
Z4M VMs and bare-metal instances are GA with up to 168,000 GiB Local SSD and 400 Gbps RDMA.
Kimi K3.1 Pro (Highspeed)
Kimi K3.1 Pro (Highspeed) is now available on Amazon Bedrock.
Kling, LTX, MiniMax in Foundry
Kling, LTX, and MiniMax video models are rolling out in public preview in Microsoft Foundry via fal.
LiteLLM 1.108.2 (LTS)
LiteLLM 1.108.2 (LTS) fixes OpenAI deployments with empty api_key and AWS Bedrock Converse service_tier handling.
MediaConvert Smart Subtitles
AWS Elemental MediaConvert adds a native integration with AWS Elemental Inference Smart Subtitles.
ModelOpt 0.47.1
ModelOpt 0.47.1 fixes NVFP4 fake quantization with Triton 3.9 on GPUs with compute capability 8.9 or newer.
Neon AI Gateway credits
All Neon accounts can purchase AI Gateway credits, with prepaid credits from $5 on the Free plan.
Qwen Code v0.26.9
Qwen Code v0.26.9 ships fixes for channels, core, managed-agent, and PR verification.
Runpod Hub
Runpod Hub is live for deploying prebuilt open-source AI repos including ComfyUI, Whisper, and Mochi 1.
Transformers v5.22.2
Patch release v5.22.2 with security and distributed fixes.
Ultralytics 8.4.204
High-resolution tiling is available across training, validation, and prediction, with FastSAM prompt, model export, and dataset handling improvements.
dotnet-1.28.0
Microsoft agent-framework released dotnet-1.28.0 with a release version bump and a fix for parsing declarative workflow formulas and values with InvariantCulture.
gaia agent 0.3.5
AMD tagged gaia agent 0.3.5 with core and agent fixes.
github/copilot-cli v1.0.106
Copilot CLI v1.0.106 adds GPT-6.1 Terra as a selectable model and new session tools.
langgraph-cli 0.4.42
langgraph-cli 0.4.42 adds a deploy metrics command and bumps filelock and langgraph-api for security fixes.
langgraph-sdk 0.4.14
langgraph-sdk 0.4.14 adds strict_resume to runs.create, stream, and wait, and tools and lifecycle to StreamMode.
openai-node v7.53.0
Agents now deliver session errors as stream events.
MiMo V2.6
Ollama v0.40.15 adds support for Xiaomi MiMo's mimo-v2.6, a 9B model built for code and agent workflows.
langchain-typesafe 0.0.2
langchain-typesafe 0.0.2 accepts a classifier in experimental middleware.
langchain-core 1.7.6
langchain-core 1.7.6 merges streamed AIMessageChunks once when accumulating runnable streams and stops parse_partial_json from retrying one character at a time.
AWS WAF AI traffic monetization
AWS WAF AI traffic monetization now supports fiat payouts through Stripe.
Amazon Q Developer in console
Amazon Q Developer in console is now the AWS assistant.
Amp GitLab Integration
Amp now integrates with GitLab on gitlab.com and self-managed instances, letting users start projects from GitLab repositories.
Anthropic Java SDK v3.6.0
Anthropic Java SDK v3.6.0 adds error codes for ramp limit and External Key validation failures and support for signing organization members out everywhere.
Anthropic Python SDK v2.6.0
Anthropic Python SDK v2.6.0 adds error codes for ramp limit and External Key validation failures, plus platform client fixes.
Claude Code and Codex in SSH tunnel
Claude Code and Codex are now available in Databricks SSH tunnel sessions, requiring Databricks CLI 1.23.0 or above.
Crush v0.100.0
Crush v0.100.0 adds subagents, sysadmin mode, and PGP/SSH password handling.
Devin Review 2.0
Devin Review 2.0 cuts PR review cost by 82% to $0.25-$0.75 per PR and adds incremental reviews.
Dynamo v1.6.2
Patch release refreshes runtime OS and Python packages, moves SGLang image to CPython 3.12.16, returns HTTP 400 on TensorRT-LLM token budget overrun, and adds opt-in GC freeze for SGLang workers.
Gemini Enterprise prepaid credits
Prepaid credits are generally available for self-serve Cloud Billing accounts on Gemini Enterprise Pay-as-you-go subscriptions and usage above quota.
Gemini Omni 1.2 Flash
Gemini Omni 1.2 Flash is available on AI Gateway, generating 3-15 second videos with native audio.
Langfuse v4.76.0
Langfuse v4.76.0 adds session list view, AI gateway key count telemetry, Topics summaries/assignments/rules in public API, MCP and in-app agent, and audit log read-access events.
LiteLLM v1.108.1
LiteLLM v1.108.1 released with signed Docker images.
Microsoft Foundry extension for Azure Developer CLI
Microsoft Foundry extension for Azure Developer CLI reaches version 1.0 and is generally available.
Model Armor CSAM filter
Model Armor templates and floor settings can enable or disable the CSAM filter with granular confidence levels (High, Medium and above, Low and above).
OpenAI Go SDK v3.96.0
OpenAI Go SDK v3.96.0 adds a model option for Responses.
OpenAI Java SDK v4.100.0
OpenAI Java SDK v4.100.0 adds image complexity and GIF and SVG output controls.
OpenAI Node SDK v7.52.0
OpenAI Node SDK v7.52.0 adds a model option for Responses.
OpenHands v1.36.0
OpenHands v1.36.0 adds automation template features and Data Center templates with extensions 0.39.0.
PyTorch XPU OneDNN grouped_mm
PyTorch merged OneDNN grouped_mm and scaled_grouped_mm for Intel XPU devices. Correction, : this row's source is a CI tag of a merged pull request, not a published PyTorch release.
Qwen SDK TypeScript v0.1.28
SDK TypeScript v0.1.28 bundles CLI version 0.26.8.
SageMaker AI Studio IAM replication
Amazon SageMaker AI Studio now supports IAM Identity Center multi-region replication.
Snowflake CoCo for Excel and Google Sheets
Snowflake CoCo, the coding agent for data teams, is now available in Microsoft Excel and Google Sheets.
Ultralytics v8.4.203
Adds NXP i.MX95 Neutron NPU export for YOLO models via format=nxp.
Weaviate v1.40.4
Weaviate v1.40.4 ships runtime reindex reliability and RBAC fixes, with no new features or breaking changes.
Web Answer on Bedrock AgentCore
Web Answer is now available on Amazon Bedrock AgentCore.
anthropic-sdk-go v2.7.0
anthropic-sdk-go v2.7.0 adds error codes for ramp limit and External Key validation failures, support for signing organization members out everywhere, and client retry fixes.
anthropic-sdk-typescript v1.6.0
Anthropic released sdk-v1.6.0, adding error codes for ramp limit and External Key validation failures.
docker-agent v1.157.0
Bug fixes for token handling, model error recognition, provider behavior, and a new build tag for embedders.
langgraph 1.2.20
LangGraph 1.2.20 adds per-task interrupt IDs and a strict resume mode that refuses stale interrupt answers.
langgraph-sdk 0.4.13
LangGraph SDK 0.4.13 adds cancel_reason to Run and select to threads.get_state and get_history.
livekit-agents 1.8.11
Responses API via LiveKit Inference with structured output and web search, plus Zoom, Kalpa, Rime, Fish Audio, and OpenAI providers.
llama.cpp b12146
Metal backend fuses DeepSeek-V4/V4.1 and GLM MoE routing, including scale-bias routing norm for DeepSeek-V4.1.
llama.cpp b12148
Vulkan RDNA3/4 large-tile split-K optimization in llama.cpp.
mcp-toolbox v1.16.0
Adds skills over MCP extension, mssql source code function, dynamic UI resources, and Looker dashboard tools.
openai-go v3.95.0
openai-go v3.95.0 adds GPT-6 Rosalind to the model catalog, Australia/India/Japan residency options, and image complexity/GIF/SVG output controls.
openai-java v4.101.0
OpenAI Java SDK v4.101.0 adds a model option for Responses and Australia, India, and Japan residency options.
openai-node v7.51.0
openai-node v7.51.0 adds GPT-6 Rosalind to the model catalog, Australia/India/Japan residency options, and image complexity/GIF/SVG output controls.
openai-python v3.46.0
openai-python v3.46.0 adds GPT-6 Rosalind to the model catalog, Australia/India/Japan residency options, and image complexity/GIF/SVG output controls.
openai-python v3.47.0
openai-python v3.47.0 adds a model option for Responses.
openai-ruby v0.119.0
openai-ruby v0.119.0 adds GPT-6 Rosalind to the model catalog, Australia/India/Japan residency options, and image complexity/GIF/SVG output controls.
openai-ruby v0.120.0
openai-ruby v0.120.0 adds a model option for Responses.
qwen-code v0.26.8
qwen-code v0.26.8 adds prompt.submit hooks in OpenTUI, shared-loop model rounds, and concurrent workspace rewinds.
supervision-0.31.5
supervision 0.31.5 adds right-to-left labels, occlusion-tolerant line counting, and exact oriented-box clipping.
AI Function tasks for jobs
Databricks jobs can now run ai_parse_document, ai_extract, or ai_classify on volume files or table rows without SQL, in Beta.
AI Gateway model aliases
AI Gateway now supports model aliases, a pool of models called by one name with fallback or smart routing.
Agent Framework builder skills
Microsoft added installable Agent Framework builder skills for .NET and Python, installable via GitHub CLI or skills CLI.
Agentforce Memory update
Agentforce Memory's updated policy recalls 1.8 times as many stated facts and 2.2 times as many changed facts.
Anthropic Java SDK v3.5.0
Anthropic Java SDK v3.5.0 adds error details types, an ids filter for list workspaces, and exception classes for HTTP statuses and API error codes.
Anthropic Python SDK v2.5.0
Anthropic Python SDK v2.5.0 adds error details types, workspace ID filtering, and HTTP/API error classes.
CUDA 13.5
CUDA Toolkit 13.5 is generally available with production-ready support for NVIDIA Vera Rubin GPU architecture.
Claude Agent SDK TypeScript v0.3.318
Claude Agent SDK TypeScript v0.3.318 adds credential_expires_at, config_file_invalid reason, and parity with Claude Code v2.1.318.
Claude Code v2.1.318
Claude Code v2.1.318 adds assume_role on mantle upstreams, an effort option for mod model forks, and login expiry dates.
Cloudflare AI Crawler and Agent access policies
Cloudflare lets you set actions for top Personal Agents individually via Security > Settings > AI Crawler and Agent access policies.
Confluent Lightning Tables
Lightning Tables is now generally available on AWS, adding query capabilities to Confluent's Data Streaming Platform.
Dify 1.19.0
Dify 1.19.0 adds nested workflow tracing, portable Workflow Tools via App packages, Skill Hub automation, and easier Agent file uploads.
GPT Image 2.6 Sunburst and Flare
GPT Image 2.6 Sunburst and Flare are available through Netlify AI Gateway with zero configuration.
Gemini CLI v0.67.0
Gemini CLI v0.67.0 bridges the IDE companion into container sandboxes over exec stdio and fixes agent loading, file context, and header handling.
Gemini Enterprise mobile team switching
Gemini Enterprise mobile app now lets users switch between multiple teams without logging out and rescanning the QR code.
GitHub Copilot in Xcode coding assistant
GitHub Copilot is now available in Xcode's built-in coding assistant, in public preview starting with Xcode 27.3 beta.
Intelligent Terminal 0.3
Intelligent Terminal 0.3 adds a sidebar for managing tabs and agents, global search, agent CLI detection, and headless mode.
Kimi K3.1 Pro on AI Gateway
Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are now available on AI Gateway from more Zero Data Retention providers, with a 1M-token context window.
Kimi K3.1 Pro on DigitalOcean Inference
Moonshot AI model Kimi K3.1 Pro is now available on DigitalOcean Inference for serverless and dedicated inference.
Langfuse AI Gateway limits
Raises Pro/Team/Enterprise AI Gateway limits to 10k req/min and 5 GiB/min.
Lovable Dreaming
Lovable now tidies project memory in the background on paid plans, a process called Dreaming.
MLX-VLM v0.7.12
Adds Mistral Large 4, Raon-1 Mini, Mage-VL-Cowork support, speculative thinking budgets, and reasoning-effort control.
Moonshot AI Kimi K3.1 Pro
Moonshot AI Kimi K3.1 Pro is available on Unity Gateway on pay-per-token endpoints in us-east-1.
Neon MCP server stateless spec
Neon MCP server added support for the stateless MCP spec () and retired its Server-Sent Events endpoints.
OpenAI Go SDK v3.94.0
Added project service tier settings and Responses cache-write usage details to the API.
OpenAI Java SDK v4.99.0
OpenAI Java SDK v4.99.0 adds 12-hour Responses caching, cache-write usage, and GPT-6 Rosalind to the model catalog.
OpenAI Node SDK v7.50.0
OpenAI Node SDK v7.50.0 adds 12-hour Responses caching and cache-write usage, plus project service tier settings.
OpenAI Python SDK v3.45.0
OpenAI Python SDK v3.45.0 adds 12-hour Responses caching and cache-write usage, plus project service tier settings.
Oracle Realtime Text to Speech
Oracle Speech adds realtime text to speech via WebSocket API, available now through the API only.
Pydantic AI v1.107.10
Pydantic AI v1.107.10 raises the remaining web_fetch timing bounds to 60 seconds.
Qwen Code v0.26.7
Qwen Code v0.26.7 adds an operator model catalog refresh switch and multiple fixes.
Ray 2.60.0
Ray 2.60.0 makes shuffle v2 default for joins and aggregations, sizes Parquet read tasks from row-group metadata, and adds max_surge_percent for Ray Serve rolling updates.
Red Hat OpenShift AI on Google Cloud
Red Hat OpenShift is now generally available in Google Cloud's sovereign regions.
Shop Direct Merchant Workspace
Amazon launches a free self-service portal with a direct AI connector from merchant stores to Alexa for Shopping and Amazon.
Unity Gateway Skills GitHub Action
A GitHub Action in Beta publishes Git-managed skills to Unity Catalog on merges.
claude-agent-sdk-python 0.2.178
claude-agent-sdk-python 0.2.178 released with bundled Claude CLI updated to version 2.1.318.
google-cloud-sdk-v1.1.3
Google Cloud SDK v1.1.3 percent-encodes project, location, and workspace ID in derived base URLs and throws AnthropicError for dot values.
harness-cli v0.2.4
harness-cli v0.2.4 adds explicit cache points on GPT-5.6+ by default and a migration guide from strands-agents-tools.
harness-python v0.3.4
Release harness-python/v0.3.4 adds SystemOneDecisionModel for Jev and decisionapi.net and explicit cache points on GPT-5.6+ by default.
harness-sdk python v1.64.0
Release python/v1.64.0 adds SystemOneDecisionModel for Jev and decisionapi.net and explicit cache points on GPT-5.6+ by default.
harness-sdk typescript v1.24.0
Release typescript/v1.24.0 adds explicit cache points on GPT-5.6+ by default and lets ClassifierStrategy route with any DecisionModel.
harness-typescript v0.3.4
Release harness-typescript/v0.3.4 adds explicit cache points on GPT-5.6+ by default and lets ClassifierStrategy route with any DecisionModel.
langchain 1.4.9
langchain 1.4.9 requires langchain-core>=1.7.5 and standardizes model refusal content blocks.
langchain-anthropic 1.7.10
langchain-anthropic 1.7.10 requires langchain-core>=1.7.5 for refusal handling and translates Gemini safety blocks to refusal content blocks.
langchain-core 1.7.5
langchain-core 1.7.5 adds Gemini safety block translation, model refusal content blocks, and cancellation fixes.
langchain-fireworks 1.7.2
langchain-fireworks 1.7.2 reports streamed token usage once and promotes reranking out of beta.
langchain-openai 1.7.4
langchain-openai 1.7.4 requires langchain-core>=1.7.5 for refusal handling and standardizes model refusal content blocks.
langchain-typesafe 0.0.1
Initial release of langchain-typesafe 0.0.1 with TypeSafeClassifier, AutoModeMiddleware, and ModelRouterMiddleware.
llama.cpp v0.9.0
Adds OCP FP8 E4M3 quantization, flash_attn_ext_rows, four new architectures, Chatterbox TTS, and Gemma 4 E2B/E4B prefill optimizations.
mistral-vibe v3.1.0
Added file autocomplete toggle, /context command with token estimates, and monthly usage display.
openai-ruby v0.118.0
openai-ruby v0.118.0 adds 12-hour Responses caching and cache-write usage.
sdk-v1.5.0
SDK v1.5.0 adds error details types, new error type values, ids filter for workspaces, and error classes for HTTP statuses.
v2.6.0
Go SDK v2.6.0 adds error details types, ids filter for workspaces, ErrorCode constants, and path parameter validation.
vertex-sdk-v1.1.2
Vertex SDK v1.1.2 percent-encodes project ID, region, and model in request paths and throws AnthropicError for empty or dot values.
AI Gateway authentication default
New AI Gateways now require authentication, on by default via API and dashboard.
AI assistant visibility in Account Abuse Protection
Account Abuse Protection now shows when a recognized AI assistant makes a login or sign up request, and which account it acted for.
Agents SDK v0.33.0
Agents SDK v0.33.0 upgrades PiHarness to Pi 1.5, cutting SQLite storage transactions by about 27x for long answers.
Browser Run crawl diagnostics
Browser Run /crawl results now include URL outcomes and robots.txt diagnostics for up to 50 origins.
Claude Agent SDK Python v0.2.177
on_failure option for HookMatcher and bundled Claude CLI 2.1.317.
Claude Agent SDK TypeScript v0.3.317
Added onFailure block for hook matchers and session_writes_lost system message.
Claude Code v2.1.317
Added onFailure block for Agent SDK hooks, OTel metrics fields, and a gateway admin cost report.
CodeQL 2.27.3
CodeQL 2.27.3 adds Python 3.15 features, JSON data extensions, C23 bit-precise integers, and an opt-in AI threat model.
Cohere North on SAP Business AI Platform
Cohere North is generally available on SAP Business AI Platform.
Database Tools MCP Server CIMD Support
Database Tools MCP Server now supports Client ID Metadata Documents in IAM Identity Domains.
FCM AndroidConfigV2
Firebase Cloud Messaging v2 brings more predictable and reliable remote notifications for Android.
FastMCP v4.1.6
ClientGroup keeps tool routes after group context exits.
Gemini Enterprise Salesforce federation
Salesforce data source connection via data federation is generally available in Gemini Enterprise.
GitHub Copilot in JetBrains Air
GitHub Copilot is now available in JetBrains Air with local and cloud coding tasks.
GitHub Copilot in JetBrains Air
GitHub Copilot is now a default agent in JetBrains Air, with Cloud Run support starting .
Haystack 2.31.1
Haystack 2.31.1 requires anyio>=4.14.2 and certifi>=2026.10.19 to address CVEs.
Lakebase sink upsert merge strategies
Merge strategies for Lakebase sink upserts from Structured Streaming, requiring Databricks Runtime 19 and above.
Lakeflow Jobs upstream dependencies
Lakeflow Jobs can now trigger when one or more upstream jobs complete, including across workspaces in the same Unity Catalog metastore.
Langfuse v4.73.0
AI Gateway analytics filtering by user and API key, GitHub Copilot CLI setup, HTTP/2, and HIPAA notice.
Langfuse v4.74.0
AI gateway now has per-organization request and byte rate limits at /resolve.
Ollama v0.40.14
Ollama v0.40.14 applies model output token limits for Claude Code, fixes web search decoding, and preserves sampler defaults.
Open WebUI v0.13.0
Open WebUI v0.13.0 adds a tabbed workspace and an Open Terminal Desktop tab for computer use.
OpenHands v1.35.0
OpenHands v1.35.0 adds a Files tab Download button, resizable sidebar, and persists workspace/repo metadata as conversation tags.
RDS for Oracle M8i/R8i
Amazon RDS for Oracle now supports M8i and R8i instances in additional AWS Regions.
Retool on Google Cloud Marketplace
Retool is now available on Google Cloud Marketplace, joining its existing AWS Marketplace listing.
Snowflake real-time analytics
Snowflake introduces a connected real-time analytics experience spanning connectivity, transformation, and serving across native and Iceberg tables.
Tencent Hy4 on AI Gateway
Tencent Hy4 is available on AI Gateway at 50% off through December 31, 2026, with a 1M-token context window.
Ultralytics 8.4.199
Ultralytics 8.4.199 sends the raw run name to Ultralytics Platform.
Ultralytics 8.4.200
Arabic class names now display correctly in plots.
Ultralytics v8.4.201
Ultralytics v8.4.201 makes PIL-based plotting up to 15x faster across all tasks.
Vercel CI
Vercel CI can now run on a GitHub repository that has no Vercel project.
Vercel Security Review
Public beta for Pro and Enterprise teams, reviewing every push to connected GitHub repos.
WorkSpaces for AI agents
Amazon WorkSpaces for AI agents now supports Linux and Windows 11 cloud desktops.
langgraph-sdk 0.4.12
langgraph-sdk 0.4.12 removes fairness_weight from PrioritySettings and fixes rejoining a run stream that closes before the run ends.
openai-go v3.92.0
Live Responses delegation tools, typed existing-item references, WebSocket final response reconstruction, and MCP argument progress.
openai-node v7.48.0
Live Responses delegation tools and choices, and sparse WebSocket output facts.
openai-ruby v0.116.0
openai-ruby v0.116.0 adds Live Responses delegation tool choices, WebSocket progress accumulation, MCP argument progress, and early required-input continuations.
pydantic-ai v2.65.0
Added 12h prompt cache retention support for GPT-5.6 and later on OpenAI Responses API.
vercel doctor
Vercel CLI adds vercel doctor to check setup and show fix commands.
AI Search billing and sync interval
AI Search billing postponed to December 1, 2026, and default sync interval changed from 6 to 24 hours.
Access service token tags
Access service tokens now support up to five key-value tags for organization and policy-based authorization.
Amazon Quick desktop sign-in
Amazon Quick on desktop now uses your organization's existing Amazon Quick sign-in.
Amazon Textract in Tokyo and Zurich
Amazon Textract is now available in Asia Pacific (Tokyo) and Europe (Zurich).
Anthropic TypeScript SDK v1.4.0
Adds GA methods for analytics, spend limits, and RBAC.
Arize Phoenix
Arize Phoenix now updates model prices automatically with catalog updates between releases.
Azure Site Recovery for Azure Local
Azure Site Recovery for Azure Local is generally available.
BigQuery data agent observability
Google Cloud Observability in BigQuery now monitors performance, adoption, latency, and costs of data agents and their conversations.
Databricks Runtime 19
Databricks Runtime 19 adds ALTER SHARE ADD/ALTER VIEW WITH HISTORY and WITHOUT HISTORY, and updates pytz and tzdata libraries.
Datadog on Claude Marketplace
Datadog is now available on Anthropic's Claude Marketplace.
Flags Explorer redesign
Flags Explorer redesigned to co-locate overrides, branch recommendations, and related actions.
Flagship local flag evaluation
Flagship bindings now evaluate flags against a local flag store during local development.
Gemini 4 Argon on Google Cloud
Gemini 4 Argon is available on Google Cloud, and Claude Opus 5.5 and Sonnet 5.5 are available in Google Antigravity.
Genie Agents file analysis
Genie Agents can analyze unstructured files in Unity Catalog volumes, with citations to source pages.
Google Cloud Developer plugin
Google Cloud Developer plugin is installable from the Antigravity Marketplace with pre-authorized Developer Knowledge MCP server.
Haiku 5.5 on Kiro in AWS GovCloud (US)
Haiku 5.5 is now available on Kiro in AWS GovCloud (US).
Lakebase Postgres on Google Cloud
Lakebase Postgres is now generally available on Google Cloud.
LongCat 2.5 on AI Gateway
Meituan's LongCat 2.5 is now available on AI Gateway with a 1M-token context window for text and image inputs.
Managed Deep Agents
Managed Deep Agents is in public beta on LangSmith Cloud, letting you deploy a deep agent from a project folder with one command.
Model Armor streaming exclusion rules
Template-specific exclusion rules for streaming sanitization are available in Preview, supporting dictionary and regex rules in buffered and real-time modes.
ModelOpt 0.48.0
ModelOpt 0.48.0 adds skip-softmax calibration through vLLM and metadata-only export specifications.
Open page from Chats
Ask Lovable in Chats to show a page in one of your projects.
Qwen Code v0.26.6
Web Shell sidebar activity view, split view, and token usage metrics in Qwen Code v0.26.6.
Qwen TypeScript SDK v0.1.27
Qwen TypeScript SDK v0.1.27 released, bundling CLI version 0.26.6.
SBOM download
Download an SBOM for your project in SPDX 2.3 or CycloneDX 1.5 format from the Security view.
Simba JDBC Driver 2.8.7
Simba JDBC Driver (Legacy) 2.8.7 updates jackson-core, jackson-databind, and jackson-datatype-jsr310 to 2.21.8.
Unity Catalog secrets limits and BROWSE
A schema can now hold 1,000 secrets and a metastore 10,000, with BROWSE support for discovery.
Vercel Flags Project Connections
Project Connections let applications evaluate flags from another Vercel project without sharing SDK keys.
Vercel MCP Client ID Metadata Documents
Vercel MCP now accepts any MCP client using a Client ID Metadata Document, removing the prior allowlist review.
Vercel MCP interactive deployment card
Vercel MCP now renders deployments as an interactive card with live status, build logs, and source details.
Vercel Sandbox with Drives startup speed
Vercel Sandboxes with Drives now start up to 2.4x faster, with median creation time dropping from 1.7s to 0.7s.
Zerobus Ingest default storage GA
Zerobus Ingest into tables backed by default storage in Lakeflow Connect is generally available.
anthropic-sdk-go v2.5.0
GA methods for analytics, spend limits, and RBAC in the Go SDK.
anthropic-sdk-java v3.4.0
GA methods for analytics, spend limits, and RBAC in the Java SDK.
langchain-anthropic 1.7.9
langchain-anthropic 1.7.9 reports streamed content-block tokens to callbacks.
CrewAI 1.15.34
CrewAI 1.15.34 adds standalone LiteLLM catalog, crewai skill search, deploy create --zip, and multiple bug fixes.
KoboldCpp 1.124.1
KoboldCpp 1.124.1 adds YuE2 music gen and BreezeTTS 2, Qwen3-TTS, VoxCPM2, and Ming 3.0 TTS models.
OpenAI Java SDK v4.96.0
Added support for Responses WebSocket warmup.
OpenAI Ruby SDK v0.115.1
Fixed connection_pool version incompatibility with Ruby 3.3.0.
Qwen Code Desktop v0.26.5
Bounded SQL history queries, Generated UI on by default, Web Shell keyboard shortcuts, Russian locale, and one-click daemon updates.
Qwen Code v0.26.5
Bounded SQL history queries, Generated UI on by default, Web Shell keyboard shortcuts, Russian locale, and one-click daemon updates.
Mistral Large 4 Gateway
Mistral Large 4 on Vercel AI Gateway now uses updated weights with lower pricing for input, cached input, and output tokens, and the existing model ID string mistral/mistral-large-4 serves the new version without changes.
GitHub webhook IP ranges
GitHub added three webhook delivery IP ranges to the Meta API hooks field: 9.234.98.160/28, 9.234.98.176/28, and 9.234.106.48/28, for github.com across all plans including GitHub Enterprise Cloud.
Codex rust-v0.166.0
Codex rust-v0.166.0 added keyboard-driven transcript selection with word, line, and page motions, integrated search, GPT-6.1 Terra in bundled, Vertex AI, and Amazon Bedrock model catalogs, and codex queue --resume.
Vercel IP geolocation
Vercel IP geolocation now resolves city-level data for nearly all requests and postal-code data for 90% of traffic, with more frequent refreshes, enabled for all projects with no code or configuration changes.
Vercel Flags SDK
Vercel Flags SDK initialization on cold starts dropped from over 70 ms to 10 ms at p75, roughly 7x faster, and usage reporting no longer keeps functions running after the response, with update @flags-sdk/vercel to 1.5.3 or later.
Claude Agent SDK v0.3.316
Added permissions.blockReadsExemptPaths to the Settings type and updated to parity with Claude Code v2.1.316.
KoboldCpp 1.124
KoboldCpp 1.124 adds YuE2 music generation and BreezeTTS 2, Ming 3.0, Qwen3-TTS, and VoxCPM2 TTS models.
OpenAI Node SDK v7.47.0
OpenAI Node SDK v7.47.0 adds typed Responses WebSocket warmup support.
llama.cpp b12021
Gemma 4 images are resized without letterbox padding in llama.cpp release b12021.
openai-go v3.91.0
Added agent context compaction, session review, time awareness, image edit overlays, and SIP DTMF commands.
openai-java v4.95.0
Adds agent context compaction, session review, time awareness, hosted tool usage, and more.
openai-node v7.46.0
Adds agent context compaction, session review, time awareness, image edit overlays, and more.
openai-python v3.42.0
Added agent context compaction, session review, time awareness, image edit overlays, and SIP DTMF commands.
openai-ruby v0.115.0
Adds agent context compaction, session review, time awareness, image edit overlays, and more.
playwright-mcp v0.0.84
playwright-mcp v0.0.84 adds isolated browser contexts per tab and redacts runtime URL parameters.
Ling 3.1 Flash 1019
Ling 3.1 Flash 1019 from InclusionAI is available on Vercel AI Gateway free until , with a 1M-token context window for coding, multi-step reasoning, and tool-using agents.
Agent Framework dotnet-1.27.0
Released dotnet-1.27.0 with a .NET consumer skill and updated AgentServer dependencies.
Browser Run Chrome 152
Browser Run now runs Chrome 152 by default with updated User-Agent, better site compatibility, and other fixes.
Claude Agent SDK Python v0.2.175
claude-agent-sdk 0.2.175 bundles Claude CLI 2.1.314 and is available on PyPI.
Claude Agent SDK TypeScript v0.3.314
Added sandbox_required_unavailable, permissions.blockWritesOutsideWorkingDirectories, and prewarm().
Claude Code auto mode on Unity Gateway
Claude Code auto mode is now supported for both Anthropic and non-Anthropic models hosted by Databricks.
Claude Code v2.1.314
Claude Code v2.1.314 adds permissions.blockWritesOutsideWorkingDirectories, gateway upstream groups, Bedrock guardrail_trace, and idle compaction for 200K+ token conversations.
Daybreak Red on Bedrock GovCloud
Daybreak Red from OpenAI is now available to eligible customers on Amazon Bedrock in AWS GovCloud (US-East).
GPT-6.1 Terra on DigitalOcean Inference
GPT-6.1 Terra is now available on DigitalOcean Inference for serverless inference.
Gemini 4 Argon on Neon AI Gateway
Gemini 4 Argon is now available on the AI Gateway with a 1M-token context window and text, image, video, audio, and PDF input.
Gemini in Google Slides
Gemini in Google Slides can now edit multiple slides or an entire presentation at once with a single prompt.
Google Cloud spend caps
Spend caps on Google Cloud Budgets are generally available with API automation, live cost reports, and automated monthly resets.
Kiro Web Search in AWS GovCloud (US)
Web Search is now available on Kiro in AWS GovCloud (US).
Microsoft Copilot October 2026 update
New Copilot Home navigation, projects, Workspaces, Autopilot, role-based plugins, and more rolling out to Frontier in October and worldwide in November.
Mistral Vibe v3.0.4
Release v3.0.4 adds /release-notes, preserve_api_base, VIBE_TERMINAL_KEY, credential source display, system prompt file replacement, and output token caps.
SageMaker AI GPU partitioning
Amazon SageMaker AI real-time endpoints now support GPU partitioning.
TensorRT Edge-LLM on DGX Spark
TensorRT Edge-LLM CLI runs Nemotron-3.5 Lightning on DGX Spark 64GB, with DSpark speculative decoding reaching 126.9 tokens per second.
Ultralytics 8.4.193
CPU ONNX Runtime and OpenVINO prediction is up to 2x faster on some systems.
Ultralytics 8.4.194
AutoBatch now sizes from the train dataset for every task, with fixes for model loading, results saving, datasets, and deployment workflows.
cua-driver-rs v0.27.0
Prebuilt Qwen CUA Driver binaries for macOS, Linux, Windows, and Node.js SDK packages.
harness-sdk python/v1.63.0
Python SDK v1.63.0 adds Bedrock maxTokens default, Model.model_info, structured output attempt limits, and a graph tool.
harness-sdk typescript/v1.23.0
TypeScript SDK v1.23.0 adds Bedrock maxTokens default, Model.model_info, structured output attempt limits, and a graph tool.
harness-typescript/v0.3.3
Harness TypeScript v0.3.3 adds Bedrock maxTokens default, Model.model_info, and a summarizer fallback fix.
langgraph 1.2.19
langgraph 1.2.19 released with streaming fixes and ToolNode tool names in graph node metadata.
langgraph-checkpoint-sqlite 3.1.3
langgraph-checkpoint-sqlite 3.1.3 released with a fix rejecting NUL bytes in namespace labels.
langgraph-sdk 0.4.11
langgraph-sdk 0.4.11 released with stream reconnect retries and SSE state preservation fixes.
Ollama v0.40.13
Ollama v0.40.13 brings Liquid AI LFM3 models, including text-to-speech in lfm3-audio and lfm3-omni, to Linux and Windows in addition to Apple silicon.
Node.js 26 LTS
Node.js 26 LTS is generally available for builds and Vercel Functions, with HTTP/2 by default for built-in fetch via Undici 8, the Temporal API, and V8 14.6, and it is the default for all new projects.
langchain-core 1.7.2
langchain-core 1.7.2 added add_notification_metadata and get_notification_metadata and fixed merge_content so it no longer changes the first message's content.
Agno v3.1.12
Native approvals for Harness Agents now reach the AgentOS approval UI for Claude and Codex.
Amp Visualize
Amp can now visualize or build charts, timelines, diagrams, and clickable mockups in the thread.
BigQuery Databricks Iceberg query
BigQuery can now query Databricks-managed Apache Iceberg tables via Lakehouse with metadata refresh as often as every 5 minutes.
CrewAI 1.15.33
CrewAI 1.15.33 adds skill search, deploy create --zip, and fixes for token usage and JSON crew loading.
Edge Accelerated App Launches
Edge 150+ on Windows 11 25H2/26H2/26H1 with October 2026 update gets up to 33% faster launch.
GPT 6.1 Terra in Retool
GPT 6.1 Terra is now available in Retool through OpenAI for AI resource queries and building apps.
GitLab Orbit
GitLab Orbit is generally available, with agents using up to 45x fewer retries and 4.5x fewer tokens in testing.
GitLab Orbit vulnerability blast radius
GitLab Orbit is generally available for querying vulnerability blast radius across projects, owners, and pipelines.
HfFileSystem Bucket copy
HfFileSystem now supports copying and moving files into and within Buckets.
Langfuse v4.72.0
Langfuse v4.72.0 adds AI Gateway analytics, PagerDuty alerts, trace-level eval filters, and AI Gateway onboarding.
Lovable credit run-out email
Workspace admins and owners now get an email when credits are likely to run out before the monthly refill.
Managed Deep Agents v0.10
Managed Deep Agents v0.10 adds browser use and async subagents, available today.
Model Armor in southamerica-east1
Model Armor is available in Brazil (southamerica-east1) with prompt injection, responsible AI, and sensitive data protection filters.
ONNX Runtime WebGPU Plugin EP v0.5.0
Expanded attention, mixture-of-experts, and quantized operator support with GPU kernel performance improvements.
ONNX Runtime v1.30.1
Patch release with model-validation, memory-safety, Plugin EP data transfer, and build fixes.
Open WebUI v0.12.5
Open WebUI v0.12.5 adds analytics session explorer, multi-page notes, live presence in notes, and rename from chat menu.
Pipecat v1.15.0
Pipecat v1.15.0 adds NVIDIA TTS custom_configuration and classifier-based user turn stop strategies.
Qwen Code v0.26.4
Qwen Code v0.26.4 adds unscoped npm extension installs, independent worktrees, and inline model timing.
RDS storage autoscaling
Amazon RDS for Oracle and SQL Server now support storage autoscaling on additional storage volumes.
Real-Time Mode for Spark Declarative Pipelines
Real-Time Mode for Spark Declarative Pipelines is generally available on Databricks.
SAP Business Data Cloud lakehouse
SAP Business Data Cloud now supports native Apache Iceberg and a universal catalog powered by Apache Polaris.
SageMaker AI SOCI-indexed images
Amazon SageMaker AI now supports SOCI-indexed images to start training jobs in seconds.
Step Functions as AI agent tools
AWS Step Functions workflows are now available as AI agent tools.
Strix on Vercel AI Gateway
Strix can now run on any of the 400+ models on Vercel AI Gateway.
TRL Mistral Large 4 support
TRL v1.17.0 adds LoRA fine-tuning support for Mistral Large 4 on a single 8×B300 node.
Transformers v5.22.0
Transformers v5.22.0 adds support for Mistral Large 4, a 1T-parameter MoE model with 49B active parameters.
Vercel Connect webhook triggers
Vercel Connect now supports webhook triggers for Resend, X, Twilio, Notion, and Telegram.
Vercel Firewall AI Bots Ruleset
Vercel Firewall now lets you log or block AI crawlers and AI assistants separately via the AI Bots managed ruleset.
Vercel Plugin for Antigravity
Vercel Plugin is now available in the Google Antigravity marketplace with skills for AI SDK, Vercel Functions, and Workflow.
harness-cli v0.2.3
Adds structured output attempt limits, agent.cancel() stop, and graph, read, write, edit tools.
harness-python v0.3.3
Adds structured output attempt limits, agent.cancel() stop, and graph, read, write, edit tools.
harness-typescript v0.3.2
Adds structured output attempt limits, agent.cancel() stop, and graph, read, write, edit tools.
@gradio/utils@0.15.0
Released @gradio/utils 0.15.0 with full screen layout support for gr.workflow.
@gradio/workflowcanvas@0.14.0
Released @gradio/workflowcanvas 0.14.0 with ZeroGPU token forwarding and workflow layout fixes.
AWS Agent Registry
AWS Agent Registry is now available in four additional AWS Regions.
Amazon Bedrock AgentCore CLI 1.0
Amazon Bedrock AgentCore CLI version 1.0 is now available.
Application Integration agent skills
Three agent skills for Application Integration are available in the public google/skills repository.
Copilot Fusion local model selection
GitHub Copilot Fusion can now route between supported on-device models and cloud models in CLI, app, and VS Code.
Copilot UX components
Copilot UX components are generally available with SharePoint Framework 1.24, enabling interactive dashboards, forms, and business actions in Copilot.
Copilot in JetBrains update
GitHub Copilot Fusion, local sandboxes, and next edit suggestions are now available in JetBrains IDEs.
Dataverse plugin for Copilot Cowork
The Dataverse plugin is now available in Copilot Cowork, building governed Dataverse apps from one prompt.
Dependabot reachability analysis
Reachability analysis for Dependabot is in public preview for JavaScript and TypeScript, adding call-path verdicts to alerts.
Docker Agent v1.154.0
Docker agent v1.154.0 adds Lunaroute as an OpenAI-compatible provider with credential-based selection and model discovery.
Echo Dot and Echo Studio with Home Camera
New Echo Dot with built-in smart home hub and Echo Studio with Home Camera are available now.
Events & Hooks
Workspace admins and owners on Business and Enterprise plans can now extend their workspace with Events & Hooks.
Gemini Enterprise Brazil region
Gemini Enterprise app is available in the Brazil (br) region with at-rest data residency and in-region ML processing, GA with allowlist.
GitHub Agentic Workflows
GitHub Agentic Workflows is now generally available for automating reasoning-based tasks with coding agents inside GitHub Actions.
GitHub Copilot computer use
Computer use is in public preview on macOS and Windows, letting Copilot read app content, click controls, and navigate across apps.
GitHub Copilot in VS Code
Cloud agent sessions, Agent Host, and cross-client session continuity are now available in GitHub Copilot for VS Code.
GitHub Copilot security extension
The GitHub security extension is in public preview, letting users find, explain, and fix code scanning alerts in the Copilot app.
Gradio 6.31.0
Gradio 6.31.0 released with video format conversions and ZeroGPU X-IP-Token forwarding.
MacBook Pro with PROLED XDR Display
New MacBook Pro with PROLED XDR Display, M5 Pro/M5 Max, and Touch is available to pre-order today, with availability beginning .
Particle-1 on AI Gateway
Particle-1 from Particle AI is now available on AI Gateway with a 1M-token context window.
Paseo agents on Vercel Sandbox
Paseo now supports running fx, Codex, Claude Code, OpenCode, and Pi in the cloud with the Vercel Sandbox plugin.
Prime 360 on Trainium
Prime 360 cinematic highlights run on Amazon Trainium chips during select NBA on Prime broadcasts this season.
Qwen Code Desktop v0.26.3
Qwen Code Desktop v0.26.3 adds session permission rules, auto approval, an experimental shared agent loop, and CLI fixes.
Raycast Notes Images
Raycast v2.10 adds images to Notes and lifts the 5 note limit on the free plan.
RunPod Batch Inference
Batch inference is generally available on RunPod Serverless with up to 3 million requests a day and up to 30% off on-demand pricing.
SAP Migration and Modernization Assistants
Four migration and modernization assistants are available to early adopter customers for cloud ERP transformation projects.
Shared Copilot Automations
Shared Copilot Automations are rolling out to Copilot Pro, Pro+, Max, Business, and Enterprise plans.
Shop SDK lead capture RAR
Shop SDK lead capture now accepts an authorization Details attribute to request specific profile fields, including phone number and birthdate.
Shopify Analytics app events
Shopify Analytics now shows events from supported apps, including marketing emails and loyalty redemptions.
Shopify Analytics bubble maps
Shopify Analytics released bubble maps that group nearby shipping or billing addresses into bubbles sized by a chosen metric.
Shopify Campaign Autopilot
Campaign Autopilot is now available to all merchants with channels like Meta Ads, Microsoft Advertising, Snapchat, Shop, and Shopify Messaging.
Shopify Flow Product updated trigger
Shopify Flow added a Product updated trigger that can monitor up to 5 product fields.
Shopify Flow via AI Toolkit
External agents can now create, update, delete, activate, and deactivate Shopify Flow workflows through AI Toolkit.
TorchVision 0.29.2
TorchVision 0.29.2 is a minor release with no new feature, compatible with PyTorch 2.14 and later.
Ultralytics v8.4.192
v8.4.192 supports torch 2.15 CUDA in DDP training and ONNX Runtime inference.
Vercel Container Registry 2 GB layers
Vercel Container Registry now supports up to 2 GB per compressed image layer, up from 500 MB.
Virtual Models on AI Gateway
Virtual Models let apps call a saved model configuration by ID and change the underlying model or settings centrally without redeploys.
Weaviate v1.40.3
Weaviate v1.40.3 fixes backup auth, telemetry timeouts, inverted index writes, shutdown cycles, and geo index queue deletion.
copilot-cli 1.0.105
Selecting Copilot Fusion High or Max in /model now works from long-context sessions.
fx in T3 Code
fx is now available as a coding agent provider in T3 Code on web, desktop, and mobile.
pydantic-ai v2.63.0
pydantic-ai v2.63.0 defaults CodeMode to dynamic_catalog=True and changes Gemini Live reconnect and Harness LLMReminder defaults.
qwen-code v0.26.3
qwen-code v0.26.3 improves tool call recovery, memory extraction, and context-window detection for qwen models.
supervision 0.31.3
supervision 0.31.3 adds grayscale annotator support and merges multi-part masks in YOLO export.
vLLM-Omni v0.32.0
vLLM-Omni v0.32.0 adds Ray-based multi-node inference, session-aware replica placement, and multi-frontend full-duplex serving.
AI Functions Unity Catalog permissions
Metastore admins can use Unity Catalog permissions on the system.ai schema to control which AI Functions users can run.
Agent Evals and cost controls for Agent Fabric
Agent Evals, API Evals, and advanced cost controls for Agent Fabric, handling over 1.2 billion requests daily.
Agno v3.1.11
Agno v3.1.11 lets ClaudeAgent and CodexAgent be members of Teams and steps of Workflows.
Amazon Aurora Serverless 384 ACUs
Amazon Aurora Serverless now supports up to 384 ACUs.
Amazon ECS GPU sharing with MPS
Amazon ECS now supports GPU sharing with NVIDIA Multi-Process Service (MPS).
Azure Blob Storage account limit
Higher limit of Azure Blob Storage accounts per region per subscription is generally available.
Claude Agent SDK v0.3.312
Claude Agent SDK v0.3.312 adds autoMode settings, unanswered annotations, and parity with Claude Code v2.1.312.
Claude cost management in Foundry
Cost management and tagging for Claude models in Microsoft Foundry is generally available.
Data Engineering Agent Google Drive
Data Engineering Agent now accepts Google Sheets, CSV, or JSONL files from Google Drive as pipeline input.
Default OAuth apps for external AI agents
ChatGPT, Codex, Claude, Claude Code, and Cursor can now connect to Databricks MCP servers using default OAuth client IDs.
Dropbox for Microsoft Copilot
Dropbox for Microsoft Copilot integration lets users find, open, summarize, organize, and compare Dropbox content in Copilot.
ElastiCache data tiering
Data tiering is now available on R8gd and R7gd nodes in Europe (Spain) and Asia Pacific (Hyderabad).
ElastiCache for Valkey durability change
Amazon ElastiCache for Valkey now supports changing durability on existing clusters.
GPT-6.1 Terra on Unity Gateway
OpenAI GPT-6.1 Terra is now available on Unity Gateway via Foundation Model APIs.
Gemini Enterprise VPC for MCP servers
VPC connectivity and static IP egress for custom MCP servers, supported in us-central1 and europe.
Gemini Robotics ER 2
Gemini Robotics Embodied Reasoning 2 is now available in public preview on the Gemini platform.
GitHub Copilot CLI 1.0.104
Copilot CLI 1.0.104 starts sessions on Auto, applies fusionTier settings, and enables Assisted Permissions without experimental mode.
GitHub Copilot server-to-server auth
GitHub Copilot supports server-to-server authentication for GitHub Apps on organizations in public preview, with read-only Copilot Requests permission and installation access tokens.
IdP group mappings
Workspace admins and owners on Business and Enterprise plans can now map IdP groups to workspace roles.
Langfuse v4.71.0
AI gateway now records model, key owner, byte and upstream error facts on generations.
LiteLLM v1.104.8
Failure logs for rejected requests now keep only core request fields, tags and guardrail details.
LiteLLM v1.105.6
Failure logs for rejected requests now keep only core request fields, tags and guardrail details.
LiteLLM v1.106.5
Failure logs for rejected requests now keep only core request fields, tags and guardrail details.
NVIDIA RTX Spark
NVIDIA RTX Spark Windows PC platform with up to 128 GB unified memory, DLSS 5, and Nemotron 3.5 Bolt E4B 4GB is available.
OCI Responses API Compaction
OCI Responses API now supports explicit and automatic context compaction for long-running conversations and agent workflows.
OpenAI Go SDK v3.89.0
OpenAI Go SDK v3.89.0 adds prompt cache breakpoint TTL options.
OpenAI Node SDK v7.45.1
OpenAI Node SDK v7.45.1 clarifies prompt cache breakpoint TTL behavior and supports google-auth-library v11.
OpenHands v1.34.0
Per-conversation Docker runtime and Settings → Runtime page added.
Pydantic AI v2.62.0
Pydantic AI v2.62.0 adds mid-conversation thinking effort changes and new model error categories.
Qwen Code v0.26.2
Qwen Code v0.26.2 adds session permission rules, auto approval, and an experimental shared agent loop.
Remote MCP Server for Oracle
Remote MCP Server for Oracle workloads is now generally available, providing a unified interface for AI agents to run SQL on Oracle databases.
SageMaker MLflow 3.16 support
SageMaker MLflow Apps now support MLflow 3.16.
Triton 3.9.0
Triton 3.9.0 adds tl.atomic_load, tl.atomic_store, and tl.atomic_poll.
Ultralytics 8.4.191
RKNN INT8 export now enabled for detection, segmentation, pose, and oriented bounding box models.
Unity Gateway Usage Dashboard v1.0
Unity Gateway Usage Dashboard v1.0 is now available with coding-agent adoption, harness usage, and estimated session spend analysis.
Vercel AI Traffic Insights
Vercel Observability now shows AI bot requests, crawled pages, assistant retrievals, markdown requests, and errors.
Vercel Plugin for OpenCode
Vercel Plugin is now available in OpenCode 2 with skills for AI SDK, Vercel Functions, Workflow, and specialist agents.
Visual Studio October Update
Visual Studio 2026 Stable Channel adds commit-to-working-tree compare, bulk conflict resolution, and a new Copilot chat experience.
Workflows jurisdiction restriction
Workflows can now be restricted to eu, us, or fedramp jurisdictions.
langchain-anthropic 1.7.7
langchain-anthropic 1.7.7 released with trace resolved reasoning effort fix and dependency updates.
openai-java v4.94.0
openai-java v4.94.0 adds prompt cache breakpoint TTL options and native OkHttp client support.
openai-python v3.40.0
Adds prompt cache breakpoint TTL options to the API.
openai-ruby v0.114.0
openai-ruby v0.114.0 adds prompt cache breakpoint TTL options.
pg_pinecone
Pinecone released pg_pinecone, an Apache 2.0 Postgres extension for filtered vector search on existing pgvector columns.
Automated Snowpipe Setup with CoCo
Automated Snowpipe setup with Snowflake CoCo is now generally available, building ingestion pipelines from a single natural-language conversation.
Browser Use 0.13.14
Browser Use 0.13.14 adds OpenAI browser tools and a shared Bash helper.
CLI v3.0.74
CLI v3.0.74 attaches to existing runs, times out Hub health checks after 3s, and retries dropped turns at most 3 times.
Cisco IQ for Partners
Cisco IQ for Partners is now generally available with MCP server and expanded APIs.
Claude Code v2.1.311
Claude Code v2.1.311 adds --hold-idle-file and --max-hold-min to self-hosted-runner and fixes long freezes and context errors.
Cline Desktop v0.0.49
Desktop v0.0.49 adds a Changes button, project files panel, and integrated terminal.
Cline v4.1.26
Added Cloud tasks with a Local | Cloud toggle, cloud model selection, and sandbox progress card.
Cloudflare Advanced Nameservers API
DNS settings endpoints now represent Advanced Nameservers with nameservers.type: "cloudflare.advanced", rolling out over seven days.
Devin Security 2.0
Devin Security 2.0 launches with frontier-model scanning, prioritization, and autonomous remediation that turns findings into pull requests.
FastMCP v4.1.4
FastMCP v4.1.4 fixes CLI transport preservation, session visibility, OAuth identity assertions, and adds redis-py credential provider support.
GPT-6.1 Terra in GitHub Copilot
GPT-6.1 Terra is generally available in GitHub Copilot for Pro, Pro+, Max, Business, and Enterprise users.
GPT-6.1 Terra on AI Gateway
OpenAI GPT-6.1 Terra is available on Vercel AI Gateway with a context window over 1M tokens and a fast mode.
GPT-6.1 Terra on Bedrock
OpenAI GPT-6.1 Terra is generally available on Amazon Bedrock.
GPT-6.1 Terra on Netlify AI Gateway
OpenAI's GPT-6.1 Terra model is now available through Netlify's AI Gateway and Agent Runners with zero configuration required.
GitHub Copilot assisted permissions
Assisted permissions are generally available in GitHub Copilot CLI, GitHub Copilot app, and Visual Studio Code.
IAM Helper Agent Skills and MCP Tools
IAM Helper Agent Skills and MCP Tools are now available to automate IAM workflows for agents.
Kilo Code v7.8.18
VS Code 7.8.18 and CLI 7.8.18 with dependency updates and hosted cloud sessions exposed through local Kilo API.
Lakeflow Performance Observability
Lakeflow Jobs now show job-level query performance metrics and insights for supported tasks.
LookML in Knowledge Catalog
LookML semantic language indexing in Knowledge Catalog for Looker Core is now generally available.
Mistral Vibe v3.0.3
Skills added or edited on disk are picked up by running sessions without /reload.
Model Armor
Model Armor enforces the managed constraint modelarmor.managed.requireTemplateDataResidencyCompliance by default, now generally available.
NVIDIA Mission Control 2.5
Extends autonomous recovery engine to Kubernetes workloads managed by NVIDIA Run:ai.
OpenAI Java SDK 4.92.0
OpenAI Java SDK 4.92.0 adds delegation controls and prompt cache lifetimes.
OpenAI Java SDK 4.93.0
OpenAI Java SDK 4.93.0 adds the gpt-6.1-terra model identifier.
SAP AI Release Highlights Q3 2026
SAP reports 45,000 cloud customers using its AI solutions and expanded Joule Assistants and specialized agents.
SDK v0.2.0
SDK v0.2.0 reattaches to live sessions, records capability registrations, and retries dropped reasoning-only turns.
Sierra on Google Cloud Marketplace
Sierra is now available on Google Cloud Marketplace.
Supabase Personal Access Token scoping
Supabase Personal Access Tokens can now be scoped by resource, permission, and expiry.
Ultralytics v8.4.190
YOLO26-seg training now uses Mask-IoU-aware label assignment, with fixes for export, inference, training utilities, and data handling.
Vercel Sandbox stdin support
Vercel Sandbox runCommand() now supports stdin with writeStdin() and closeStdin() in TypeScript and Python SDKs.
Vercel custom monitors
Custom monitors are available on Pro and Enterprise plans with Observability Plus at $0.0035 per GB scanned.
claude-agent-sdk 0.3.311
claude-agent-sdk-typescript 0.3.311 released with cache lifetime token fields and Node.js 18.14.0 minimum.
langgraph 1.2.18
DeltaChannel now takes a full snapshot every 100 updates instead of 1000, with snapshot_frequency=1000 to keep old behavior.
langgraph-checkpoint 4.3.1
langgraph-checkpoint 4.3.1 released, rejecting NUL bytes in namespace labels.
langgraph-cli 0.4.39
langgraph-cli 0.4.39 adds --json to deploy list.
langgraph-cli 0.4.40
CLI now sends the upload headers the control plane returns.
langgraph-sdk 0.4.10
Retries runs.wait with a bodyless GET, follows SSE spec, and accepts durability, stream_resumable and context in runs overloads.
openai-go v3.87.0
The OpenAI Go SDK adds delegation controls and prompt cache lifetimes.
openai-go v3.88.0
The OpenAI Go SDK adds the gpt-6.1-terra model identifier.
openai-node 7.44.0
openai-node 7.44.0 released, adding delegation controls, prompt cache lifetimes, and scheduled automations.
openai-node 7.45.0
openai-node 7.45.0 released, adding gpt-6.1-terra model identifier.
openai-python v3.38.0
Adds delegation controls, prompt cache lifetimes, and expands Live Decision item and question types.
openai-python v3.39.0
Adds gpt-6.1-terra model identifier to the OpenAI Python SDK.
openai-ruby v0.112.0
Adds delegation controls and prompt cache lifetimes to the openai-ruby SDK.
openai-ruby v0.113.0
Adds gpt-6.1-terra model identifier to the openai-ruby SDK.
sherpa-onnx v2.0.1
sherpa-onnx v2.0.1 adds VoxLock target-speaker voice isolation to speech denoisers.
Cloudflare Managed Ruleset
Two rules for CVE-2026-111497 added to Cloudflare Managed Ruleset, enabled by default with action set to Log.
LiteLLM v1.104.7
Fixed proxy startup ImportError when the remote model cost map is unreachable.
LiteLLM v1.105.5
Fixed proxy startup ImportError when the remote model cost map is unreachable.
LiteLLM v1.106.4
Fixed proxy startup ImportError when the remote model cost map is unreachable.
Open WebUI v0.12.4
Open WebUI v0.12.4 adds on-demand skill loading and a context compacted marker in chats.
Ultralytics 8.4.189
Ultralytics 8.4.189 fixes IMX500 and Hailo exports, dataset errors, and model output handling.
NVIDIA Nemotron 3.5 Bolt E4B
Ollama v0.40.10 adds NVIDIA Nemotron 3.5 Bolt E4B, a Gemma 4-based vision-language model with a 128K-token context window and a DFlash draft for speculative decoding, runnable with ollama run nemotron-3.5-bolt:e4b.
Copilot global default policy
GitHub is gradually rolling out enforcement of a global default policy for generally available Copilot features through , setting eligible unconfigured features to Enabled, Disabled, or Let organizations decide.
Vercel CLI spend management
You can now view and manage your team's Spend Management budget from the Vercel CLI with vercel budgets, including setting a budget with a --pause flag that pauses production deployments of all projects when spend reaches 100%.
Vercel build cache size
Deployment summaries now show the size of the build cache each deployment saved and how close it is to the limit for its build machine, on by default on all plans for deployments built on or after .
LangGraph 1.2.17
LangGraph 1.2.17 released with recursion limit, namespace, and dependency fixes.
Langfuse v4.70.0
Adds read-only Topics API endpoints, Claude Desktop setup updates, and runBatchEvaluation MCP tool.
Pipecat v1.14.0
Pipecat v1.14.0 adds PerplexityAgentHttpLLMService with web search and function calling.
Qwen Code Desktop v0.26.1
Qwen Code Desktop v0.26.1 adds daemon token persistence.
Qwen Code v0.26.1
Adds daemon token persistence and durable manual context compression.
Ultralytics v8.4.186
Adds a shared import helper to load torch 1.10-1.12 and MNN on glibc 2.41+.
Ultralytics v8.4.187
YOLO26-pose training now uses OKS-only label assignment with a pyramid-level gate.
livekit-agents@1.8.9
livekit-agents 1.8.9 adds LiveKit Inference decision evaluation and custom LLM request attributes.
pydantic-ai v2.61.0
pydantic-ai v2.61.0 released with thinking override warnings and Cohere tool return handling.
supervision-0.31.2
Pascal VOC boxes follow devkit convention, and crashes on edge-case inputs are fixed.
Google Vids playback speed
Google Vids now lets you adjust the playback speed of individual video clips, speeding up footage to 2x or slowing it down to 0.25x.
Kimi K3.1 Pro
Kimi K3.1 Pro from Moonshot AI is now available on AI Gateway along with Kimi K3.1 Pro Highspeed, keeping the 1M-token context window and image input with improvements in coding, 3D modeling, financial analysis, and agentic tasks.
Vercel Connect Stripe keys
Vercel Connect can now create a separate restricted Stripe API key for each agent or task, limited to the permissions you pick, with rotation from the connector's settings and the old key staying valid for up to 24 hours.
@modelcontextprotocol/client@2.4.0
Adds opt-in scope for refresh-token requests for authorization servers that reject refresh without it.
@modelcontextprotocol/core@2.4.0
Adds Skills extension (SEP-2640) via new ext/skills subpaths.
@modelcontextprotocol/node 2.1.2
@modelcontextprotocol/node 2.1.2 published with @hono/node-server dependency range widened to ^1.19.9 || ^2.1.3.
@modelcontextprotocol/server 2.4.0
@modelcontextprotocol/server 2.4.0 published with Skills extension reachable through new ext/skills subpaths.
@modelcontextprotocol/server-legacy 2.4.0
@modelcontextprotocol/server-legacy 2.4.0 published with updated dependency on @modelcontextprotocol/core 2.4.0.
Agent Framework dotnet-1.26.0
Agent Framework dotnet-1.26.0 released with fixes for tool calls, Copilot session hooks, and AG-UI samples.
Agno v3.1.10
CodexAgent auto sign-in with OPENAI_API_KEY, OS Manager runs external agents, tracing keeps up to 1,024 attributes.
Amazon Connect persistent chat
Amazon Connect Customer Global Resiliency now supports persistent chat across linked AWS Regions.
Amazon MWAA Mexico (Central) Region
Amazon MWAA is now available in the Mexico (Central) Region.
Anthropic Go SDK v2.2.0
Adds message threads and usage/cost reports by dimension to the Go SDK.
Anthropic Google Cloud SDK v1.1.1
Fixes user profile routes to the organization endpoint.
Anthropic Java SDK v3.2.0
Anthropic Java SDK v3.2.0 adds message threads API support and usage and cost reports by dimension.
Anthropic Java SDK v3.3.0
Java SDK v3.3.0 adds Claude Tag endpoints for Enterprise organizations and makes StreamResponse iterable.
Anthropic Python SDK v2.2.0
Anthropic Python SDK v2.2.0 adds message threads API support and usage and cost reports by dimension.
Anthropic TypeScript SDK v1.3.0
Adds Claude Tag endpoints for Claude Enterprise organizations.
Bedrock Web Search controls
Web Search on AWS Bedrock now supports domain filtering and user location controls.
Box Audit Logs connector
The Box Audit Logs connector in Lakeflow Connect is now available in Beta.
Cisco Antares DevNet Learning Labs
Two GPU-backed Antares vulnerability localization labs are now live in DevNet Learning Labs.
Claude Agent SDK TypeScript v0.3.310
Claude Agent SDK for TypeScript v0.3.310, updated to parity with Claude Code v2.1.310.
Claude Code v2.1.310
Added Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, plus fixes for gateways, cleanup, and compaction.
CrewAI 1.15.29
CrewAI 1.15.29 adds LiteLLM-compatible kwargs, CLI search, Azure DocumentDB vector search, and promotes AgentExecutor out of experimental status.
DataFrame caching on serverless compute
DataFrame caching on serverless compute is now in Public Preview, requiring serverless environment version 5 or above.
Diffusers 0.42.0
Diffusers 0.42.0 adds FLUX.3 Image Klein, Fibo 2.0, Kandinsky 6, SANA-WM, and RFD4-Proteína; Python 3.11+ required.
Gemini Notebook Connected App
Gemini Notebook is now a Connected App in the Gemini app, available to all Google Workspace customers and personal accounts.
GitHub Copilot in Visual Studio
September update adds Git agent pull request exploration, BYOM preview, and NuGet vulnerability fixer.
Google Vids audio extraction
Google Vids can extract a video clip's audio into a standalone clip on the timeline.
Goose v1.56.0
Goose v1.56.0 adds automatic thinking level operation, subagent session links, Windows NSIS installer, and IO Intelligence provider.
Jev on Neon AI Gateway
Neon's AI Gateway now serves TypeSafe's Jev 1.14 and OpenJev decision models, billed for input tokens only.
Langfuse v4.69.0
AI gateway per-tool setup instructions, guided setup, and self-hosted gating on LANGFUSE_AI_GATEWAY_DEPLOYED.
MCP TypeScript SDK 2.4.0
MCP TypeScript SDK 2.4.0 released with client, server, core, server-legacy, and codemod packages at 2.4.0.
MiniMax M3.1 Flash on Netlify
MiniMax M3.1 Flash is available through Netlify AI Gateway and Agent Runners with zero configuration.
MiniMax M3.1-Flash on DigitalOcean
MiniMax M3.1-Flash is now available in public preview on DigitalOcean Inference for serverless inference.
OpenAI Go SDK v3.86.0
OpenAI Go SDK v3.86.0 changes Decisions and Live question Instructions fields to typed unions, breaking direct string assignment.
OpenAI Java SDK v4.91.0
OpenAI Java SDK v4.91.0 changes Decisions question instructions() to return an Instructions union.
OpenHands v1.32.0
OpenHands v1.32.0 adds pinned automations in agent-server settings, installable library options in MCP dialog, and cloneable provider repositories in automation picker.
OpenHands v1.33.0
Launch --mars-web and --lock-to-cloud, keep web build signed in across restarts, default new agents to smallest VM.
PostHog AI observability for Gemini
AI observability captures foreground Gemini Interactions calls, including streamed responses, tool activity, usage, and supported media output.
Promptfoo 0.125.0
Promptfoo 0.125.0 adds provider-only environment overrides, rouge-l/rouge-s assertions, and safe mode for inline JavaScript.
Pydantic AI v2.60.0
Pydantic AI v2.60.0 released with model error categories, ModelSelectionContext fields, Bedrock maxTokens default, and deprecations.
Workers Builds packageManager
Workers Builds now installs the npm version set in packageManager before dependencies, supporting npm, Yarn, pnpm, and Bun.
aws-sdk-v1.1.0
Anthropic TypeScript SDK release adds support for message threads.
bedrock-sdk-v1.1.0
Anthropic TypeScript SDK release adds support for message threads.
foundry-sdk-v1.1.0
Anthropic TypeScript SDK release adds support for message threads.
google-cloud-sdk-v1.1.0
Anthropic released google-cloud-sdk-v1.1.0, adding support for message threads.
huggingface_hub v2.3.0
Released huggingface_hub v2.3.0 with bucket live-follow and faster HfFileSystem listings.
langgraph-cli 0.4.38
langgraph-cli 0.4.38 adds the priority section to langgraph.json.
langgraph-sdk 0.4.9
langgraph-sdk 0.4.9 adds Priority for thread priority settings.
llama.cpp Soprano TTS support
llama.cpp b11850 adds Soprano-80M and Soprano-1.1-80M audio generation models with a Qwen3 backbone.
mcp-toolbox v1.15.0
Adds conversational-analytics data agent tools, Looker saved query support, and MCP Apps UI support.
sdk-v1.2.0
Anthropic released sdk-v1.2.0, adding message threads support and usage and cost reports by dimension.
sherpa-onnx v2.0.0
Adds NeMo transducer support, diacritization, hotword beam search, and Kokoro TTS demos.
vertex-sdk-v1.1.0
Anthropic released vertex-sdk-v1.1.0, adding support for message threads.
Google Meet speech translation
Gemini-powered speech translation in Google Meet now supports 63 languages across web and mobile devices with automatic spoken language detection, individual participant controls, and synchronized translated captions, with listening support on Google Meet hardware devices.
Ollama speech and d3
Ollama v0.40.9 adds speech generation with Phonon on Apple Silicon, streams audio through the OpenAI-compatible /v1/audio/speech endpoint, and brings vLLM Semantic Router's d3 decision models in 2B, 4B, 9B, and 27B sizes.
Agents SDK v0.30.0
Agents SDK v0.30.0 runs PiHarness on Pi 1.4 with hibernation, parked tasks, storage error recovery, and retried model streams.
Agno v3.1.9
Adds POST /mcp/server/tools/{tool_name}/run to run any tool listed on the AgentOS Server Card over HTTP.
BigQuery AI.TRANSLATE
AI.TRANSLATE function for translating text strings is generally available in BigQuery.
Box and whisker charts in Google Sheets
Google Sheets added native box and whisker charts with quartile options and Excel import/export preservation.
Claude Agent SDK Python v0.2.172
Claude Agent SDK Python v0.2.172 bundles Claude CLI 2.1.308 and is on PyPI.
Claude Agent SDK Python v0.2.173
Updated bundled Claude CLI to version 2.1.309.
Claude Agent SDK TypeScript v0.3.308
Updated to parity with Claude Code v2.1.308.
Claude Agent SDK TypeScript v0.3.309
Claude Agent SDK TypeScript v0.3.309 released with fixes for managedSettings and extractFromBunfs, and parity with Claude Code v2.1.309.
Claude Code v2.1.309
Claude Code v2.1.309 fixes sandboxed Bash commands, macOS sandbox glob patterns, MCP config modification, and Bash permission checks.
Claude Models on Google Cloud (Anthropic managed)
Anthropic-managed Claude Models on Google Cloud is generally available with day-zero access to Claude models and platform features.
Cloudflare Tunnel Read And Monitor role
Granular Tunnel Read And Monitor role is generally available, adding log streaming to read access for specific Tunnels.
Devin Vulnerability Fixes plugin
Open-source Vulnerability Fixes plugin for Devin and any coding agent patches affected repos to verified fixed versions.
Dynamo v1.6.0
Dynamo v1.6.0 released with pluggable flow control, TensorRT-LLM OpenEngine API sidecars, vLLM LoRA lifecycle, and separate engine/runtime containers.
Feature Flags setup in Wizard
Set up Feature Flags from the Wizard, creating inactive example flags and framework-appropriate evaluations.
Gemini Enterprise single-user quota limits
Administrators can configure single-user quota limits on the Usage & Spending page to prevent one user from exhausting a shared quota pool.
GitHub Actions blob storage endpoints
GitHub Actions adds blob storage endpoints on github.com.
GitHub Copilot CLI 1.0.103-0
GitHub Copilot CLI v1.0.103-0 released with code block copy, cached MCP tool snapshots, remote launch flag changes, and sandbox setting fixes.
JetBrains Air Governance
JetBrains Air Governance is generally available with free and paid plans for organizational customers.
Kilo Code JetBrains 7.1.12
JetBrains 7.1.12 adds project-scoped agent usage aggregation, custom auto routers, and a session host registry.
Langfuse v4.68.0
Langfuse v4.68.0 adds listLlmConnections MCP tool, Treemap and Grid views for Topics, AI gateway socket write logging, and blob export score metadata.
Microsoft Agent Framework python-1.23.0
Adds allowlisted forwarding of function-invocation and client arguments from A2A request metadata and an opt-in synthetic trailing user turn.
Microsoft Entra ID connector
Microsoft Entra ID connector is available in Beta on Databricks.
OpenAI Java SDK v4.90.0
OpenAI Java SDK v4.90.0 adds voice deletion API and Kotlin compiler classloader reuse.
OpenAI Ruby SDK v0.110.0
OpenAI Ruby SDK v0.110.0 adds voice deletion and clarifies service-account API key deletion.
OpenHands v1.30.0
OpenHands v1.30.0 released with automation connection state and Cloud LLM profile fixes.
OpenHands v1.31.0
OpenHands v1.31.0 released with automation GitHub token hiding and MCP OAuth fixes.
OpenSearch Serverless 5-second refresh
Amazon OpenSearch Serverless now supports a 5-second default refresh interval.
Pinecone Documents API integrated embedding
Integrated embedding on the Pinecone Documents API with llama-text-embed-v2, multilingual-e5-large, and pinecone-sparse-english-v0.
Polaris 2.0
Polaris Web Components 2.0 is now available on the stable Polaris CDN channels.
Qwen Code v0.26.0
Qwen Code v0.26.0 adds session-targeted Skill and Extension refresh, workspace-isolated session warm-up, and a read-only preflight check.
Qwen SDK TypeScript v0.1.22
Qwen SDK TypeScript v0.1.22 released, bundling CLI version 0.26.0.
React Native render crash capture
Error Tracking captures fatal React render crashes in React Native 0.78 and later, including crashes that bypass the JavaScript error hook.
Retool 4.78 Edge
Retool 4.78 is now available on the Edge release channel for self-hosted organizations.
RunPod AP-JP-1 Fukushima
RunPod's first Japan data center is live in Fukushima with NVIDIA H200 GPUs and 8-50ms latency for Asia-Pacific users.
RunPod CPU Pods Docker and Network Volumes
RunPod CPU pods now support Docker runtime and network volumes.
RunPod GPU Pricing
RunPod lists per-hour GPU pricing for B300, H200, B200, and other instances.
RunPod Global Networking
RunPod launched Global Networking for secure pod-to-pod communication across data centers, live in CA-MTL-3, US-GA-1, US-GA-2, and US-KS-2 with a 100mbps link limit.
RunPod Serverless CPU
RunPod launched Serverless CPU with up to 3.75 GHz cores, DDR5 memory, and NVMe SSD storage.
RunPod Serverless Multi-GPU
RunPod Serverless now supports assigning two A100 or H100 80GB GPUs to a worker, or up to ten 24GB or 48GB GPUs.
SageMaker AI serverless customization
Amazon SageMaker AI now supports serverless model customization for Muse Glimmer, Qwen 3.8, and Ministral 3 models.
Scoped API Keys on RunPod
RunPod now supports scoped API keys with per-endpoint access, usage tracking, and on/off toggles.
Self-Hosted Orbs
Amp now lets users self-host orbs by running amp orb provider in their own infrastructure.
Self-hosted Retool 4.34 and 4.0 stable
Retool 4.34.10 and 4.0.23 are now available on the Stable release channel with bug fixes and security patches.
Shopify POS reactive storage
Adds shopify.storage.current API for reactive storage access in POS UI extensions using API version 2026-10.
Shopify s-pos-list
Adds s-pos-list virtualized list component for POS UI extensions in API version 2026-10 and Shopify POS 11.17.0.
Simpler MCP installations
Wizard detects local coding agents such as Claude Code and Codex, then installs the PostHog MCP connection by default.
Stable Diffusion XL 1.0 on RunPod
Stable Diffusion XL 1.0 is live on RunPod with full support in the Fast Stable Diffusion template.
TensorRT-LLM v1.4.0rc1
TensorRT-LLM v1.4.0rc1 adds DeepSeek-V4.1-Flash, NVFP4 GLM-5.3-Flash, and Qwen3.8-Flash-Next support.
Ultralytics v8.4.184
v8.4.184 reads multi-page grayscale TIFFs as their first page unless every band is requested.
Vercel CLI accountless deploy
Deploy apps or single files to Vercel without an account using vercel deploy --temporary, with one-hour expiry.
harness-cli/v0.2.2
harness-cli/v0.2.2 released with decision usage in invocation context, experimental OpenAI Live provider, and docs-verifier skill.
harness-python/v0.3.2
harness-python/v0.3.2 released with consolidated agent tool streaming, decision usage in invocation context, and experimental OpenAI Live provider.
langchain-core 1.7.0
Tool-call args now stream as tool-call-delta slices instead of block-delta snapshots.
mistral-vibe v3.0.2
Added enable_mouse_capture, max_subagents, and max_concurrent_subagents settings; VS Code connectors needing no login now connect in one click.
openai-node v7.42.0
Adds voice deletion API feature and bug fixes.
openai-ruby v0.111.0
openai-ruby v0.111.0 released with breaking changes to Live response question instructions and Decisions request inputs.
ChatGPT Ads
ChatGPT Ads expands to 26 additional countries, extending availability to 89 countries worldwide, with over 100,000 advertisers having run campaigns since launch just over eight months ago.
AI Runtime
Databricks AI Runtime is generally available.
AWS Neuron 2.33
AWS Neuron 2.33 adds native PyTorch support and Neuron Observer.
Agno v3.1.8
Added PostgresCheckpointStore for storing sandbox checkpoints in PostgreSQL, opt-in and available now.
Anthropic Bedrock SDK v1.0.0
Anthropic Bedrock SDK v1.0.0 released with support for API version and breaking changes.
Anthropic Foundry SDK v1.0.0
Anthropic Foundry SDK v1.0.0 released with support for API version and breaking changes.
Anthropic Google Cloud SDK v1.0.0
Anthropic Google Cloud SDK v1.0.0 released with support for API version and breaking changes.
Anthropic Java SDK v3.0.0
Anthropic Java SDK v3.0.0 adds support for API version , a workspace_id filter, and usage_tier scope type.
Anthropic Java SDK v3.1.0
Anthropic Java SDK v3.1.0 adds enforcement status, actions, and filter to user profiles, plus GraalVM native image support.
Anthropic Python SDK v2.0.0
Anthropic Python SDK v2.0.0 adds support for API version and a workspace_id filter for spend limits.
Anthropic TypeScript SDK aws-sdk-v1.0.0
Anthropic released aws-sdk-v1.0.0 with support for API version .
Anthropic TypeScript SDK v1.0.0
Anthropic TypeScript SDK v1.0.0 released with support for API version and breaking changes.
Anthropic TypeScript SDK v1.1.0
Anthropic TypeScript SDK v1.1.0 adds enforcement status, actions, and filter to user profiles.
BAND AI kit for Docker Sandboxes
The official BAND AI kit for Docker Sandboxes is now available at docker.io/bandhq/band-python-kit:latest.
Basin SQL OFFSET support
Basin SQL now supports OFFSET to skip a specified number of rows when retrieving query results.
BigQuery ObjectRef GA
BigQuery ObjectRef and multimodal data analytics are now generally available, enabling unstructured data analysis in SQL.
Claude Agent SDK Python v0.2.170
Fixed parallel tool calls missing from session messages and updated bundled Claude CLI to 2.1.306.
Claude Agent SDK Python v0.2.171
Python SDK v0.2.171 bundles Claude CLI 2.1.307 and is installable from PyPI.
Claude Agent SDK v0.3.306
Updated to parity with Claude Code v2.1.306.
Claude Agent SDK v0.3.307
Claude Agent SDK v0.3.307 adds wakeup_source, scheduled_for, and supportedDialogKinds, with parity to Claude Code v2.1.307.
Claude Code v2.1.307
Claude Code v2.1.307 adds /claude-api api-version, a safety_event OpenTelemetry event, and fixes for model aliases, beta headers, and MCP authentication.
Docs Live in Google Docs mobile
Docs Live voice drafting is now rolling out to eligible Workspace users on Android and iOS.
Gemini Notebook Slide Decks and Video Overviews
Gemini Notebook now offers step-by-step creation for Slide Decks and Video Overviews with guided customization and outline review.
GitHub Copilot CLI 1.0.102
Copilot CLI 1.0.102 honors managed Auto model selection and fixes sandboxed command reliability past 10 seconds.
GitHub Copilot CLI v1.0.102-0
Copilot CLI v1.0.102-0 fixes proxy handling, plugin marketplaces, shell completion, chat blocking, and sandboxed command reliability.
Google ADK Java v1.13.0
Google ADK Java v1.13.0 adds workflow graph builders and single-node execution.
Google Meet mobile video tile pairing
Google Meet mobile now supports video tile pairing on iOS and Android, with Android rollout started and iOS starting .
Langfuse v4.67.0
Langfuse v4.67.0 adds simplified CLI install for skills, name search and gateway key filter for API keys.
LiteLLM v1.105.3
LiteLLM released v1.105.3.
Lovable Organizations
Enterprise companies can now group multiple Lovable workspaces into an organization with SSO, SCIM, and centralized admin.
Lovable Supabase Creation
Users can now ask Lovable to create a Supabase project for an app with no backend, choosing organization and region.
Lovable department adoption insights
Workspace admins and owners on Business and Enterprise plans can now see adoption by department in Insights when using SSO without SCIM.
Lovable organizations and Supabase creation
Lovable now lets enterprise companies group workspaces into an organization with SSO and SCIM, and can create Supabase projects for apps without a backend.
MCP Inspector 2.12.0
MCP Inspector 2.12.0 fixes three vulnerabilities affecting every v2 release from 2.0.0 through 2.11.0.
MLX-VLM v0.7.10
MLX-VLM v0.7.10 adds Muse Spark Open support with audio/video/images and native Flint BF16 support.
MLflow 3.17.2
Record dataset, scorer, and agent lineage on mlflow.genai.evaluate runs.
Mammoth-1 and Elephant-1 on AI Gateway
Baseten's Mammoth-1 (27B) and Elephant-1 (9B) decision models are free on Vercel AI Gateway through , with 16k context.
Model Armor custom org policies
Custom organization policies for Model Armor Template resources are generally available.
OCI GenAI no-auth applications
OCI Generative AI hosted applications can now be created with No authentication for public content.
OCI GenAI persistent file storage
Hosted applications in OCI Generative AI can now add up to 50 GB of persistent file storage.
OKE GPU maintenance event repair
OKE can coordinate maintenance event repair for eligible bare metal GPU worker nodes in enhanced clusters.
Ollama v0.40.8
Ollama v0.40.8 adds Flint model support for MLX.
OpenAI Java SDK v4.88.0
OpenAI Java SDK v4.88.0 adds custom voice consent management.
OpenAI Java SDK v4.89.0
OpenAI Java SDK v4.89.0 adds Vertex AI support for the Responses API.
OpenAI Node SDK v7.40.0
OpenAI Node SDK v7.40.0 adds 30-minute cache-write usage counts, compaction trigger IDs, and custom voice consent management.
OpenAI Python SDK v3.36.0
OpenAI Python SDK v3.36.0 adds Vertex AI support for the Responses API and 30-minute cache-write usage counts.
OpenAI Ruby SDK v0.108.0
OpenAI Ruby SDK v0.108.0 adds a bounded Chat Completions tool runner and custom voice consent management.
OpenAI Ruby SDK v0.109.0
OpenAI released openai-ruby v0.109.0 with Vertex AI support for the Responses API.
Pydantic AI v1.107.9
Fixed GHSA-4whf-38hw-pxxh where attacker-controlled HTML in web_fetch could delay unrelated work.
Pydantic AI v2.59.0
Fixed GHSA-4whf-38hw-pxxh where attacker-controlled HTML in web_fetch could delay unrelated work.
Qwen Code Desktop v0.26.0
Qwen Code Desktop v0.26.0 released with session-targeted Skill and Extension refresh, managed-agent configuration template, and local/SSH workspace file references.
Ray 2.57.1
Ray 2.57.1 fixes out-of-scope block callbacks and adds google-cloud-cli to base-extra images.
Ray 2.58.1
Ray 2.58.1 fixes out-of-scope block callbacks and adds google-cloud-cli to base-extra images.
SAP CX Q3 2026 AI Assistants
Deal Qualification Assistant and Case Management Assistant are now available to select customers.
SageMaker AI custom sequence lengths
Amazon SageMaker AI now supports custom sequence lengths for serverless model customization jobs.
Snowflake AIM Application
Snowflake AIM application in public preview, a dedicated data migration surface with guided workflow and AI remediation.
Supabase .NET SDK v8
Supabase .NET SDK v8.0.0 unifies all packages under one version and adds a dependency injection extension.
Unity Gateway jailbreak screening
Unity Gateway can now screen MCP tool calls and results for jailbreak and prompt injection attempts.
cua-driver-rs v0.26.0
Prebuilt binaries for macOS, Linux, Windows, and Node.js SDK are published.
langchain 1.4.7
langchain 1.4.7 released with tool-call-delta read in stream consumers and dependency bumps.
openai-go v3.85.0
Vertex AI support for the Responses API in openai-go.
openai-go v3/vertex v1.0.0
Vertex AI support for the Responses API in openai-go.
openai-node v7.41.0
Vertex AI support for the Responses API in openai-node.
@openai/agents-core@0.21.0
Released @openai/agents-core@0.21.0 with fixes for token usage accounting and removal of Runloop sandbox provider.
@openai/agents-extensions@0.21.0
Minor release removes the Runloop sandbox provider and preserves Twilio audio format defaults.
@openai/agents-openai@0.21.0
Patch release preserves nested token usage breakdowns and image detail in OpenAI Conversations sessions.
@openai/agents-realtime@0.21.0
Patch release fixes WebRTC connection rejection, Twilio audio defaults, and updates the browser bundler to Vite 8.
@openai/agents@0.21.0
Released @openai/agents@0.21.0 with updated dependencies.
Agno v3.1.7
OSManager tool_call_limit defaults to 8 and member_tool_call_limit to 24; CartesiaTools defaults to sonic-3.6.
Anthropic Go SDK v1.83.0
Adds data_refreshed_at and has_more to analytics report pages, workspace rate-limit updates to Admin API, and makes User Profiles generally available.
Anthropic Google Cloud SDK v0.2.0
Uses v1 endpoints and adds the organization endpoint.
Anthropic Python SDK v1.16.0
Anthropic Python SDK v1.16.0 adds data_refreshed_at and has_more to analytics report pages, workspace rate-limit updates, and makes User Profiles generally available.
Anthropic TypeScript SDK v0.136.0
Adds data_refreshed_at and has_more to analytics report pages, workspace rate-limit updates to Admin API, and makes User Profiles generally available.
Azure DevOps Plugin for Microsoft Copilot
Azure DevOps Plugin is now available in Microsoft Copilot, bringing Azure DevOps into Copilot Chat, Cowork, and Code.
Bedrock Advanced Prompt Optimization
Amazon Bedrock Advanced Prompt Optimization now supports prompt shortening.
Bedrock Guardrails Standard tier
Amazon Bedrock Guardrails now supports Standard tier for contextual grounding checks.
Claude Agent SDK Python v0.2.169
Claude Agent SDK Python v0.2.169 released with bundled Claude CLI 2.1.305 and hash-pinned release build tools.
Claude Agent SDK TypeScript v0.3.305
Claude Agent SDK TypeScript v0.3.305 released with fixes and parity with Claude Code v2.1.305.
Claude Code v2.1.305
Claude Code v2.1.305 adds sandbox.allowNestedUserNamespaces and CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS, and fixes provider request failures.
Dependabot alerts REST API
Dependabot alert responses now include a version_requirement field with the version or version constraint recorded for the alert.
Dependabot package manager support
Dependabot now supports npm 12, pnpm 11 and 12, and Bun 1.4 for all github.com users.
ElastiCache Serverless for Valkey
Amazon ElastiCache Serverless for Valkey now supports online migration with zero downtime.
FastMCP v3.4.10
FastMCP v3.4.10 backports authorization checks after transforms and prevents denied concrete resources from being served by matching templates.
FastMCP v3.4.11
FastMCP v3.4.11 requires certifi 2026.10.19 or later for its HTTP stack and certifi-backed integrations.
FastMCP v4.1.2
FastMCP v4.1.2 applies component authorization after transforms and prevents denied resources from falling through matching templates.
Gemini CLI v0.65.0
Gemini CLI v0.65.0 released with fixes for untrusted folder workspace settings, session resumption, and OAuth validation.
Gemini Enterprise: Antigravity Enterprise Gateway
Gemini Enterprise now supports Antigravity Enterprise Gateway for routing model inference requests.
GitHub Copilot CLI 1.0.101
Native structured output for dynamic workflow subagents and assistedApprovalInstructions setting.
GitLab AI Governance Dashboard
GitLab AI Governance Dashboard is now in beta, showing agent activity across top-level groups.
Horizon Context
Metadata connectors for 18 sources and automatic description propagation are now in public preview.
Langfuse v4.65.0
Langfuse v4.65.0 adds non-blocking clustering, topic naming, recovery option, stabilized skills API, and self-hosted ingestion mode.
Lovable workspace publishing policies
Enterprise workspace admins can now block publishing or require approval for apps with personal data findings, external collaborators, public apps, connectors, or unverified email domains.
Metaobject analytics queryable capability
GraphQL Admin API version 2027-01 adds analytics queryable capability for metaobject definitions.
Mistral Vibe v3.0.1
Mistral Vibe v3.0.1 adds enable_auto_approve and compaction settings including compaction_max_output_tokens 80000 and output_token_reserve 4096.
Nemotron 3.5 Super VL on OCI
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 can now be imported into OCI Generative AI for image and text understanding.
OCI Generative AI CPU-only regions
CPU-only access to on-demand models is now supported in 30 OC1 commercial regions via routing profiles.
OCI Generative AI Sandboxes
Managed temporary Linux sandboxes are now available in OCI Generative AI for running code and shell commands.
OpenHands v1.29.0
OpenHands v1.29.0 released with agent profile skills, condenser, verification, and model router options.
Polly Generative engine
Polly Generative engine upgraded with more natural speech, 14 new voices, and 2 new languages.
Pydantic AI v1.107.8
Fixed MCP request telemetry exposure of server URLs, tokens, and headers in OpenTelemetry traces.
Pydantic AI v2.58.0
Fixed MCP request telemetry exposure of server URLs, tokens, and headers in OpenTelemetry traces.
Qwen3.6-35B-A3B-FP8 on OCI
Qwen/Qwen3.6-35B-A3B-FP8 can now be imported into OCI Generative AI for image and text understanding.
RunPod Clusters
RunPod launched Clusters, allowing up to 8 nodes and 64 H100s with high-speed interconnects.
RunPod GPU Price Cuts
RunPod reduced Serverless and Secure Cloud GPU prices by up to 40%, with H100 SXM5 now $3.99/hr.
Ultralytics 8.4.183
Ultralytics 8.4.183 updates Axelera SDK to 1.9.0 and supports every YOLO26 task.
anthropic-sdk-go v1.84.0
Go SDK v1.84.0 adds org webhook endpoints and user profile enforcement events.
anthropic-sdk-java v2.75.0
Java SDK v2.75.0 adds org webhook endpoints and user profile enforcement events.
bedrock-sdk v0.36.0
Anthropic Bedrock SDK v0.36.0 sends user_profile_id in the request body on AnthropicBedrockMantle Messages and token counting requests.
copilot-cli v1.0.101-1
GitHub released copilot-cli v1.0.101-1 with faster session resuming, sandboxed MCP server startup, and permission prompt fixes.
llm-d 1.0
llm-d 1.0 open-source distributed inference stack with cache-aware routing and tiered KV cache is available.
openai-go v3.83.0
Adds 30-minute cache-write usage counts, compaction trigger IDs, raw WebSocket helpers, and base64 embedding vector decode fix.
openai-java v4.87.0
OpenAI Java SDK v4.87.0 adds 30-minute cache-write usage counts, compaction trigger IDs, and complete JSON property access.
vertex-sdk v0.22.0
Anthropic Vertex SDK v0.22.0 throws an AnthropicError when userProfiles or beta.userProfiles is read on AnthropicVertex.
Agno v3.1.5
Sandboxed ClaudeAgent and CodexAgent now accept a repository parameter and S3CheckpointStore keeps checkpoints in S3-compatible buckets.
Alyx on Google Cloud Marketplace
Alyx, the AI engineering agent in Arize AX, is now available on Google Cloud Marketplace.
Azure Monitor workspace metrics usage insights
Metrics usage insights for Azure Monitor workspace is generally available.
Claude Agent SDK TypeScript v0.3.304
Added suspendSseStream and resumeSseStream to browser SDK, stable row ids to getContextUsage, and startup timeout fixes.
Cloud Workload Security
Cloud Workload Security is now available in Beta, applying policy controls to cloud API requests.
Cloudflare API MCP server step-up authorization
The Cloudflare API MCP server now supports step-up authorization, available in all MCP clients that support it.
Databricks Runtime 19
Spark Connect DataFrame execution metrics now hide internal operators and metrics associated with row filters and column masks.
DeepSeek V4.1 Flash (1017)
DeepSeek V4.1 Flash (1017) is now available on Unity Gateway with text and image inputs.
DeepSeek V4.1 Flash 1017 on Workers AI
DeepSeek V4.1 Flash 1017 is available on Workers AI with a 1,048,576 token context window and 20 requests per minute default rate limit.
Docker Agent v1.151.0
Adds Atlas Cloud and API Route provider aliases, live background agent visibility, streaming file previews, and Command Code harness type.
Gemini 4 Argon in Retool
Gemini 4 Argon is available in Retool through Google and Google Vertex AI for Enterprise organizations that bring their own key.
Gemini app export to Google Sites
Interactive apps built in the Gemini app can now be exported directly to Google Sites as a new private site draft.
GitHub Copilot CLI 1.0.100
Copilot CLI 1.0.100 adds a disable-client-telemetry flag, trust-folder flag, plugin install links, and a full-screen share menu.
GitHub Copilot CLI 1.0.101-0
Native structured output for dynamic workflow subagents and assistedApprovalInstructions setting added; several model and MCP fixes.
GitHub Copilot model deprecations
Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini, and Grok 4.5 deprecated across most Copilot experiences.
Grok 4.7 on Bedrock GovCloud
Grok 4.7 is now available on Amazon Bedrock in AWS GovCloud (US).
Kilo Code v7.8.15
VS Code extension update adds browser_open permission remember choice and Agent Manager custom agent selection.
Langfuse v4.64.0
Langfuse v4.64.0 adds message comparison, project API key permissions by default, and gateway API key pagination.
MLX-VLM v0.7.9
MLX-VLM v0.7.9 adds Nemotron 3.5 Super VL support, live image resolution controls, and several vision model fixes.
Meeting recaps in Google Chat
Meeting recaps with summaries, action items, and artifact links are now available in Google Chat.
Mercury 3 on AI Gateway
Mercury 3 from Inception is available on AI Gateway with 50% off launch pricing and a 1M-token context window.
MiniMax M3.1 Flash on AI Gateway
MiniMax M3.1 Flash is available on AI Gateway for free until , with a 1M-token context window.
Mistral Vibe v3.0.0
Mistral Vibe v3.0.0 adds model compaction threshold reporting, project/session import, Lean agent install commands, and curated model catalog support.
OpenHands v1.28.0
OpenHands v1.28.0 adds Bahasa Indonesia locale, in-conversation secret requests, and reading-pace streaming.
Qodo v3.1
Automated rule deactivation, GA analytics dashboard, quick search, and expanded background activity reporting.
Qwen Code Desktop v0.25.3
Qwen Code Desktop v0.25.3 released with fixes and features.
Qwen SDK TypeScript v0.1.21
SDK TypeScript v0.1.21 bundles CLI version 0.25.3.
Transformers v5.20.2
Patch release v5.20.2 fixes input type loss in generate and zero expert gradients in bfloat16.
ogx v1.4.1
ogx v1.4.1 adds PostgreSQL connection URI support for SQL and key-value stores.
openai-java v4.86.0
Adds ultrafast service tier for Agents and opt-in bounded transport recovery for realtime.
Claude Agent SDK TypeScript v0.3.303
Claude Agent SDK TypeScript v0.3.303, updated to parity with Claude Code v2.1.303.
ComfyUI v0.42.0
ComfyUI v0.42.0 adds Krea 3 Image node, MOSS-image support, and Qwen 3.x performance improvements.
LiteLLM v1.106.0
LiteLLM v1.106.0 released with 778 commits since the previous release.
OpenAI Go SDK v3.82.0
OpenAI Go SDK v3.82.0 adds opt-in Realtime WebSocket recovery and bounded session recovery.
openai-node v7.39.0
openai-node v7.39.0 adds opt-in bounded connection recovery for realtime.
openai-python v3.35.1
openai-python v3.35.1 preserves beta Realtime byte reads on websockets.
Gmail AI Inbox
Gmail's AI Inbox is expanding to paid Google Workspace users starting , extracting action items and deadlines into suggested to-dos and summarizing priority topics.
Ollama v0.40.5
Ollama v0.40.5 adds NVIDIA Nemotron 3.5 Super, a 120B-parameter vision-language model with 12B active per token, and Nemotron 3.5 Bolt, a 74B-parameter model tuned to fit a 24GB NVIDIA GPU.
Claude Code v2.1.302
Claude Code v2.1.302 adds CLAUDE_CODE_AUTO_MODE_MODEL to choose the client-side auto mode classifier model and fixes image files over 128 MB being loaded entirely into memory.
Codex rust-v0.163.0
Codex rust-v0.163.0 enables Daybreak by default for eligible accounts, adds a configurable leader key with Ctrl+X as default, and lets you send a follow-up while Codex is responding.
Xcode 27 runner image
The Xcode 27 runner image is now generally available in GitHub Actions, running on macOS 27 with the Xcode 27 toolchain and Apple SDKs on Apple Silicon runners only.
Cline SDK v0.0.95
SDK v0.0.95 sends max_completion_tokens for GPT-6 models and refreshes the model catalog to 7,041 models.
DeepSeek V4.1 Flash 1017 on AI Gateway
DeepSeek V4.1 Flash 1017 is available on AI Gateway as deepseek/deepseek-v4.1-flash-1017.
OpenAI Java SDK v4.85.0
OpenAI Java SDK v4.85.0 adds typed Live sideband events and beta connections.
OpenAI Python SDK v3.33.0
Adds safety identifiers to image requests and responses, and shares Decisions cache breakpoint parameter type.
OpenAI Python SDK v3.34.0
Adds degraded external storage status and Realtime Translation WebSocket sessions.
OpenAI Python SDK v3.35.0
OpenAI Python SDK v3.35.0 adds typed Live sideband events and an ultrafast service tier for Agents.
OpenAI Ruby SDK v0.106.0
OpenAI Ruby SDK v0.106.0 adds Decisions prompt caching options, degraded external storage status, typed Live sideband events, and ultrafast service tier for Agents.
llama.cpp HF Hub model discovery
llama.cpp b11714 adds UI to discover and download models from Hugging Face Hub.
openai-go v3.80.0
Adds Decisions delegation, triggers, Live events, prompt caching options, degraded external storage status, and Realtime and Translation WebSocket connections.
openai-go v3.81.0
openai-go v3.81.0 adds typed Live sideband events, beta connections, and an ultrafast service tier for Agents.
openai-node v7.36.0
Adds safety identifiers to image requests and responses.
openai-node v7.37.0
Adds degraded external storage status and uses generated Translation bindings for Realtime.
openai-node v7.38.0
openai-node v7.38.0 adds typed Live sideband events.
openai-ruby v0.105.0
Adds safety identifiers to image requests and responses.
Agno v3.1.4
ClaudeAgent and CodexAgent now run in an isolated per-session sandbox with state that survives container or host loss.
Amp Runner Desktop
Amp users can now see and control their macOS or Linux runner's desktop.
Beam on SageMaker JumpStart
Reflection's Beam model is now available on Amazon SageMaker JumpStart and AWS Trainium.
Beam-1.0 on Baseten
Reflection's Beam-1.0 is available via Baseten Model APIs with a 1M-token context window, tool calling, and always-on reasoning.
CLI v3.0.72
Plugins now run in a worker, provider errors retry up to 3 times, and cline hub gains JSON output and port fallback flags.
Checkout MCP and Cart MCP UCP consent
Checkout MCP and Cart MCP now support the UCP buyer consent extension starting with UCP .
Claude Agent SDK v0.3.302
Claude Agent SDK v0.3.302 fixes structured output error handling, changes permissionMode default, enables fork subagents by default, and updates to Claude Code v2.1.302 parity.
Cline Cloud sessions
Cline v4.1.25 adds Cline Cloud sessions, rolling out gradually: run a task in a hosted sandbox on a GitHub repo and branch you pick.
Cline Desktop v0.0.47
Cline Desktop v0.0.47 fixes marketplace plugin loading and sets the Cline provider default model to Gemini 4 Argon.
Cline SDK v0.0.94
Plugins now run only in worker threads or subprocess sandbox; in_process mode removed.
Conversational analytics in BigQuery
Conversational analytics in BigQuery is now available in northamerica-northeast1 (Montréal) and northamerica-northeast2 (Toronto).
Dialogflow gemini-3.5-flash-lite
gemini-3.5-flash-lite is generally available in Dialogflow.
Elorian Glimpse on AI Gateway
Elorian's visual reasoning model Glimpse is available on AI Gateway as elorian/glimpse.
Gemini Enterprise Workflow Builder
Workflow Builder can connect to Confluence Data Center and Jira Data Center to search data and automate actions.
GitHub Copilot CLI 1.0.100-1
Pre-release 1.0.100-1 ships unified Sessions browser by default, 500-record account discovery cap, and proxy fixes.
GitHub Copilot CLI v1.0.99-3
GitHub Copilot CLI v1.0.99-3 adds --disable-client-telemetry flag and fixes.
GitHub Copilot in Slack and Teams
Multi-repo support, natural mentions, smoother repository switching, Slack context, and reliability improvements for GitHub Copilot in Slack and Microsoft Teams.
Kilo Code JetBrains 7.1.11
JetBrains 7.1.11 adds remote agent listing for mobile and bundles Kilo CLI v7.8.13.
KoboldCpp 1.123.1
KoboldCpp 1.123.1 adds a community website and support for Qwen Image 2.1 image generation and editing.
Langfuse v4.61.0
Langfuse v4.61.0 adds AI gateway routing by connection slug and a dedicated traces skills tab.
Langfuse v4.62.0
AI gateway request limit raised to 16 MiB and execution limits made configurable.
Langfuse v4.63.0
Langfuse v4.63.0 routes slugless codex models to OpenAI connections and adds AI gateway error attribution.
MCP gateway for OpenShift
Model Context Protocol gateway for Red Hat OpenShift is generally available.
NVIDIA RTX Spark
RTX Spark systems with GB10 and up to 128GB unified memory are available for purchase.
Neon Realtime and AI Gateway models
Neon Realtime public beta and 11 new AI Gateway models including claude-sonnet-5-5, gpt-6-sol, and gemini-3-7-flash.
Netlify Support Hub
Netlify launched Support Hub for Enterprise teams to create, track, and reply to support tickets.
Open WebUI v0.12.3
End-to-end encrypted chats for direct messages and private group channels, with MLS encryption and 16 KiB message limit.
OpenAI Go SDK v3.79.0
OpenAI Go SDK v3.79.0 adds prompt-based voice creation, regional processing residency options, and response error diagnostics.
OpenAI Node SDK v7.35.0
OpenAI Node SDK v7.35.0 adds Decisions prompt caching, prompt-based voice creation, response error diagnostics, audio fixture playback, Decisions in Live sessions, and project API key scope updates.
Perplexity Decider V1.2 on AI Gateway
Perplexity Decider V1.2 27B and Decider Flash V1.2 4B are now available on AI Gateway.
Pydantic AI v2.57.0
Pydantic AI v2.57.0 adds MetaProvider for Meta Muse models and updates realtime session handling.
Reflection Beam on AI Gateway
Reflection AI's Beam model is available on AI Gateway free for a limited time, with 1M-token context and Apache 2.0 weights.
Replit Bring Your Own Cloud
Replit BYOC is available for development and production in Microsoft Azure, Google Cloud, or Amazon Web Services.
Sentry Agent Conversation sorting and filters
Sentry added sorting and filtering for agent conversations by total cost, tokens, and tool calls.
Transformers v5.20.1
Transformers v5.20.1 adds Beam model support and fixes loading on older torch versions.
TypeSafe AI Jev 1.14.0
TypeSafe AI Jev 1.14.0 is now available on Unity Gateway.
TypeSafe Jev 1.14.0 on AI Gateway
TypeSafe Jev 1.14.0 is available through Netlify AI Gateway with zero configuration and billed to Netlify credits.
langgraph 1.2.16
langgraph 1.2.16 released with fixes for resume handling and checkpoint-postgres prune support.
langgraph-cli 0.4.36
langgraph-cli 0.4.36 released with fixes for serverless and dedicated deployment aliases and Docker context in langgraph deploy.
langgraph-sdk 0.4.8
langgraph-sdk 0.4.8 released with a fix to surface thread stream errors and stop retrying rejected streams.
openai-python v3.32.0
Python SDK v3.32.0 adds cache settings, prompt-based voice creation, regional processing residency, response error diagnostics, and Live session audio fixture playback.
openai-ruby v0.104.0
Ruby SDK v0.104.0 adds beta session spending limits, prompt-based voice creation, regional processing residency options, and more.
supervision-0.31.0
supervision 0.31.0 adds DepthMap, moving camera support for PolygonZone and LineZone, and KeyPointMeanAveragePrecision.
ADBC driver for Power BI
ADBC driver for Power BI is generally available and is the default driver for new connections.
AWS Transform for migrations
AWS Transform for migrations is now available in Asia Pacific (Singapore).
Amazon S3 Metadata
Amazon S3 Metadata is now available in six additional AWS Regions.
Amazon Time Sync Service
Microsecond-accurate time now supports 135 additional EC2 instance types in all commercial regions.
Anthropic Go SDK v1.82.0
Anthropic Go SDK v1.82.0 adds the speed parameter and usage.speed to Messages.
Anthropic TypeScript SDK v0.135.0
Adds between_tools to thinking types, speed parameter, usage.speed, and spend limit; fixes stream closing.
Anthropic models in Gemini Enterprise
Claude Opus 5.5 and Claude Sonnet 5.5 are available in the Gemini Enterprise app after an administrator enables them.
BGP Route Filtering for IPsec/GRE
Cloudflare WAN and Magic Transit IPsec and GRE tunnels now support BGP import and export filtering.
BigQuery cross-region table copy
BigQuery users can now copy tables across regions, generally available.
Browser Use 0.13.12
Release 0.13.12 adds OpenAI browser tools backed by Browser Use Actor, installable via browser-use[openai-tools].
Browser Use 0.13.13
Release 0.13.13 adds the OpenAI browser-tool driver and fixes Cloud navigation and scaled display alignment.
Cat Jam on AI Gateway
Cat Jam, a reasoning model for coding and agentic tasks, is now available free in stealth on AI Gateway.
Claude Code v2.1.301
Claude Code v2.1.301 adds retry watchdog usage limit wait, OpenTelemetry tracing guidance, vim % motion, and multi-line input.
Cloudflare Gateway Custom Applications
Custom applications can now be created in the Application Library and referenced in Gateway DNS, Network, and HTTP policies.
Devin Oncall
Devin Oncall is generally available, achieving 100% end-to-end success on SREGym with fastest time to mitigation.
Disco Diffusion on RunPod
RunPod added a template for running Disco Diffusion, with A5000 GPUs recommended and $25 suggested starting credit.
DreamBooth on RunPod Fast SD
RunPod added a guide and template for training DreamBooth models using the Runpod Fast Stable Diffusion template.
DynamoDB Streams timestamp-based processing
DynamoDB Streams now supports timestamp-based stream processing.
Figma Config India 2026 releases
Figma launched code layers, Specs, Payload in Make, and code sources, rolling out now across plans.
Figma Specs
Figma launched Specs, a multiplayer Markdown container on the canvas, rolling out now in open beta on paid plans.
GitHub AI Scan for pull requests
AI Scan for pull requests is generally available, finding vulnerabilities in languages CodeQL does not cover.
GitHub Copilot CLI v1.0.99-0
GitHub Copilot CLI v1.0.99-0 adds a full-screen share menu, session-scoped sandboxing, and automatic trusted plugin updates.
GitLab MCP server
GitLab MCP server is generally available on GitLab.com and self-managed, giving MCP-compatible agents access to the expanded GitLab tool catalog.
Google Drive CSE preview
Google Drive now previews client-side encrypted PDF and image files directly in the browser.
Haystack v3.4.0
Haystack v3.4.0 released with Python 3.15 support and ToolResultOffloadCompactor.
Invoke AI Stable Diffusion Template
RunPod added an easy deploy template for Invoke AI Stable Diffusion, launchable with an RTX A5000 GPU.
KTransformers v0.7.2
KTransformers v0.7.2 adds LoRA fine-tuning for DeepSeek-V4-Flash with native MXFP4 routed-expert forward and backward.
Kilo Code v7.8.12
Kilo Code v7.8.12 routes gateway traffic through ai-gateway.kilo.ai and adds Search Ignored Paths setting.
Lambda Durable Execution SDK for Go
AWS Lambda Durable Execution SDK for Go is now generally available.
Langfuse v4.60.0
Adds organization-level connections, billable unit ledger, CLI import instructions, and prompt cache hit rate display.
Liquid AI d1-ultra on AI Gateway
Liquid AI's d1-ultra is available on AI Gateway with a 32,768-token context window and input-only billing.
Lovable Growth tools
Growth tools in Lovable turn a goal like first 100 signups into a plan and can launch Google and Facebook ads.
Lovable audit log exports
Enterprise admins can schedule audit log exports to S3, GCS, Azure Blob, Splunk, or Azure Log Analytics.
MCP Events in Vercel Connect
Vercel Connect now supports MCP Events in public beta, allowing apps and agents to subscribe to webhook events from compatible MCP servers.
Microsoft Agent Framework Python 1.22.0
Microsoft Agent Framework Python 1.22.0 released with Python 3.15 support.
Muse Spark Open and Nemotron 3.5 Super VL
Meta Muse Spark Open and NVIDIA Nemotron 3.5 Super VL are available through Baseten Model APIs.
Muse Spark Open in llama.cpp
llama.cpp b11671 adds Muse Spark Open model support for text, vision, and audio.
Muse Spark Open on AI Gateway
Meta's Muse Spark Open is available on AI Gateway with 1M-token context and no training.
Muse Spark Open on SageMaker JumpStart
Muse Spark Open model is now available on Amazon SageMaker JumpStart.
NVIDIA Nemotron 3.5 Super VL
NVIDIA Nemotron 3.5 Super VL is now available on DigitalOcean Inference for serverless inference.
OpenAI Java SDK v4.82.0
OpenAI Java SDK v4.82.0 adds regional processing residency options, response error diagnostics, and model notices.
Pinecone BYOC on-demand mode
On-demand capacity mode for Pinecone BYOC is available now, with a shared pool holding millions of namespaces.
Pipecat PhoneLLM Mini on Workers AI
Pipecat PhoneLLM Mini is now available on Workers AI, built for voice agents and realtime AI applications.
Postman Code-Based Mocks
Postman Mock Servers can now be written in JavaScript, with state between requests, running locally, in CI, or in the cloud.
Qwen Code Desktop v0.25.2
Qwen Code Desktop v0.25.2 adds test failure report explorer and TypeScript authoring for mods.
RTX 5090 on RunPod
RunPod added the NVIDIA RTX 5090 to its GPU lineup, serving Qwen2-0.5B at 65,000+ tokens/sec and 250+ requests/sec.
RunPod Batch Jobs
Batch Jobs are in public beta with up to 5,000 requests per batch and 50,000 queued per endpoint.
Sentry React Native SDK Turbo Module insights
Sentry React Native SDK adds TurboModule Context integration recording native module calls, counts, errors, durations, and breadcrumbs.
Snowflake Postgres Data Mirroring
Postgres data mirroring is generally available, replicating Postgres tables into Snowflake in seconds.
Stream WebRTC live streaming
Ultra-low latency live video with WebRTC is generally available in Cloudflare Stream, with usage-based billing starting .
Stripe Data Pipeline for Supabase
Stripe Data Pipeline now syncs Stripe data to Supabase Postgres, with backfill and continuous sync.
TRL v1.16.0
TRL v1.16.0 adds AWS Trainium training support with pad_to_multiple_of defaulting to auto.
Transformers v5.20.0
Adds Muse Spark Open and Ling 3.0 Flash model support.
TypeSafe AI Jev 1.14 on AI Gateway
Jev 1.14 is available on AI Gateway with image input and experimental long-context mode.
Unity Gateway consumer access
Consumer access to query Unity Gateway services is generally available, no longer requiring an account admin to enable a preview.
VPC Service Controls
VPC Service Controls now supports folder membership and granular exceptions, generally available at no additional cost.
Vercel Connect Secure Compute
Vercel Connect now supports Secure Compute routing with dedicated static IP addresses for providers like Salesforce and Snowflake.
Vercel Drives
Vercel Drives, persistent storage for agents, is now generally available for Vercel Sandbox.
Vercel Token Pass
Vercel Token Pass is in early access for Pro teams at $30 per month with $80 monthly credit for GLM 5.3 and Kimi K3.
Web Search on Bedrock AgentCore
Web Search on Amazon Bedrock AgentCore expanded to AWS GovCloud and 3 regions.
langgraph-prebuilt 1.1.1
langgraph-prebuilt 1.1.1 released with fixes for ToolNode resume values and delta channel replay ordering.
llama.cpp v0.7.0
llama.cpp v0.7.0 adds LiliCorr speculative decoding, MTP for GLM5-Next, and a GPU cache for MoE experts with up to ~2.2x decode speedup.
AWS Backup for Amazon FSx in New Zealand
AWS Backup now supports Amazon FSx file systems in the Asia Pacific (New Zealand) Region.
Amazon S3 on Vercel Marketplace
Amazon S3 is now available in the Vercel Marketplace with OIDC authentication and $100 in credits for new AWS accounts.
Amazon S3 on Vercel Marketplace
Amazon S3 is now available on the Vercel Marketplace and v0 by Vercel.
Anthropic Go SDK v1.81.0
Anthropic Go SDK v1.81.0 adds OpenTelemetry spans for API calls, streams, and tool runs, on by default with a registered tracer provider.
Anthropic Java SDK v2.72.0
Java SDK v2.72.0 adds OpenTelemetry spans for API calls, streams, and tool runs, on by default.
Azure MCP Server 3.0
Azure MCP Server 3.0 stable released with Azure Backup, Resilience Management, and SRE Agent toolsets.
BigQuery Conversational Analytics agent
Publish a BigQuery Conversational Analytics agent in Gemini Enterprise.
BigQuery generative AI cost management
Daily quotas for AI input and output tokens per project and per user, with defaults up to 200 billion input tokens per day.
Claude Agent SDK TypeScript v0.3.299
Added nextFireAt to CronCreate and CronList outputs, property_order to elicitation control, and several fixes.
Claude Code v2.1.299
Added CLAUDE_CODE_DISABLE_FILE_MENTIONS, idle compaction for 200K+ token conversations, and CLAUDE_CODE_IDLE_COMPACT_MIN_TOKENS.
Claude Code v2.1.300
Claude Code v2.1.300 adds virtualText prompt decorations, cache write metrics, advisor on AWS, and mod UI features.
Copilot CLI v1.0.98
Copilot CLI v1.0.98 adds Gemini 4 Argon support and fixes command hooks, MCP sync, and session resume behavior.
CrewAI 1.15.28
CrewAI 1.15.28 adds a crewai eval command and uses the LiteLLM catalog for context windows.
Gemini 3.8 Flash in UK
Gemini 3.8 Flash is generally available in the United Kingdom, supported in europe-west2 with in-region at-rest data residency.
Gemini 4 Argon on GitLab
Gemini 4 Argon is now available on GitLab Duo Agent Platform, completing 93.3% of GitLab's software engineering benchmark tasks.
GitHub Copilot CLI 1.0.98-1
Added support for Gemini 4 Argon and fixed MCP status sync after split-view session switches.
GitHub Copilot CLI 1.0.98-2
GitHub Copilot CLI 1.0.98-2 adds Ctrl+E to expand /ask answers, Ctrl+Y to copy the entire answer, and reopens the last usable completed answer.
Google ADK Java v1.12.0
ADK Java v1.12.0 adds a Gemini context cache manager and experimental workflow types.
Graphiti v0.31.0
Graphiti v0.31.0 sets gpt-6-luna as the default OpenAI model.
Hydrogen 2026-10
Hydrogen 2026-10 is GA as a framework-agnostic JavaScript library with React Router and Next.js starters.
Lambda recursive loop detection
AWS Lambda recursive loop detection now supports Amazon EventBridge Custom event buses.
Nemotron 3.5 Lightning on AI Gateway
NVIDIA Nemotron 3.5 Lightning is now free on AI Gateway with 1M context and 30B parameters.
Open WebUI v0.12.1
External apps in channels, enabled via Admin Settings or ENABLE_APPS, with per-app permissions and channel manager control.
Open WebUI v0.12.2
MinerU 4.x server support and a Keep both button in Compare revision view.
OpenAI Node SDK v7.33.0
OpenAI Node SDK v7.33.0 adds browser and computer toolsets and beta session spending limits.
OpenAI Node SDK v7.34.0
OpenAI Node SDK v7.34.0 adds regional processing residency options.
OpenAI Python SDK v3.31.0
OpenAI Python SDK v3.31.0 adds browser and computer toolsets.
Power Pages plugin localization
The /add-localization skill adds multilingual support to Power Pages SPA sites in 43+ languages.
Raycast v2.8
File Search up to 6x faster, extension installs up to 30x faster, and 20% less startup memory.
Workspace-level package repositories
Workspace admins can configure default Python and npm package repositories for Databricks Apps, generally available .
anthropic-sdk-python v1.14.0
anthropic-sdk-python v1.14.0 adds execution_identity to Managed Agents, telemetry destinations to Admin API, and OpenTelemetry tracing.
aws-sdk-v0.8.0
Adds execution_identity to Managed Agents and OpenTelemetry spans for API calls.
bedrock-sdk-v0.35.0
Adds execution_identity to Managed Agents and OpenTelemetry spans for API calls.
claude-agent-sdk-python v0.2.166
claude-agent-sdk-python v0.2.166 adds hook-specific typed output classes and a fully typed SystemInitData for init system messages.
foundry-sdk-v0.6.0
Anthropic Foundry SDK v0.6.0 adds execution_identity to Managed Agents and OpenTelemetry spans for API calls.
google-cloud-sdk-v0.1.0
Anthropic Google Cloud SDK v0.1.0 adds execution_identity to Managed Agents and OpenTelemetry spans for API calls.
harness-python/v0.3.0
Released harness-python/v0.3.0 with Strands packaging for Claude, Codex, and Cursor, DecisionModel primitive, and MCP progress callbacks.
harness-sdk python/v1.61.0
Released python/v1.61.0 with Strands packaging for Claude, Codex, and Cursor, DecisionModel primitive, and MCP progress callbacks.
harness-sdk typescript/v1.21.0
Released typescript/v1.21.0 with Strands packaging for Claude, Codex, and Cursor, DecisionModel primitive, and MCP progress callbacks.
harness-typescript/v0.3.0
Released harness-typescript/v0.3.0 with Strands packaging for Claude, Codex, and Cursor, DecisionModel primitive, and MCP progress callbacks.
langchain-openai 1.7.2
langchain-openai 1.7.2 fixes keeping Responses stream items on one block when output_index drifts.
langgraph-checkpoint-postgres 3.2.0
Version 3.2.0 adds prune to PostgresSaver and AsyncPostgresSaver.
livekit-agents 1.8.7
livekit-agents 1.8.7 adds Claude Opus 5, Opus 5.5 and Sonnet 5.5 support and realtime E2E latency measurement.
openai-python v3.30.0
openai-python v3.30.0 adds beta session spending limits, OCI external-storage provider support, and organization Decisions usage reporting.
sdk-v0.134.0
Anthropic TypeScript SDK v0.134.0 adds execution_identity, telemetry destinations, and OpenTelemetry spans on by default.
vertex-sdk-v0.21.0
Anthropic Vertex SDK v0.21.0 adds execution_identity to Managed Agents and OpenTelemetry spans for API calls.
AI Search in LangSmith
AI Search in LangSmith lets users query agent traces by describing behaviors in natural language.
AWS Agent Registry custom metadata
AWS Agent Registry now supports custom metadata for registry records.
Apple TV 4K with Siri AI
New Apple TV 4K with Siri AI, faster performance, and hands-free far-field microphones; pre-orders start today, availability .
Autonomous Database Storage Cache Metrics
Storage cache read-hit and write-hit metrics are now available for Autonomous Database Serverless.
BigQuery AI.AGG function
The AI.AGG function is generally available in BigQuery for semantic aggregation of unstructured input data.
CLI v3.0.71
Plugins now load inside the hub, plugin failures are reported, and --thinking applies in ACP mode.
Cline Desktop v0.0.46
Desktop v0.0.46 adds prompt navigation, plugin error status, cloud sign-in cancel, and routine fixes.
Cline SDK v0.0.93
Cline SDK v0.0.93 loads plugins in-process with timeouts, error capture, and plugin state tracking.
Cline v4.1.24
Cline v4.1.24 defaults Cline and OpenRouter to Claude Sonnet 5.5, adds Claude Haiku 5.5, and refreshes providers.
Code scanning AI Scan metrics
AI Scan metrics in security overview show findings, remediation rate, repositories, trends, and autofix usage.
Databricks AI Runtime SDK
Databricks AI Runtime SDK replaces serverless_gpu in GPU environment version 6, with renamed arguments and deprecation warnings.
Drama 3 on AI Gateway
Fish Audio's Drama 3 text-to-speech model is available on AI Gateway at 80% off for 30 days.
Gemini 4 Argon in Devin
Gemini 4 Argon is live in Devin Desktop and CLI at 75% off list price through .
Gemini 4 Argon in Figma Make
Gemini 4 Argon is rolling out in Figma Make, available on all plans via the model picker.
Gemini 4 Argon in GitHub Copilot
Gemini 4 Argon is now generally available in GitHub Copilot for Pro+, Max, Business, and Enterprise users.
Gemini 4 Argon on AI Gateway
Gemini 4 Argon is available on AI Gateway with a 1M token context window and thinking levels.
Gemini 4 Argon on Google Cloud
Gemini 4 Argon is available on Google Cloud for business use.
Gemini 4 Argon on Netlify
Gemini 4 Argon is available in Netlify AI Gateway and Agent Runners with zero configuration.
Google Gemini 4 Argon on Unity Gateway
Google Gemini 4 Argon is now available on Unity Gateway via Foundation Model APIs.
Google Meet Android role switching
Google Meet on Android now lets eligible live stream viewers switch to contributing with audio and video.
Google Play Game finder
Game finder begins rolling out to English-language users in the US today.
Lambda durable functions payload limits
AWS Lambda durable functions increased durable operation and checkpoint payload limits.
LangChain MCP support
MCP support moved into langchain.mcp with stateless spec, caching, and elicitation.
Langfuse v4.58.0
Langfuse v4.58.0 adds Turnstile on password-reset emails, per-project trace idle time, and Topics on project LLM connections.
Lovable Files tab image editing
Edit images directly in the Files tab by marking changes, pinning comments, erasing, or removing backgrounds.
Lovable WebMCP browser agent tools
Lovable now lets browser agents use your app via WebMCP tools, starting with read-only or easy-to-undo actions.
MAI-Image-2.6 on AI Gateway
MAI-Image-2.6 and MAI-Image-2.6-Flash are available on AI Gateway with up to 1536x1536 output and five reference images.
MLX-VLM v0.7.8
MLX-VLM v0.7.8 adds Kolibri1 and EmbeddingGemma 2 multimodal embedding support.
MLflow 3.17.1
MLflow 3.17.1 adds Decision API support in make_judge and review queue management, plus tracing and scorer fixes.
Mistral Large 4 in Agent Runners
Mistral Large 4 is available in Netlify Agent Runners with a 524K-token context window.
NVIDIA Run:ai open source
NVIDIA released the full Run:ai platform as open source, including KAI Scheduler, GPU Fractioning Operator, KAI Resource Management, and Workload Map.
Open SWE
Open SWE, an open-source framework for internal coding agents, is released today.
Puck MCP
Puck is now available via MCP in ChatGPT, Claude, and other agents.
Pydantic AI v2.56.0
Pydantic AI v2.56.0 adds Skills layering, ZaiProvider base_url, PGTaskDurability, and Render Workflows integration.
ScaleDown in LangChain
langchain-scaledown integration and LangSmith LLM Gateway support for ScaleDown constrained decoding models.
Sentry Android SDK Nav3 Support
Sentry Android SDK 8.60.0 adds SentryNavEffect for Jetpack Navigation 3 to record navigation transactions, breadcrumbs, screen names, and back stack context.
SharePoint Embedded MCP server
SharePoint Embedded MCP server is now available in public preview for building and managing apps with a coding agent.
Shop MCP
Shop MCP is live at mcp.shop.com with 17 tools for search, carts, and Shop Pay checkout.
Supabase Grok Bot Integration
Supabase integrates Grok Bot with Cursor to ship backend changes via chat.
TanStack Start on Netlify
TanStack Start 1.0 apps deploy on Netlify with SSR, server routes, server functions, and middleware on Netlify Functions.
Unity REST API external view access
External engines can query Unity Catalog views over Delta Lake tables through the Unity REST API.
langsmith-sdk v0.14.8
Adds customer-managed KMS keys for sandbox and fixes session_id on RunTree.patch.
openai-java v4.81.0
openai-java v4.81.0 adds organization Decisions usage reporting and shida named Live voices.
API Shield schema learning on demand
API Shield users can now manually request a schema learning run on demand.
Agno v3.1.3
Agno v3.1.3 adds durable external agent sessions so ClaudeAgent sessions resume on any replica.
Amazon Bedrock AgentCore pricing
Amazon Bedrock AgentCore introduced consumption-based pricing for short-term memory.
Amazon Connect Customer step-by-step guides
Amazon Connect Customer now prefills step-by-step guides for after contact work.
BigQuery Data Transfer Service
Incremental data transfers for PostgreSQL and ServiceNow are generally available.
Databricks Feature Views
Feature Views are generally available for batch, streaming, and request-time data.
DigitalOcean Harness Runtime OpenHands
Harness Runtime now supports OpenHands agents in isolated sandboxes, creatable via OpenHands Agent Canvas or the DigitalOcean API.
DigitalOcean Simulation
Simulation is now available in public preview for testing agent behavior through generated multi-turn conversations.
EC2 G7 instances
Amazon EC2 G7 instances are now available in Europe (Frankfurt) and Europe (Stockholm) Regions.
Google Meet next steps
Google Meet added post-meeting next steps to draft follow-up emails and export action items to Google Tasks.
Instagram Live MoQ ingest
Instagram Live now uses Media over QUIC (MoQ) for live video ingest on iOS and Android.
Lovable invite-only publishing
Free and Pro plans can publish apps to an invite-only audience.
Lovable workspace publishing domains
Enterprise workspace admins can set a publishing domain so projects publish at your-app.yourdomain.com instead of your-app.lovable.app.
Meta Models on Netlify AI Gateway
Meta's Muse Spark and Muse Wonder models are now available through Netlify's AI Gateway with zero configuration.
Modal Endpoint Candidates
Endpoint Candidates are generally available for all Modal workspaces, enabling staging and promotion of alternative Dedicated Endpoint deployments.
Muse Wonder on AI Gateway
Meta's Muse Wonder model is available on AI Gateway with a 1M-token context window and text, image, and PDF input.
OpenCode 2.0 on Cloudflare Agents SDK
Agents SDK 0.28.0 adds OpenCode 2.0 support through an experimental OpenCodeHarness, with SQLite sessions and Lifecycle jobs.
SAP Pay
SAP Pay embeds payment execution directly into SAP Cloud ERP, supporting EFT, wire transfers, checks, and stablecoin settlement.
Segment Conversation Memory Integration
Twilio's Segment Conversation Memory integration is now generally available.
Semantic Studio
Semantic Studio, the IDE for semantic views, is now generally available in Snowflake Workspaces with CoCo, git, and CI/CD.
Ultralytics v8.4.176
YOLO-World checkpoints after set_classes drop from 328 MB to 26 MB by not caching the CLIP text encoder.
Unified Zero Trust dashboard navigation
Cloudflare dashboard now combines Zero Trust and main dashboard navigation, available to all customers starting today.
Unity Gateway Skills API
Unity Gateway Skills REST API is available in Beta with CRUD and finalize support across Databricks CLI and SDKs.
Workers Builds preview URLs
Workers Builds now posts preview URLs to GitHub pull requests and GitLab merge requests within seconds of a build completing.
langgraph 1.2.15
langgraph 1.2.15 released with fixes for message IDs, cached node writes, and interrupt_before breakpoints.
langgraph-checkpoint 4.3.0
langgraph-checkpoint 4.3.0 released with fixes for delta history, namespace validation, and serialized data.
langgraph-checkpoint-postgres 3.1.3
langgraph-checkpoint-postgres 3.1.3 released with fixes for empty checkpoint_id handling and a delta walk performance improvement.
langgraph-checkpoint-sqlite 3.1.2
langgraph-checkpoint-sqlite 3.1.2 released with fixes for empty checkpoint_id handling and namespace label validation.
langgraph-sdk 0.4.7
langgraph-sdk 0.4.7 released with fixes for thread stream run ending and delta channel replay ordering.
AWS Open Data Registry
46 new datasets are available on the Registry of Open Data on AWS.
LiteLLM v1.105.0
LiteLLM v1.105.0 released with 747 commits to main since the previous release.
Qwen Code Desktop v0.25.1
Qwen Code Desktop v0.25.1 adds Qwen Live endpoint settings, conversation search, and MCP image bounds.
RunPod MCP Server
RunPod ships an official MCP server for AI IDEs including Claude Code, Cursor, and VS Code.
openai-python v3.29.0
openai-python v3.29.0 adds a billing_not_active session error code, shida Live voice, and vault updates and metadata filters.
Microsoft Decision-1
Microsoft Decision-1 is now available on AI Gateway, answering typed questions about text with probabilities, choices and scores for classification, workflow routing or rubric assessment, with no separate Azure account or deployment required.
Liquid d1
Liquid d1 is now available on AI Gateway, a decision model that evaluates shared state against typed questions for classification, routing and scoring, returns structured answers with probabilities without generating text tokens, and supports vision for image classification and inspection.
Grok Imagine Video 1.5 Lite
Grok Imagine Video 1.5 Lite from xAI is now available on AI Gateway, turning text prompts and images into video with native audio in clips from 1 to 15 seconds at 480p, 720p and 1080p across seven aspect ratios.
OpenAI Ultrafast tier
AI Gateway now supports OpenAI's Ultrafast service tier for GPT 6 Astra and GPT 6.1 Sol, billed at 6x the standard per-token rate, with requests pinned to unsupported regions such as the EU running at the standard tier.
FLUX 3 Image
FLUX 3 Image from Black Forest Labs is now available on AI Gateway, generating images from text or editing existing images with up to ten reference images and five resolution tiers from 768 by 768 to 4K, with no Black Forest Labs account required.
Step 5 Preview
Step 5 Preview from StepFun is now available on AI Gateway, built for agentic coding, professional knowledge work and financial analysis, with text and image input and a 1M-token context window.
GitHub Copilot weekly releases
GitHub Copilot added Claude Haiku 5.5 for Pro, Pro+, Max, Business and Enterprise users, made local sandboxing generally available in Copilot CLI, the Copilot app and VS Code sessions using Agent Host, and let the Copilot app use separate GitHub accounts for license and repositories.
CodeQL 2.27.2
CodeQL 2.27.2 is now available, adding a C++ regular-expression parser, SQL-injection sink models for the Comdb2 C API, Go websocket modeling, Rust async data flow improvements, and JavaScript Workflow SDK directive recognition, with the Default suite running 498 security queries covering 170 CWEs.
Claude Code v2.1.296
Claude Code v2.1.296 added a code key to the Claude apps gateway managed policies, an autoCompactWindow option for subagents, a CLAUDE_CODE_WORKFLOW_SUBAGENT_MODEL environment variable, and updated Sonnet 5.5 cache reads to $0.10 per million tokens from $0.20.
Codex rust-v0.162.1
Codex rust-v0.162.1 fixed a TUI crash when asynchronous questions contain multiple lines, preserving line breaks and complete hyperlink destinations, and fixed startup failures from differences between a running background server's feature settings and CLI defaults.
Ollama v0.40.2
Ollama v0.40.2 upgrades models downloaded with earlier versions in the background the first time you run them for better performance and compatibility on llama.cpp, keeps the original copy as a backup, and makes ollama list stop showing duplicate entries for upgraded models.
Google Voice Carrier Link
Google made Carrier Link available in 14 additional countries including the US, Canada and much of Europe, letting Workspace customers add phone numbers and calling plans from certified local carriers through partners Southlight Services, Gamma Communications, Tata Communications and Telefonica Global Solutions.
Workspace Studio October release
Google Workspace Studio added nested conditionals, Gmail skip replies for thread triggers, Google Meet calendar outputs with full invitee lists and post-meeting email draft templates, and a Search for a Doc Drive step, rolling out gradually starting .
Claude Plan in Amp
Amp now supports using your Claude Pro/Max subscription in Claude Code mode, free for everyone.
GitHub Copilot CLI 1.0.96-2
Model IDs in /model and /config are now case-insensitive and canonical IDs are saved.
GitHub Copilot CLI v1.0.96-1
Interactive sandbox settings now suggest possible environment secrets and let you add masking hosts before saving.
Open WebUI v0.12.0
Open WebUI v0.12.0 adds realtime voice calls using OpenAI Realtime voice model gpt-realtime-2.1-mini.
OpenAI Java SDK v4.80.0
The OpenAI Java SDK adds agent environment webhook events and vault updates.
RunPod REST API
RunPod's new REST API lets users manage GPU workloads programmatically, including launching, scaling, and monitoring pods.
llama.cpp b11551
llama.cpp release b11551 adds MiniCPM-V 4.7 model support.
Alteryx Live Query for BigQuery
Alteryx Live Query now integrates with BigQuery, enabling Gemini-powered extraction from PDFs and images with warehouse-native execution.
Amazon Bedrock reasoning summaries for OpenAI models
Amazon Bedrock now supports reasoning summaries for OpenAI models.
Amazon Connect Customer automated checks
Amazon Connect Customer now provides automated checks to improve performance evaluation forms.
Amazon EC2 R8g instances
Amazon EC2 R8g instances are now available in additional regions.
Amazon EC2 R8gd instances
Amazon EC2 R8gd instances are now available in additional regions.
Anthropic Go SDK v1.80.0
Go SDK v1.80.0 adds types for Chat and Cowork unified analytics metrics and Managed Agents workflows, multiagent configuration, and thread status filtering.
Anthropic Java SDK v2.71.0
Java SDK v2.71.0 adds types for Chat and Cowork unified analytics metrics, Managed Agents workflows, multiagent configuration, thread status filtering, and client options().
BigQuery Data Engineering Agent
Available in asia-northeast1 (Tokyo) and supports gemini-3.5-flash.
Claude Agent SDK TypeScript v0.3.296
Claude Agent SDK TypeScript v0.3.296 adds claude_code_version to initialize responses and autoCompactWindow to AgentDefinition.
Claude Haiku 5.5 on DigitalOcean Inference
Claude Haiku 5.5 is now available on DigitalOcean Inference for serverless inference.
Claude Sonnet 5.5 and Opus 5.5 on Kiro
Anthropic Claude Sonnet 5.5 and Claude Opus 5.5 are now available on Kiro in AWS GovCloud (US).
Clef-omni on Workers AI
Clef-omni adds audio and video input, Clef-flash is cheaper, and Clef is faster.
Cloudflare Workers flamegraphs
On-demand CPU and memory profiling with flamegraphs for Workers and Durable Objects.
Copilot CLI 1.0.95-2
Fixed copilot config supports sandbox credential injectHosts keys, with key completion in Bash, Zsh, and Fish.
Crush v0.98.1
Crush v0.98.1 routes newer Copilot models through the Responses API.
Docker agent v1.150.0
Docker agent v1.150.0 adds DaoXE provider alias, OSC 7501 status reporting, execution capabilities, and a datetime toolset.
Dynamo v1.5.0
Dynamo v1.5.0 adds custom Router scoring, Mooncake and disk KV indexing, and guided tool call streaming.
Genie One code execution (Public Preview)
Genie One can now run code in a secure, isolated sandbox for work beyond SQL.
GitHub Copilot CLI 1.0.95-1
GitHub Copilot CLI 1.0.95-1 adds native Microsoft Entra broker authentication on macOS with browser fallback.
GitHub Copilot CLI v1.0.96-0
Pre-release v1.0.96-0 improves interactive session startup, permission decision visibility, and model failure recovery.
Google Workspace connector
Managed Google Workspace connector is available in Beta in Databricks Lakeflow Connect for ingesting audit activity.
LangSmith SDK v0.14.7
LangSmith SDK v0.14.7 released with sandbox API endpoint prefix normalization.
Langfuse v4.56.0
Langfuse v4.56.0 adds syntax highlighting to session tool previews and spend alerts for ClickHouse-billed organizations.
Mistral v2.26.1
Mistral v2.26.1 adds session read-only status, proxy setup, narrator, and plugin commands.
ONNX Runtime CUDA Plugin EP 0.3.0
ONNX Runtime CUDA Plugin EP 0.3.0 adds sparse attention, packed continuous-batching, INT2 and mixed-width QMoE execution, and decode-kernel tuning.
Office in Microsoft Copilot app
Word, Excel, and PowerPoint creation and collaboration are now available inside the Microsoft Copilot app.
OpenAI Java SDK v4.79.0
OpenAI Java SDK v4.79.0 adds prewarmed hosted environments API support.
OpenJev evaluator for LLM-as-a-judge
Databricks lets users select OpenJev (Qwen3.5 4B) as the evaluator model service for custom LLM-as-a-judge service policies.
Pydantic AI v2.55.0
Pydantic AI v2.55.0 requires Python 3.11 or newer and adds durable execution for ExaSearch, YouSearch, and LocalStack tool requests.
Sentry Agent Tracing for JavaScript SDKs
JavaScript SDKs now support Anthropic, OpenAI, Google GenAI, Vercel AI, LangChain, and LangGraph with automatic instrumentation since 11.0.0.
TwelveLabs Pegasus 1.5 on Bedrock
TwelveLabs Pegasus 1.5 model is now available on Amazon Bedrock.
Unity Gateway request tags (Beta)
Custom service policies in Unity Gateway can now check caller-supplied request tags before a model request or MCP tool call.
Workspace Studio October 2026 release
Workspace Studio adds nested conditionals, Gmail skip replies, Meet calendar outputs, and Drive document search, rolling out from .
anthropic-sdk-typescript v0.133.0
Types for Chat and Cowork unified analytics metrics, plus workflows, multiagent configuration, and thread status filtering for Managed Agents.
copilot-cli v1.0.95
Native Microsoft Entra broker authentication on macOS, sandbox credential injectHosts keys, and --context for ACP sessions.
ogx v1.5.0
ogx v1.5.0 adds Text-Embeddings-Inference provider, DeepSeek and Fireworks AI passthrough, and Anthropic reasoning model thinking support.
openai-node v7.31.0
openai-node v7.31.0 adds prewarmed hosted environments.
openai-node v7.32.0
API adds agent environment suspension and expiration.
openai-python v3.27.0
openai-python v3.27.0 adds prewarmed hosted environments.
openai-python v3.28.0
openai-python v3.28.0 adds agent environment suspension and expiration.
openai-ruby v0.102.0
openai-ruby v0.102.0 adds prewarmed hosted environments.
openai-ruby v0.103.0
openai-ruby v0.103.0 adds agent environment suspension and expiration.
@gradio/tabs 0.11.1
Fixes hidden Accordion revealed with open=True rendering empty.
@gradio/workflowcanvas 0.13.0
Adds an app view to gr.Workflow and reuses up-to-date upstream results when running a node.
@openai/agents-core@0.20.0
Default automatic MCP tool discovery now caps at 64 pages, with explicit maxListPages for larger listings.
@openai/agents-extensions@0.20.0
Fixed Vercel authentication configuration for restored sessions.
@openai/agents-realtime@0.20.0
Fixed audio interruption after generation with transport-appropriate buffer clearing.
@openai/agents@0.20.0
Patch release updates dependencies to @openai/agents-core@0.20.0, agents-realtime@0.20.0, and agents-openai@0.20.0.
AWS Cost Tools Bedrock Attributes
AWS Cost Explorer, Budgets, and Dashboards now support Amazon Bedrock product attributes.
Agno v3.1.2
Agno v3.1.2 adds conversation compaction to keep long sessions inside the context window.
Amazon GuardDuty RDS Protection
GuardDuty RDS Protection now detects data exfiltration and destruction in Aurora and RDS databases.
Azure Database for PostgreSQL flexible server
Azure Database for PostgreSQL flexible server is generally available in East US 3.
CLI v3.0.70
CLI v3.0.70 fixes 400 errors on GPT-6 Astra, GPT-6.1 Sol, Claude Fable 5, and Claude Opus 5.5, and fixes MCP server exit timing.
Claude Agent SDK Python v0.2.165
Python SDK v0.2.165 on PyPI, bundling Claude CLI 2.1.294.
Claude Agent SDK TypeScript v0.3.294
Claude Agent SDK TypeScript v0.3.294 updates to parity with Claude Code v2.1.294.
Claude Code v2.1.294
Claude Code v2.1.294 fixes prompt and agent hooks written as instructions and improves Stop/SubagentStop hook judgment.
Claude Code v2.1.295
Added onFailure block for hooks, Program Status Protocol support, and quoted text in /copy picker.
Claude Opus 5.5 and Sonnet 5.5
Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available in Gemini Enterprise AI developer tools.
Copilot CLI 1.0.94
Claude Haiku 5.5 added to model selection and --model completions.
Crush v0.98.0
Crush v0.98.0 adds x.AI OAuth login, OSC 7501 support, and many fixes.
DOKS 1.37 GPU plugin defaults
GPU device plugins are no longer enabled by default on clusters with GPU nodes; DRA drivers are opt-in.
Databricks Discover page and domains
The Discover page and domains are now generally available on Databricks.
DeepSeek V4.1 Flash Fast on Baseten
DeepSeek V4.1 Flash Fast is available on Baseten Model APIs with 1M-token context and dedicated Fast capacity.
DigitalOcean Prompt Caching
Prompt caching for DigitalOcean-hosted models is generally available with automatic context caching and no cache-write charge.
Disconnected cluster analysis with pen drive
Disconnected cluster analysis is available now with pen drive powered by Red Hat Lightspeed.
Dynamic Workflows in Azure Functions Hosted Skills
Adds LLM-planned DAG workflows with Durable Functions execution, retries, and crash recovery.
Dynamo v1.5.0-kimi-k3-post.1
Experimental snapshot build serving moonshotai/Kimi-K3 from an SGLang runtime on Dynamo 1.5.1 and SGLang v0.5.18.
FastMCP v4.1.0
FastMCP v4.1.0 released with fixes across OpenAPI, proxies, auth, tasks, CLI, and full Python 3.15 support.
File upload in Genie One
File upload in Genie One is now generally available for CSV, Excel, PDF, image, Word, and plaintext files.
GPT-6.1 Sol Ultrafast on Bedrock
OpenAI GPT-6.1 Sol now supports Ultrafast mode on Amazon Bedrock.
Gemini assistance in BigQuery Studio SQL editor
Gemini assistance in the BigQuery Studio SQL editor is generally available through an inline action button.
Genie One file upload
File upload in Genie One is generally available for CSV, Excel, PDF, image, Word, and plaintext files.
GitHub Copilot CLI v1.0.94-3
Added Claude Haiku 5.5 to model selection and --model completions.
GitHub MCP Server 2.0.2
Bugfix release restoring typed tool HTTP header validation.
Gradio 6.30.0
Adds an app view to gr.Workflow and reuses up-to-date upstream results when running a node.
Kilo Code JetBrains 7.1.9
JetBrains extension adds prompt navigator, MCP OAuth sign-in, and markdown agent board messages.
LangSmith Fine-Tuning
smithtune CLI turns LangSmith trajectories into fine-tuned models via Fireworks or Baseten.
Langfuse v4.55.0
Langfuse v4.55.0 adds OpenAI decision model support and skill import from local files and ZIPs.
Managed Deep Agents 0.8
Adds user-owned credentials, user-level memory, HTTP channels, Slack file transfer, and Parallel web search.
Managed StandardV2 NAT Gateway for AKS
Managed StandardV2 NAT Gateway for AKS is generally available.
ONNX Runtime CUDA Plugin EP 0.2.0
Expanded quantized inference and attention support, kernel performance improvements, and reliability fixes.
OpenHands v1.26.0
OpenHands v1.26.0 released with new features including verify-openhands skill and backend workspace explanations.
Physical AI Toolchain on AWS
AWS launched an open-source stack for building physical AI machines, with architecture guidance, deployment automation, and code.
Power Pages Sweden Central and Italy North
Microsoft Power Pages is generally available in Sweden Central and Italy North.
Promptfoo 0.124.1
Promptfoo 0.124.1 adds OpenAI Decisions support and exposes catalog text-token pricing.
Self-hosted Retool 4.34 and 4.0 stable updates
Retool 4.34.8 and Retool 4.0.21 are now available on the Stable release channel.
TRL v1.15.0
Fused LM head on by default, up to 6.9x longer sequences on the same GPU.
Vercel skipMiddlewareRequestBody
Added skipMiddlewareRequestBody option to reduce Fast Origin Transfer usage and improve time to first byte.
harness-cli/v0.2.0
harness-cli v0.2.0 adds a vended subagent tool and exposes a tool client accessor.
harness-python/v0.2.0
harness-python v0.2.0 adds a vended subagent tool and exposes a tool client accessor.
harness-sdk python/v1.59.0
Python SDK v1.59.0 adds a vended subagent tool and fixes Anthropic cache writes on older LiteLLM.
harness-sdk typescript/v1.20.0
TypeScript SDK v1.20.0 adds a vended subagent tool and exposes a tool client accessor.
harness-typescript/v0.2.0
harness-typescript v0.2.0 adds a vended subagent tool and exposes a tool client accessor.
huggingface_hub v2.2.0
huggingface_hub v2.2.0 adds hf jobs stats snapshots, concurrent xet downloads, and HfFileSystem caching fixes.
langchain-openai 1.7.0
langchain-openai 1.7.0 adds support for the decisions API.
mcp-toolbox v1.14.0
Adds BigQuery authorized views, LookML dashboards, Spanner Omni, and a looker-get-explore tool.
openai-node v7.30.1
OpenAI Node SDK v7.30.1 corrects custom voice creation parameters.
supervision-0.30.9
supervision 0.30.9 installs without OpenCV, fixes COCO/CreateML box loading, and improves video frame reading.
AI Security for Apps unsafe topic categories
Updated unsafe topic detection categories are now available in cf.llm.prompt.unsafe_topic_categories.
Agent Framework .NET 1.24.0
Stabilizes Anthropic agent package and adds fixes for session state, search memory, and request messages.
Amazon EC2 C8gb instances
C8gb instances are now generally available in additional regions.
Anthropic Go SDK v1.79.0
Go SDK adds claude-haiku-5-5 and typed computer and browser toolset tool calls.
Anthropic Java SDK v2.69.0
Java SDK adds claude-haiku-5-5 and typed computer and browser toolset tool calls.
Anthropic TypeScript SDK v0.132.0
Anthropic TypeScript SDK v0.132.0 adds claude-haiku-5-5 and typed computer and browser toolset tool calls.
BigQuery TimesFM 3.0
BigQuery now offers TimesFM 3.0 as a built-in time series forecasting model with AI.FORECAST, including multivariate forecasting.
Claude Agent SDK TypeScript v0.3.293
Added optional subagent_type to background_tasks_changed task entries and updated to parity with Claude Code v2.1.293.
Claude Code v2.1.293
Claude Code v2.1.293 adds Claude Haiku 5.5, now the default Haiku model, with 1M context and $0.10/$0.50 per Mtok.
Claude Haiku 5.5 in Devin
Claude Haiku 5.5 is live in Devin, scoring 58.4% on FrontierCode 1.1 at about an eighth of Sonnet 5's cost per task.
Claude Haiku 5.5 in GitHub Copilot
Claude Haiku 5.5 is generally available in GitHub Copilot for Pro, Pro+, Max, Business, and Enterprise users.
Claude Haiku 5.5 on AI Gateway
Claude Haiku 5.5 is now available on Vercel AI Gateway with effort levels and Zero Data Retention support.
Claude Haiku 5.5 on AWS
Claude Haiku 5.5 is now available on AWS.
Claude Haiku 5.5 on AWS GovCloud
Claude Haiku 5.5 is now available on AWS GovCloud (US).
Claude Haiku 5.5 on Netlify
Claude Haiku 5.5 is available through Netlify AI Gateway and Agent Runners with zero configuration required.
Claude Haiku 5.5 on Unity Gateway
Anthropic Claude Haiku 5.5 is now available on Unity Gateway via Foundation Model APIs.
Cline v4.1.23
Cline v4.1.23 adds GPT-6.1 Sol to recommended models and changes default models for 20 providers.
Cloudflare One Client for Windows
Cloudflare One Client for Windows 2026.8.2100.0 is GA with faster reconnections, lower memory use, and service recovery.
Cloudflare One Client for macOS
Cloudflare One Client for macOS 2026.8.2100.0 is GA with faster connects, lower memory use, and split tunnel fixes.
Cloudflare Organizations GA
Cloudflare Organizations is generally available for Enterprise customers and MSSP/Distributor partners, with nested sub-organizations for partners.
Copilot CLI v1.0.93-4
Command sandboxing is available to all users via /sandbox and --sandbox.
Databricks Apps OBO authorization
Databricks Apps now GA with on-behalf-of-user authorization for permission-aware apps.
Deep Agents Skills
Deep Agents can bind tools to skills, pin skills at runtime, and reload skills mid-thread.
DeepSeek V4.1 Flash on Databricks
DeepSeek V4.1 Flash now supports priority pay-per-token and reserved provisioned throughput on Databricks.
DigitalOcean Memphis region databases
Managed databases and Storage-Optimized Kafka/OpenSearch plans are available in Memphis (mem1).
Docker Agent v1.149.0
Adds GitHub repository skill loading, evaluator routing through the models gateway, and model pricing and capability fixes.
Dynamo v1.5.1
Patch release fixes router overload recovery, min_tokens, Qwen3-VL video routing, and RL worker discovery.
FlashAttention fa4-v4.0.0.beta34
Pre-release fa4-v4.0.0.beta34 with Windows CUDA 13 and PyTorch 2.15 build fixes.
GKE Sandbox microVM GA
The microVM sandbox type is generally available with GKE Sandbox in clusters running version 1.37.0-gke.4713000 and later.
GitHub Copilot CLI 1.0.93
GitHub Copilot CLI 1.0.93 adds enterprise permissions.limitTo, safe command execution during active turns, and localhost allowlist changes.
GitHub Copilot CLI local model discovery
GitHub Copilot CLI version 1.0.94-0 adds /model to discover supported models from a running local Ollama instance.
GitHub Copilot CLI v1.0.93-3
MCP server configuration changes apply between turns without restarting the session.
GitHub MCP Server 2.0.1
GitHub MCP Server 2.0.1 fixes the Go module path for library users.
Glyph Cluster on AI Gateway
Glyph Cluster reasoning model is available in stealth for free on AI Gateway for Pro and Enterprise plans with purchased AI Gateway credits.
Kilo Code v7.8.8
Kilo Code v7.8.8 adds pinned worktrees, in-app web links, and reduced Agent Manager header height.
Langfuse v4.54.0
Released v4.54.0 with trace classification, external media storage, and session transcript views.
Local sandboxing for GitHub Copilot
Local sandboxing for GitHub Copilot is generally available in CLI, app, and VS Code.
Lovable credit usage limits and alerts
Workspace admins and owners on paid plans can now set credit usage limits and alerts for workspaces, projects, members, groups, or access tokens.
MLflow 3.17.0
MLflow 3.17.0 adds typed judges, fine-grained permissions, and faster analytics for large trace datasets.
Managed Deep Agents v0.9
Managed Deep Agents v0.9 adds agent-created schedules, per-run configuration, and Slack reactions.
OpenAI Decisions API on AI Gateway
OpenAI Decisions API now available through Netlify AI Gateway, running on gpt-6-luna with zero configuration required.
OpenAI Decisions API on AI Gateway
Vercel AI Gateway adds an OpenAI-compatible /v1/decisions endpoint for GPT-6 Luna Decisions and other decision models.
Retool 4.70 Edge
Retool 4.70 is now available on the Edge release channel for self-hosted organizations.
SAP Commerce Cloud, cloud ERP edition
SAP Commerce Cloud, cloud ERP edition is generally available, with new and enhanced Joule Assistants for SAP Customer Experience.
SAP Joule Work
SAP is rolling out Joule Work to all customers this month, a new UI for AI.
SDK v0.0.91
Stdio MCP servers get a 10s default initialize budget, up from 3s.
Self-hosted Retool 4.34.7
Retool 4.34.7 is now available on the Stable release channel for self-hosted instances.
Vercel Flags timestamp attributes
Vercel Flags now supports timestamp attributes for entities, configurable via dashboard or CLI.
anthropic-sdk-python v1.12.0
Adds claude-haiku-5-5 and typed computer and browser toolset tool calls.
copilot-cli 1.0.94-0
Pre-release 1.0.94-0 adds update guidance for managed settings and lets managed policy disable Assisted Permissions.
langgraph-cli 0.4.33
Adds --image-uri to deploy an already-pushed image and a 'langgraph deploy listeners list' command.
AWS Certificate Manager ACME via PrivateLink
AWS Certificate Manager now supports ACME issuance through AWS PrivateLink.
Canvas authoring plugin
Canvas authoring plugin for Copilot is available in the Awesome Copilot marketplace to generate Azure canvas projects.
Claude Agent SDK TypeScript v0.3.291
Updated to parity with Claude Code v2.1.291; install via npm, yarn, pnpm, or bun.
Claude Agent SDK TypeScript v0.3.292
Claude Agent SDK TypeScript v0.3.292 adds agent_id, parent_task_id, run_id, and typed sections to ListAgents.
Claude Code v2.1.292
Claude Code v2.1.292 adds marketplace install, Agent effort parameter, overloaded retry delay, and prompt.autocomplete.
Diffusers 0.41.0
Diffusers 0.41.0 adds Qwen-Image 2.1 pipeline with text-to-image, image editing, native transparency, and LoRA training.
DigitalOcean Harness Runtime CrewAI
DigitalOcean Harness Runtime now supports CrewAI agents in an isolated sandbox.
Figma agent
The Figma agent is generally available with improved latency, file search, and configurable guidelines.
Gemini Nano Banana 2.1
Gemini Nano Banana 2.1 is generally available, optimized for high-speed multimodal image generation and editing at 1K, 2K, and 4K output resolutions.
Gemini Nano Banana 2.1
Google's Gemini Nano Banana 2.1 is now available through Netlify AI Gateway, callable from Netlify Functions without configuring API keys.
Genie Code CLI
Genie Code CLI, a terminal coding agent for Databricks data and AI work, is in Beta.
GitHub MCP Server 2.0.0
GitHub MCP Server 2.0.0 adds structured outputs and output schemas for clients advertising MCP spec support or later.
Google Vids point-in-time editing
Point-in-time editing is now available in Google Vids, making the canvas match the video timeline 1:1.
Harness SDK python/v1.58.1
Patch release restores legacy task execution on SDK 2.x client and preserves reported cache token usage.
Langfuse v4.52.0
Langfuse v4.52.0 bounds trace batches by estimated weight and shows organization usage breakdown on every deployment.
Langfuse v4.53.0
AI gateway now exposes resolution context in response headers, spans and logs.
Lightwell Clearinghouse
Lightwell Clearinghouse is generally available, letting businesses request priority review and remediation for open source software.
Line comments in Agent Runners
Users can comment on specific lines in the diff on the Code tab of Agent Runners.
Mistral Large 4 on AI Gateway
Mistral Large 4 is available on AI Gateway via one API key, with AI SDK, OpenAI-compatible, Responses, and Anthropic Messages APIs.
Mistral Vibe v2.26.0
Mistral Vibe v2.26.0 adds built-in plugin discovery, image attachment warnings, background process panel, and owner-only .env fallback.
Nano Banana 2.1 on AI Gateway
Google's Nano Banana 2.1 image model is available on Vercel AI Gateway via AI SDK, OpenAI-compatible API, or AI CLI.
OpenAI Go SDK v3.72.0
OpenAI Go SDK v3.72.0 adds agent turn items and usage source grouping.
OpenAI Node SDK v7.29.0
OpenAI Node SDK v7.29.0 adds local tool failure observation, session stream tool running, and tool search support.
Puck Multiple Conversations
Users can now run multiple separate Puck conversations, each with its own Puck, switching between them.
TRL v1.14.2
Patch release fixes two cases of silently wrong training and three crashes, including end-of-turn handling for GRPO, RLOO, and Distillation.
Trello for Google Workspace
Trello for Google Workspace now lets users create Trello cards from Google Chat messages.
copilot-cli 1.0.93-2
Pre-release 1.0.93-2 adds enterprise permissions.limitTo and prioritizes GPT-6.1 Sol, GPT-6 Astra/Luna, and Claude 5.5 models.
livekit-agents 1.8.5
livekit-agents 1.8.5 adds Gemini 3.8 Live support and sticky LLM fallback routing.
llama.cpp K2 Horizon support
llama.cpp b11454 adds K2 Horizon dense and MoVA model support.
openai-go v3.73.0
openai-go v3.73.0 adds standalone Decisions support.
openai-java v4.78.0
openai-java v4.78.0 adds standalone Decisions support.
openai-node v7.30.0
openai-node v7.30.0 adds standalone Decisions API support.
openai-python v3.26.0
openai-python v3.26.0 adds standalone Decisions API support.
openai-ruby v0.100.0
openai-ruby v0.100.0 adds agent tool search and turn items, and selects Mantle for GPT-6.1 Sol.
supervision-0.30.8
supervision 0.30.8 fixes video quality, YOLO label parsing, mask drift, and VLM parsing.
vLLM v0.31.1rc0
vLLM v0.31.1rc0 exposes cached prompt tokens by cache tier in metrics.
@modelcontextprotocol/client@2.3.1
MCP TypeScript SDK client package version 2.3.1 released.
@modelcontextprotocol/codemod@2.3.1
MCP TypeScript SDK codemod package version 2.3.1 released.
@modelcontextprotocol/core@2.3.1
MCP TypeScript SDK core package version 2.3.1 released.
@modelcontextprotocol/server@2.3.1
MCP TypeScript SDK server package version 2.3.1 released.
@openai/agents-openai 0.19.0
Adds optional rollback item budget for Responses session compaction and fixes trace exports and generation reasoning.
@openai/agents-realtime 0.19.0
Fixes conditional tool approvals, durable approval resumes, uncopyable normalized values, and default function redaction.
AWS Capabilities by Region notifications
AWS Capabilities by Region now offers availability notifications for individual features and advanced filters.
Amazon EC2 Hpc8a in Singapore
Amazon EC2 Hpc8a instances are now available in Asia Pacific (Singapore).
BigQuery Iceberg flexible column names
Iceberg external and managed tables now support flexible column names by default.
Claude Code v2.1.290
Claude Code v2.1.290 adds serverToolUses, agentId, ceiling, and ThemeKey/Color types to plugin hooks.
ComfyUI v0.39.0
ComfyUI v0.39.0 adds LynnReal light Minimax-H3 VAE support, DynamicGroup widget input, and higher quality defaults for Save Video encoding.
Databricks SQL 2026.39
Databricks SQL version 2026.39 is rolling out to the Current channel.
Docker Agent v1.147.0
Hook-driven agent routing, lean TUI settings panel, codemode tool call visibility, and new CLI and eval capabilities.
Docker agent v1.148.0
Docker agent v1.148.0 fixes oversized tool output handling by bounding complete tool results to 50 KiB and fixes duplicate line rendering in the lean TUI.
Genie Code scheduled tasks
Genie Code scheduled tasks are now available by default for workspaces with the compliance security profile enabled.
GitHub Copilot CLI 1.0.92
Copilot CLI 1.0.92 adds config subcommands, a pre-conversation environment picker, and fixes for MCP connections and voice runtime errors.
Lakeflow Jobs multiple triggers
Lakeflow Jobs can now use up to five triggers, with combined types and independent pause.
Lakeflow pipeline run-as group
Lakeflow pipelines can now set run-as identity to an account group, in addition to user or service principal.
Langfuse v4.51.0
Langfuse v4.51.0 adds decision-model evaluators, comparison grid annotations, and AI gateway request ID correlation.
Lovable workspace announcement banner
Workspace admins on Business and Enterprise plans can now show an announcement banner to every member of the workspace.
MCP TypeScript SDK 2.3.1
requireBearerAuth in server-legacy now accepts the optional expectedResource parameter.
OpenAI Agents JS v0.17.1
OpenAI Agents JS v0.17.1 adds server-wide MCP tool guardrails, custom output guardrail blocked messages, Docker sandbox labels, and image results in web search.
Qwen Code Desktop v0.25.0
Qwen Code Desktop v0.25.0 released with session diagnostics, managed runtime attestation client, trajectory time range selection, Qwen Live endpoint settings, and private/group access policies.
Qwen SDK TypeScript v0.1.18
SDK TypeScript v0.1.18 released, bundling CLI version 0.25.0.
Redshift Iceberg materialized views
Amazon Redshift now supports creating and refreshing Apache Iceberg materialized views.
Segment Conversation Memory Integration
Segment Conversation Memory Integration is now in general availability.
langgraph 1.2.13
langgraph 1.2.13 released with fixes for checkpoint replay, update_state, and DeltaChannel counters.
llama.cpp v0.6.0
llama.cpp v0.6.0 adds GLM-5.3-Flash 320B, Clef, Qwen4Exp MTP, and a new /v1/systemone server API.
GitHub Copilot CLI
Version 1.0.92-4 adds copilot config subcommands and improves MCP server startup responsiveness.
Ultralytics 8.4.173
Ultralytics 8.4.173 adds AMD Xilinx Vitis AI export for Versal AI Edge Gen 2 NPUs.
openai-java v4.76.0
openai-java v4.76.0 adds custom voices and agent session webhook events.
openai-node v7.28.0
openai-node v7.28.0 adds custom voice creation and agent session events.
supervision-0.30.7
supervision 0.30.7 fixes video processing hangs, dataset export, mAP, and Transformers loading.
AI Search
Cloudflare's AI Search is generally available, combining Workers AI, Vectorize, R2, and Browser Run into a fully managed index and retrieval pipeline, with billing starting .
Cloudflare Basin
Cloudflare Basin is generally available as a serverless data analytics platform built on Apache Iceberg and R2 Object Storage, including Basin Pipelines, Basin Catalog, and Basin SQL.
Workers KV Instant
Workers KV Instant, powered by Quicksilver, offers 100 times faster p99 reads than classic mode with reads resolving in under two milliseconds at p99, and writes replicating in around 250ms for 99% of writes.
Ollama v0.35.1
Ollama v0.35.1 supports Clef and Clef Flash, Cloudflare's new open-source decision models, through /v1/systemone, with Clef at 27B and Clef Flash at 9B, both multimodal.
Stateless installation tokens
The staged rollout of the stateless GitHub App installation token format is complete, with all newly minted tokens in the stateless ghs_APPID_JWT format at about 520 characters long instead of 40.
Laya on AI Gateway
Laya from Convai Innovations is free to use on AI Gateway through via Boundless, evaluating shared context against yes/no, choice, or scoring questions and returning structured answers with probabilities.
MAI models on AI Gateway
Vercel and Microsoft AI partnered to make MAI models available on AI Gateway, including MAI-Voice-2.1, MAI-Voice-2.1-Flash, and MAI-Transcribe-2 Streaming, billed at listed rates with no platform fee or markup on inference.
Protected Quick Tunnels
Starting with cloudflared 2026.9.3, you can add --allowed-mail to a Quick Tunnel command, and the tunnel only lets in the email addresses and domains you choose, with visitors proving ownership via a one-time PIN from Cloudflare Access.
Workers post-quantum crypto
Cloudflare Workers added support for post-quantum-resistant algorithms within Web Crypto, including ML-KEM-768 and ML-KEM-1024 for key encapsulation and ML-DSA-44, ML-DSA-65, and ML-DSA-87 for signatures, behind the webcrypto_modern_algorithms compatibility flag.
Claude Code v2.1.288
Claude Code v2.1.288 added $.ui.selection() for mods, a built-in gh api to cloud sessions, recovery for a prompt cleared with Ctrl+C, and --max-findings <n>|all to /code-review.
Claude Code v2.1.287
Claude Code v2.1.287 added Claude Mods, a built-in mod called You should know, an n:<text> filter to the agents view, and prompt_text to the OpenTelemetry user_prompt event.
vLLM v0.31.0
vLLM v0.31.0 adds a Transformers version upper bound in requirements.
Claude Agent SDK TypeScript v0.3.289
Updated to parity with Claude Code v2.1.289.
Claude Code v2.1.289
Fixes for deny rules, terminal freezing, symlink Read rules, and sign-out frequency.
Pydantic AI v2.54.0
Released pydantic-ai v2.54.0 with fixes for JSON schema, image generation, and durable execution.
@modelcontextprotocol/core@2.3.0
License field of package manifests is now Apache-2.0; LICENSE file carries full terms.
@modelcontextprotocol/express@2.0.2
requireBearerAuth and verifyBearerToken take a new optional expectedResource to accept only tokens issued for this resource.
@modelcontextprotocol/fastify@2.0.1
Server or McpServer now serves one connection at a time; stateless Streamable HTTP transport serves one request.
@modelcontextprotocol/hono@2.0.2
Server or McpServer now serves one connection at a time; stateless Streamable HTTP transport serves one request.
@modelcontextprotocol/server 2.3.0
requireBearerAuth and verifyBearerToken take a new optional expectedResource to accept only tokens issued for this resource.
@modelcontextprotocol/server-legacy 2.3.0
The license field of the package manifests is now Apache-2.0 with no code change.
AI Object Storage
CoreWeave launched AI Object Storage, an object storage service optimized for AI workloads.
Amazon EKS Kubernetes 1.37
Amazon EKS and EKS Distro now support Kubernetes version 1.37.
Android Device Streaming in Android CLI
Android Device Streaming is now available in Android CLI, giving agents access to real physical devices remotely.
Baseten CLI 1.1.0
Baseten CLI 1.1.0 adds model rename and volume sync, with sync supporting Hugging Face, S3, GCS, Azure, R2, or CoreWeave sources.
BigQuery Rust SDK
The Rust SDK for BigQuery is now generally available.
BigQuery Rust SDK GA
The Rust SDK for BigQuery is now generally available.
Cline Desktop v0.0.42
New /compact slash command and a redesigned Connectors tab with search and brand logos.
Cline SDK v0.0.90
Agent teams no longer slow down as a session runs or while a teammate is streaming; stream chunks and heartbeats are no longer persisted.
Cloudflare Web Search API
Web Search API beta on AI Gateway with Ceramic.ai, Exa, and Linkup providers, billed at list API price.
ComfyUI v0.38.2
ComfyUI v0.38.2 is released.
Data API builder 2.1.5
Adds SQL json and vector data type support to REST and GraphQL endpoints.
ElastiCache for Valkey OpenTelemetry
Amazon ElastiCache for Valkey now supports OpenTelemetry metrics and detailed monitoring.
Flutter replay masking
Session Replay for Flutter can mask selected text ranges like account numbers or email addresses while leaving safe labels visible.
GLM 5.2 on CoreWeave Inference
GLM 5.2 is now available on CoreWeave Inference.
GPT Live voice in Lovable
Lovable now lets users add live voice conversations to apps with GPT Live, working in TanStack Start apps and using credits.
GitHub Copilot CLI 1.0.92-3
Pre-release 1.0.92-3 adds a pre-conversation Ctrl+E environment picker and fixes input ordering, sandboxed shell network prompts, and Git credential handling.
GitLab AI Gateway Critical Patch
GitLab released AI Gateway versions 19.2.4, 19.3.2, and 19.4.1 with a critical security fix for self-hosted installations.
Google ADK Python v2.11.0
ADK Python v2.11.0 adds graceful cancellation, tool confirmation, a model consultation tool, and a built-in SQLite memory service.
Goose v1.53.0
Goose v1.53.0 adds support for Opus 5.5, GPT-6-sol, GPT-6-luna, and a lean ACP-only binary.
GuardDuty Runtime Monitoring
GuardDuty Runtime Monitoring is now included in the AWS Security Hub Threat Analytics plan.
JDBC Unity Catalog connections
JDBC Unity Catalog connections are now generally available on serverless compute, Databricks Runtime 19 and above, and SQL warehouses 2025.40 and above.
Langfuse v4.50.0
Langfuse v4.50.0 adds facet type, built-in protection, and rule idle time to evals, plus error IDs in tRPC toasts.
MCP TypeScript SDK 1.32.0
HTTP client transports now follow redirects only on the same origin unless redirectPolicy is set to follow.
MCP TypeScript SDK 2.3.0
Server.connect() now rejects while the instance is already connected, and a stateless server is one per request.
NVIDIA GB200 NVL72 Instances
CoreWeave is the first cloud provider to announce general availability of NVIDIA GB200 NVL72 instances.
NVIDIA HGX B200 Instances
CoreWeave expanded its NVIDIA Blackwell fleet with generally available NVIDIA HGX B200 instances.
NVIDIA RTX PRO 6000 Blackwell Server Instances
CoreWeave launched the first generally available NVIDIA RTX PRO 6000 Blackwell Server Instances.
Neon AI Gateway embedding models
Neon AI Gateway supports qwen3-embedding-0-6b and gte-large-en embedding models, returning 1024-dimension vectors.
ONNX Runtime v1.28.3
Patch release with memory-safety, model-validation, plugin execution, and packaging fixes.
OpenAI Agents Python v0.23.0
Adds configurable MCP listing page limits, opt-in Docker removal protection, memory consolidation turns, and encrypted history scan budget.
OpenAI models in Retool
Retool supports GPT 6 Luna, GPT 6 Sol, and enterprise-only GPT Image 2.5 Flare and Sunburst for AI resource queries.
OpenFeature provider for Elixir
Elixir applications can evaluate Feature Flags through a new optional OpenFeature provider.
OpenJev (Qwen3.5 4B)
OpenJev (Qwen3.5 4B) is available as a pay-per-token model service on Unity Gateway.
Pydantic AI v2.53.0
Fixes a high-severity concurrency slot leak in ConcurrencyLimitedModel.
Ray 2.59.0
Ray Data LLM and Ray Serve LLM APIs are GA, with vLLM 0.27.0 and an external disk-backed shuffle backend.
React Native fatal error recovery
Error Tracking in React Native preserves fatal JavaScript exceptions through process crashes for reporting after relaunch.
Retool natural language resources
Prompt the app building agent to create REST API or PostgreSQL resources directly from the app builder.
Roboflow Inference v1.7.3
RF-DETR Nano on Mac goes from 72 ms to 16 ms end to end.
Ruby MCP analytics
Experimental MCP analytics is available for Ruby servers built with the Ruby MCP gem.
SecurityAdvisory GraphQL API fields
The SecurityAdvisory object gained five new fields and the securityAdvisories query gained two new filters.
Spanner queues
Spanner queues are generally available, providing native transactional messaging embedded directly within Spanner.
Strict service token authentication
Cloudflare Access added a strict service token authentication setting, default on for organizations created after .
SwiftUI tap autocapture
The iOS SDK can now autocapture SwiftUI control taps with an opt-in configuration.
Workers KV namespace jurisdictions
Workers KV namespace jurisdictions are generally available with eu, us, and fedramp regions.
Workers Observability in Custom Dashboards
Cloudflare adds Workers Observability Logs and Traces datasets to Custom Dashboards, with up to 100 dashboards per account.
openai-python v3.24.0
openai-python v3.24.0 adds custom voice creation and agent session events.
Agno v3.1.0
Agno v3.1.0 adds role-based access control and a filesystem to AgentOS.
Azure Cosmos DB Shell
Azure Cosmos DB Shell is now available in the Azure portal as a preview, accessible from Data Explorer.
Azure Pipelines GitHub-hosted agents
GitHub-hosted agents with pay-as-you-go pricing are generally available, including macOS SKUs and Linux/Windows previews.
BigQuery conversational analytics
Chatting with graphs in conversational analytics is now generally available, using multiple graphs, tables, views, and UDFs as data sources.
BigQuery metadata enrichment
BigQuery pipelines now supports automated metadata enrichment and Knowledge Catalog data quality scorecard integration, generally available.
Claude Agent SDK TypeScript v0.3.287
Adds optional remote-session latency fields and fixes partial message streams and revoked login errors.
Claude Opus 5.5 in Retool
Claude Opus 5.5 is available in Retool through Anthropic and Amazon Bedrock for Enterprise AI resource queries.
Copilot CLI 1.0.92-0
Copilot CLI 1.0.92-0 fixes MCP tools continuing to work after OAuth reauthentication when tool definitions are unchanged.
CoreWeave AI Object Storage
Cross-region writes and Archive storage are now available in CoreWeave AI Object Storage.
Databricks IP Functions
IP Functions for network analytics are generally available on the Lakehouse.
DigitalOcean Inference and Agents balance
Prepaid balance and auto-reload for Serverless Inference and Managed Agents, with monthly plans in public preview.
Dynamic workflows in Copilot
Dynamic workflows are now available in Copilot CLI, the GitHub Copilot app, and the GitHub Copilot SDK.
GitHub Actions macOS 14 retirement
The macOS 14 runner image will be retired on , with brownout periods starting .
GitHub Copilot CLI 1.0.91
Adds sandbox CA commands for check, create, trust, rotate, and remove, plus session timeline and Windows sandbox fixes.
GitHub Copilot CLI 1.0.91-1
Adds copilot sandbox ca commands for proxy CA trust and fixes shutdown telemetry flush.
GitHub Copilot computer use
Computer use is now available in public preview in GitHub Copilot CLI and the GitHub Copilot app on macOS and Windows.
GoldenGate Veridata connections
GoldenGate Veridata adds support for 15 new connection types including Amazon Aurora, Azure Database, and SingleStoreDB.
Haystack 3.3.0
Haystack 3.3.0 released with faster SentenceWindowRetriever, BM25 retrieval changes, and CJK tokenization fixes.
Haystack v3.3.0
SentenceWindowRetriever now queries the Document Store once per run instead of once per retrieved document.
Hugging Face Hub v2.1.0
Hugging Face Hub v2.1.0 adds Jobs retries, rescheduling, port exposure, ZeroGPU quota tracking, and a revamped Model Catalog.
Kilo Code v7.8.3
Kilo Code v7.8.3 adds a copy content button, document context menu actions, a manual Fetch Models button, and multi-root workspace file suggestions.
LTAP Direct Writes
LTAP Direct Writes is generally available for Lakebase, writing initial loads and full refreshes directly to storage.
LibreChat v0.8.8
LibreChat v0.8.8 adds agent control, unified agent builder, and background tasks.
Meet-Teams Android Interop
Google Meet and Microsoft Teams interoperability on Android (AOSP) devices is now generally available.
NVIDIA DOCA Agent Skills
DOCA AI agent skills for Flow, GPUNetIO, PCC, and RDMA are available on GitHub.
OCI DRG NAT
OCI Dynamic Routing Gateway now supports NAT for IPv4 addresses, configurable on DRG attachments.
OpenAI Go SDK v3.69.0
Adds typed output schema binding, translation and session trace APIs, and requires secure credential transport.
OpenAI Node SDK v7.26.0
OpenAI Node SDK v7.26.0 adds agent session trace listing and typed application functions for Agents tools.
Polaris 2.0.0-rc.1
Polaris 2.0.0-rc.1 updates components to the new admin style and improves mounting and update performance.
PostHog HogQL batch export modifiers
HogQL-model batch exports can now use their own HogQL modifiers when created or updated.
Redshift Cross-Region Queries
Amazon Redshift now supports cross-Region queries for your data lake.
Shopify Next Gen Events
Next Gen Events is generally available across 18 topics with the 2026-10 API version.
SubscriptionContractCalculation API
Shopify released a SubscriptionContractCalculation API that runs contract edits through checkout, supporting bundles and Shopify Functions.
Ultralytics v8.4.171
Adds end-to-end AMD GPU support via ROCm and MIGraphX for training and native PyTorch mode.
Workers Web Crypto ML-KEM/ML-DSA
Workers Web Crypto API now supports ML-KEM-768, ML-KEM-1024, ML-DSA-44, ML-DSA-65, and ML-DSA-87.
Workspace Client-side encryption simple setup
A new simple setup path in the Admin console lets admins set up Client-side encryption in minutes using Cloud HSM Keys and Google Identity.
livekit-agents@1.8.4
livekit-agents 1.8.4 adds smallestai TTS continuations, baseten inline instructions, and Azure Voice Live Realtime API support.
openai-python v3.23.0
openai-python v3.23.0 adds typed answers from session streams, session traces, Realtime translations, and typed application actions as agent tools.
openai-ruby v0.98.0
openai-ruby v0.98.0 adds typed output parsing, hosted files, session traces, and beta agent tool binding.
5th Gen AMD EPYC on Aurora and RDS
Amazon Aurora and RDS now support 5th generation AMD EPYC processors.
AI Gateway Browserbase Tools
Browserbase Search and Fetch tools are available through AI Gateway, requiring AI SDK 7.0.116 or later.
AI Gateway Machine Payments
AI Gateway supports Machine Payments in beta for /ai/run with select open models via x402 stablecoin payments.
AWS CLI Agent Toolkit updates
AWS CLI now supports bulk skill updates and version checks for the Agent Toolkit for AWS.
AWS Continuum for Penetration Testing
AWS Continuum for Penetration Testing is now available in 6 additional regions.
AWS Jam AI Agent Experiences
Three new AWS Jam experiences for building, deploying, and hardening AI agents are now available.
Amazon Managed Grafana 13.2
Amazon Managed Grafana now supports creating Grafana 13.2 workspaces.
Amazon S3 Vectors metadata pre-filtering
Amazon S3 Vectors now supports metadata pre-filtering for higher recall on filtered searches.
Anthropic Java SDK v2.67.0
Adds refusal stop reason, Claude Enterprise analytics, spend limits, RBAC, per-user usage reports, and Plugins to the Admin API.
Anthropic Python SDK v1.10.0
Anthropic Python SDK v1.10.0 adds Admin API analytics, spend limits, RBAC, and Plugins.
Aurora Serverless faster scaling
Amazon Aurora serverless now scales faster to support agentic AI and other bursty workloads.
Aurora and RDS R8a instances
Amazon Aurora and RDS now support AMD-based R8a instances.
Bedrock Claude in-region London
Amazon Bedrock expands Claude models in-region support in the UK (London).
Claude Code v2.1.286
Claude Code v2.1.286 adds a count to stacked permission prompts and mouse support for "N more" rows in fullscreen lists.
Cline CLI v3.0.66
CLI binaries now built with Bun 1.4.2 and Windows proxy startup fixed.
Cline Desktop v0.0.38
Linux ARM64 .deb and .rpm packages now ship alongside x64 builds.
Cline Desktop v0.0.39
Desktop v0.0.39 fixes blank window on Linux with NVIDIA driver and adds app info to .deb and .rpm packages.
Cline SDK v0.0.88
Anthropic requests now use server-side refusal fallback and provider allow_fallbacks; Stop during turn preparation no longer dropped.
Cline v4.1.22
Adds Bee and Pareto Inference providers; GPT-6.1 Sol becomes default model for OpenAI and other providers.
Cloudflare One Client for Windows
Beta release 2026.8.2033.1 is available with fixes for traffic blocking, reauthentication, DNS, and client crashes.
Copilot Code Reviews for Azure Repos
Effort levels, comment resolution, and audit log events added to Copilot Code Reviews for Azure Repos.
Cosmos DB Mirroring VNet Data Gateways
Cosmos DB mirroring in Fabric now supports virtual network data gateways for accounts secured by private endpoints or virtual networks.
Data Agent Kit GA
Data Agent Kit is generally available with support for BigQuery Graph, Bigtable, and Managed Service for Apache Spark.
Docs, Sheets, Slides comments API
Google Docs, Sheets, and Slides APIs now support programmatic comments; Docs adds suggested edits.
GPT-6 Astra UltraFast on Bedrock
OpenAI GPT-6 Astra now supports UltraFast mode on Amazon Bedrock.
GPT-6.1 Sol on DigitalOcean Inference
GPT-6.1 Sol is now available on DigitalOcean Inference for serverless inference and Agent Development Kit.
GitHub Copilot CLI 1.0.91-0
Version 1.0.91-0 lets statically analyzable read-only shell pipelines enter execution-evidence review; incomplete or unbound pipelines require explicit approval.
GitHub Copilot CLI v1.0.90
Release 1.0.90 adds GPT-6.1 Sol model selection, --mcp-github-auth, and session-scoped read-only directory approvals.
GitHub Copilot CLI v1.0.90-6
Added GPT-6.1 Sol to model selection.
Google Cloud CLI remote MCP server
Google Cloud introduced the Google Cloud CLI remote MCP server in preview, giving AI agents access to gcloud and bq commands.
Google Vids caption customization
Google Vids captions can now be customized for font, position, and animation.
HSTU Generative Recommender Workflow
NVIDIA recsys-examples now provides an end-to-end HSTU inference workflow with Dynamo-Triton, achieving up to 5.93x lower latency at batch size 8.
Lakebase Postgres extensions
Supported Postgres extensions updated to newer versions, including postgis 3.6.4 on Postgres 18 and hll 2.21.
Ling 3.1 Flash on AI Gateway
Ling 3.1 Flash from InclusionAI is available on AI Gateway, free through , with 262K-token context.
MCP Inspector 2.2.0
MCP Inspector 2.2.0 released with sandbox proxy loading and keychain degradation fixes.
MCP Inspector 2.3.0
MCP Inspector 2.3.0 released with loopback binding and sandbox port pinning fixes.
MCP Inspector 2.4.0
MCP Inspector 2.4.0 released with app-rendered form elicitations and SecretStore support.
MCP Inspector 2.5.0
MCP Inspector 2.5.0 released with Firefox smoke tests and tool schema rendering fixes.
Microsoft plugin registry
Plugin registry rolling out now for Copilot Home, Code, Autopilot, Microsoft 365 apps, and SharePoint.
NVIDIA cuObject and SCADA Server SDK
NVIDIA cuObject client and server libraries are now generally available, with the SCADA Server SDK enabling storage providers to build servers.
Nemotron 3 Diarization
Transformers v5.18.0 adds Nemotron 3 Diarization, an open-weight streaming speaker diarization model supporting up to eight speakers.
RDS M8a instances
Amazon RDS now supports AMD-based M8a instances.
Raycast v2.6
Raycast v2.6 reduces host memory by 50% and adds Auto model preferences: Lightweight, Balanced, Flagship.
Retool 4.66 Edge
Retool 4.66 is now available on the Edge release channel for self-hosted organizations.
SDK v0.0.89
Oversized MCP and Composio tool results can now be recovered in full via a per-session cache with a cline://cache URI.
Spanner Omni GA
Spanner Omni, the deploy-anywhere version of Spanner, is now generally available for on-premises and other clouds.
Together AI LoRA rank limit
Together AI now allows LoRA adapters with rank up to 128, up from 64.
Together Link beta
Together Link beta runs six coding agents on Together AI models on macOS and Linux, installable with one command.
TorchVision 0.29.1
TorchVision 0.29.1, a patch release compatible with PyTorch 2.14.1, with no new features.
Vercel Sandbox Secure Compute
Vercel Sandbox now supports Secure Compute, connecting sandboxes to a team's dedicated network with static IPs and VPC peering.
WorkSpaces Core Blackwell GPU
Amazon WorkSpaces Core Managed Instances adds support for NVIDIA Blackwell GPU.
anthropic-sdk v0.130.0
Adds refusal stop reason, Claude Enterprise analytics, spend limits, RBAC, usage reports, and plugin marketplaces to the Admin API.
anthropic-sdk-go v1.78.0
anthropic-sdk-go v1.78.0 adds a list spend limits endpoint and marks Claude Sonnet 4.5 deprecated with end-of-life November 30, 2026.
anthropic-sdk-java v2.68.0
anthropic-sdk-java v2.68.0 adds a list spend limits endpoint and marks Claude Sonnet 4.5 deprecated with end-of-life November 30, 2026.
langchain-openai 1.6.7
langchain-openai 1.6.7 released with Azure workload identity discovery.
openai-java v4.73.0
Adds external storage provider callback handlers, session traces, translation secrets, and pagination and Azure deployment fixes.
sdk v0.131.0
Adds list spend limits endpoint and deprecates sonnet 4.5.
AI Gateway User Insights
User Insights for AI Gateway is available to all customers at no additional cost, showing model overuse and potential savings.
Agent Runners link previews
Every site created with Agent Runners now includes Open Graph tags for rich link previews.
Azure Cosmos DB in Fabric Database Hub
Azure Cosmos DB accounts can now be discovered and monitored from Fabric Database Hub in public preview.
BigQuery FAILOVER_HISTORY view
BigQuery users can query INFORMATION_SCHEMA.FAILOVER_HISTORY for near real-time failover events.
Claude Code v2.1.285
Claude Code v2.1.285 adds CLAUDE_CODE_DISABLE_WEB_FETCH, claude --desktop, and plugin configure options.
Claude on Bedrock in India, South Korea, Singapore
Amazon Bedrock expands Claude model availability to India, South Korea, and Singapore.
Cloudflare Application Profiles
Positive security enforcement with Cloudflare Application Profiles.
Cloudflare Containers disk limit
Custom Container instance types can now allocate up to 20 GB disk regardless of memory.
Cloudflare network log fields
Gateway network logs and Network Session Logs now identify Mesh, Workers VPC, and Tunnel replica traffic.
ComfyUI v0.38.0
ComfyUI v0.38.0 released.
DOKS Isolated Worker Nodes
Isolated Worker Nodes for DigitalOcean Kubernetes are generally available, removing public IPv4 addresses from nodes.
Databricks JDBC Driver (Simba) 2.8.4
Simba JDBC Driver (Legacy) 2.8.4 adds Java 25 support and upgrades libthrift, httpclient5, httpcore5, and lz4-java.
DiskANN Vector Index in Azure SQL
DiskANN Vector Index and Search are generally available in Azure SQL Database, Managed Instance, and Fabric SQL database.
ElastiCache Serverless for Valkey
Amazon ElastiCache Serverless for Valkey now supports public endpoints.
Final Cut Camera 2.4
Final Cut Camera 2.4 adds variable aperture on iPhone 18 Pro, Cinematic mode effects for regular video, and iOS 27 pro options.
Firefox FX 157
Firefox FX 157 rolls out the new design to all desktop and mobile users.
GKE Agent Sandbox for RL
GKE Agent Sandbox optimized for RL and Agent Sandbox RL orchestration SDK are generally available, with 10x-45x faster time-to-first-command.
GPT-6.1 Sol in GitHub Copilot
GPT-6.1 Sol is generally available in GitHub Copilot for Pro+, Max, Business, and Enterprise users.
GPT-6.1 Sol on AI Gateway
GPT-6.1 Sol is available on Vercel AI Gateway as openai/gpt-6.1-sol with lower standard input and output pricing than GPT-6 Astra.
GPT-6.1 Sol on Netlify AI Gateway
OpenAI's GPT-6.1 Sol model is available through Netlify's AI Gateway and Agent Runners with zero configuration required.
Gemini 3.8 Flash Lite TTS in Vids
Google Vids upgraded AI voiceovers and avatar narration to Gemini 3.8 Flash Lite TTS, available now.
Gemini 3.8 Flash default for AlphaEvolve
Gemini 3.8 Flash is now the default model for AlphaEvolve experiments, replacing Gemini 3.5 Flash.
Gemini Enterprise security agents
New partner-built security agents and AI defenses from Acalvio and Britive are available in Gemini Enterprise.
GitHub Copilot CLI v1.0.90-5
Fixed model availability message and MCP tool calls completing despite progress updates.
Jev in LangSmith Evals
Jev is available as a judge for evaluations in LangSmith, offering fast, low-cost evaluation of open-ended agent behavior.
Lasv5 and Laosv5 Azure VM series
Storage optimized Lasv5 and Laosv5 Azure VM series are generally available.
NVIDIA VSS Blueprint 3.3
VSS Blueprint 3.3 adds the Build Vision Agent skill and Adaptive EVS, cutting alert contextualization latency 17% and increasing concurrent VLM streams 46%.
Ollama v0.35.0
Ollama now supports decision models through /v1/systemone, returning choices, probabilities, and scores.
OpenAI GPT-6.1 Sol on Unity Gateway
OpenAI GPT-6.1 Sol is available on Unity Gateway via Foundation Model APIs.
OpenAI Python SDK v3.21.0 adds GPT-6.1 Sol model identifier
The openai-python SDK release adds the GPT-6.1 Sol model identifier.
Plaid Speed
Plaid inference for GPT-6 Astra modes runs up to 6x faster and costs 6x per token.
Qwen Code Desktop v0.24.7
Qwen Code Desktop v0.24.7 released with session diagnostics fix, Java SDK attestation client, trajectory time range, and Qwen Live endpoint settings.
RunPod Deploy When Available
RunPod's Deploy When Available is now GA, queuing for any GPU spec and deploying when capacity opens.
Seer Agent
Seer Agent gains new capabilities for interacting with Sentry projects and collecting data from more places.
Sentry JavaScript SDK 11.1.0
Sentry JavaScript SDK 11.1.0 traces TypeSafe Jev and adds typesafeIntegration for @typesafe-ai/sdk, enabled by default.
Shopify App Pricing migration
Apps using the Billing API can now migrate existing subscriptions to Shopify App Pricing via Partner Dashboard tool or Shopify CLI commands.
TESSERA Earth observation embeddings
TESSERA global Earth observation embeddings are now available on AWS Open Data.
Threat Signals
Agentic skills for open-source threat intelligence, free for every Cloudflare account.
TogetherLink beta
TogetherLink beta runs Claude Code, Codex, and desktop apps on Together AI models with automatic routing, cost tracking, and headless mode.
Visual Studio BYOM
Bring Your Own Model is available in preview and enabled by default across Community, Professional, and Enterprise SKUs.
WSL Containers (WSLC)
WSL containers is now generally available with the new wslc.exe command.
a2a-python v1.2.0
a2a-python v1.2.0 adds HTTP+JSON responses, caching headers, multi-replica cluster mode, and media type validation.
langchain-anthropic 1.7.5
Release adds Claude Sonnet 5.5 compatibility and serializes invalid tool calls as tool use on replay.
langchain-core 1.6.6
langchain-core 1.6.6 released with Claude Sonnet 5.5 compatibility fix.
openai-go v3.68.0
OpenAI Go SDK v3.68.0 adds computer use to beta agents.
openai-java v4.72.0
GPT-6.1 Sol model identifier and computer use for beta agents in Java SDK v4.72.0.
openai-node v7.25.0
OpenAI Node SDK v7.25.0 adds computer use to beta agents.
1Password Event Logs connector (Beta)
1Password Event Logs connector is now available in Lakeflow Connect in Beta, ingesting 1Password event logs into Databricks.
@modelcontextprotocol/core 2.2.0
@modelcontextprotocol/core 2.2.0 published with deprecation warning for OAuth providers missing expectedIssuer.
@modelcontextprotocol/server 2.2.0
@modelcontextprotocol/server 2.2.0 published with fixes for unhandled promise rejection and stack overflow.
@modelcontextprotocol/server-legacy 2.2.0
@modelcontextprotocol/server-legacy 2.2.0 published with dependency update to core 2.2.0.
Agent Runners inline preview
Agent Runners now shows a deploy preview inline next to the prompt.
Akamai WAF connector (Beta)
Akamai WAF connector is now available in Lakeflow Connect in Beta, ingesting WAF security events from Akamai into Databricks.
Anthropic Python SDK v1.9.0
Adds claude-sonnet-5-5, between_tools thinking type, and cache diagnostics GA.
Ask in Google Earth Engine
Ask, a Gemini-powered chat assistant, is available in Google Earth Engine Code Editor for writing, debugging, and optimizing geospatial queries.
BigQuery Data Transfer Service MCP server
The BigQuery Data Transfer Service MCP server is now Generally Available (GA).
Blazor AI components
Experimental Blazor AI components for agentic UI, available as a prerelease package with .NET 11 RC1 SDK.
Claude Agent SDK Python v0.2.161
Python SDK v0.2.161 released with bundled Claude CLI updated to version 2.1.284.
Claude Code v2.1.284
Claude Sonnet 5.5 is now the default Sonnet model on the Anthropic API with 1M context, $2/$10 per Mtok, $0.20/Mtok cache reads.
Claude Sonnet 5.5 in Devin
Claude Sonnet 5.5 is available in Devin, scoring 64.4% on FrontierCode 1.1.
Claude Sonnet 5.5 in GitHub Copilot
Claude Sonnet 5.5 is generally available in GitHub Copilot for Pro, Pro+, Max, Business, and Enterprise users.
Claude Sonnet 5.5 on AI Gateway
Claude Sonnet 5.5 is available on AI Gateway as anthropic/claude-sonnet-5.5.
Claude Sonnet 5.5 on AWS
Claude Sonnet 5.5 is now available on AWS.
Claude Sonnet 5.5 on AWS GovCloud (US)
Claude Sonnet 5.5 is now available on AWS GovCloud (US).
Claude Sonnet 5.5 on DigitalOcean Inference
Claude Sonnet 5.5 is now available on DigitalOcean Inference for serverless inference and Agent Development Kit.
Claude Sonnet 5.5 on Netlify
Claude Sonnet 5.5 is available through Netlify AI Gateway and Agent Runners with zero configuration required.
Codex CLI rust-v0.158.0
Codex CLI 0.158.0 adds copy-on-select, OAuth client secrets for MCP, bearer tokens for exec-server, and transparent image backgrounds.
CrewAI 1.15.23
CrewAI 1.15.23 adds native Gemini 3.8 Flash support and crewai eval improvements.
CrowdStrike Falcon Event Stream connector
CrowdStrike Falcon Event Stream connector is available in Lakeflow Connect in Beta, ingesting Falcon Event Stream events into Databricks.
Firebase Phone Number Verification
10 new carrier networks are available today across Malaysia, Spain, Pakistan, and six Vodafone countries.
Firebase plugin for Codex
Firebase agent plugin is available in the Codex plugin directory with agent skills, MCP server, and CLI tools.
GitHub Copilot CLI 1.0.89
Adds Claude Code rule files as custom instructions, click-to-focus inputs, unread turn dots, routing tier suggestions, and MCP OAuth scope support.
GitHub Copilot CLI v1.0.89-6
Copilot CLI v1.0.89-6 improves PR creation to follow repository pull request templates and fixes shell output metadata.
Jev-as-a-Judge in Arize AX
Arize AX now integrates directly with TypeSafe AI, bringing native Jev-as-a-Judge evaluations into the Arize evaluation workflow.
Luxembourg Azure Extended Zones
Luxembourg Azure Extended Zones are generally available.
MCP TypeScript SDK 1.31.0
Stored OAuth tokens and client information now include an issuer field; pass expectedIssuer when constructing OAuth providers.
MCP TypeScript SDK 2.2.0
MCP TypeScript SDK 2.2.0 released with expectedIssuer required for machine-to-machine OAuth providers.
MLX-VLM v0.7.4
Generate multiple images per prompt via num_images for qwen_image, flux2, ideogram4, plus audio and padding fixes.
Microsoft 365 Unified Audit Logs connector
Beta connector ingests unified audit events from Microsoft 365 workloads into Databricks.
Milvus v2.6.24
Milvus v2.6.24 released with lower peak memory and faster filtered search.
Milvus v3.0.2
Milvus v3.0.2 released with search and query performance improvements.
Okta System Logs connector
Beta connector ingests Okta System Log audit and security events into Databricks.
OpenAI Python SDK v3.20.0
OpenAI Python SDK v3.20.0 adds Agents credential and session options, Cyber access programs, and incremental WebSocket snapshots.
PostHog Backfill App Store analytics
Data Warehouse can backfill App Store Connect analytics from account inception or January 2024 on first sync, resync, or full refresh.
Rekognition Face Liveness Feedback Codes
Amazon Rekognition Face Liveness now returns Feedback Codes.
SQLAlchemy 2.1 mssql-python support
SQLAlchemy 2.1.0 is generally available with built-in mssql-python support for SQL Server and Azure SQL.
Valkey 9 on DigitalOcean
Valkey 9 is now available for database clusters, and new clusters use it by default.
Vector search in Azure SQL
Vector search and vector indexes are generally available in Azure SQL.
Workday Activity Logging connector
Beta connector ingests Workday user activity log events into Databricks.
Z4D machine family GA
Storage-optimized Z4D VM and bare metal instances are generally available with up to 84,000 GiB Local SSD and up to 40% better performance than Z3.
anthropic-sdk-go v1.76.0
Anthropic Go SDK v1.76.0 adds claude-sonnet-5-5, between_tools thinking type, and cache diagnostics GA.
anthropic-sdk-java v2.66.0
Anthropic Java SDK v2.66.0 adds claude-sonnet-5-5, between_tools thinking type, and cache diagnostics GA.
bedrock-sdk v0.34.0
Anthropic Bedrock SDK v0.34.0 adds claude-sonnet-5-5.
claude-agent-sdk-typescript v0.3.284
claude-agent-sdk-typescript v0.3.284 adds renamed skill directory aliases, ultracode settings, and fixes forkSession and getSessionMessages bugs.
foundry-sdk v0.5.0
Foundry SDK v0.5.0 adds claude-sonnet-5-5.
langchain 1.4.3
langchain 1.4.3 supports Bedrock Mantle chat models in init_chat_model and recognizes GPT-6 structured output.
langchain-fireworks 1.7.0
langchain-fireworks 1.7.0 adds prompt caching middleware and fixes mid-stream read timeouts.
playwright-mcp v0.0.83
Bug fixes for browser_find, browser_navigate, browser_reload, and download handling.
sdk v0.129.0
SDK v0.129.0 adds claude-sonnet-5-5, between_tools thinking type, and ClientToolUnion.
vertex-sdk v0.20.0
Vertex SDK v0.20.0 adds claude-sonnet-5-5.
Compute Engine X5 series
Compute Engine X5 series is generally available with 48TB memory configurations, up from the X4's 32TB limit.
Copilot CLI v1.0.89-5
Copilot CLI v1.0.89-5 pre-release adds Claude Code rule files in .claude/rules as custom instructions.
InvokeAI 6.14.2
Version 6.14.2 adds custom font import for Canvas text and style transfer to krea-2 via reference image.
KoboldCpp 1.122.1
KoboldCpp 1.122.1 adds an integrated KoboldCpp Agent with 9 built-in tools and a 2k token system prompt.
Lovable connectors and GPT-6 models
Lovable adds Discord and Google Business Profile connectors, plus GPT-6 Sol and GPT-6 Luna for app AI features.
Unsloth CUDA 13 Wheels
Prebuilt Linux x86_64 CUDA 13 wheels for flash-attn 2.8.4, causal-conv1d 1.7.0, and mamba-ssm 2.3.2.post1.
Codex rust v0.157.0
Codex rust-v0.157.0 adds GPT-6 Sol and Luna to the model catalog, including Amazon Bedrock support and migration prompts for older models.
Zed v1.21.0
Zed v1.21.0 adds BYOK support for Claude Opus 5.5 with an Anthropic API key and GPT-6 Astra, Sol, and Luna with an OpenAI API key.
Ollama v0.34.4
Ollama v0.34.4 makes structured outputs on thinking models apply in a single pass, and Qwen 3.8 prompt processing is faster on Apple Silicon.
Copilot weekly releases
GitHub Copilot adds Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and Grok 4.7 across Pro, Pro+, Max, Business, and Enterprise plans, with local sandboxing in the Copilot app now in public preview.
Gemini TTS on AI Gateway
Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS from Google are now available on AI Gateway, generating speech in more than 100 languages with long-form narration and two-speaker dialogue.
Omni 1.1 in Vids
Google Vids now supports generating and upscaling AI videos to 1080p with Gemini Omni 1.1 Flash, with full rollout starting .
Meet occupancy counting
Occupancy counting is now available for Android-based Logitech Gen 2 room hardware, starting with Logitech Rally Board 65, with an extended rollout starting .
Compute Engine X5 48TB instances
New X5 series generally available with 48TB memory configurations, up from the 32TB X4 limit.
PostHog AI Observability Backfill
AI Observability evaluation can now run on data already collected, instead of only on new data as they arrive.
16k context LLM models
RunPod now supports Panchovix's 16k-token context models.
AI agent skills for AWS MCP Server
AWS End User Messaging and Amazon SES now offer AI agent skills for the AWS MCP Server.
Better Forge template
RunPod released Better Forge, a template for Stable Diffusion pods with a total payload of approximately 12GB.
Claude Agent SDK TypeScript v0.3.283
v0.3.283 adds plugin_errors to SDKSystemMessage, fixes session rewinding, and includes warnings in stream-json output.
Cline Desktop v0.0.36
Desktop v0.0.36 fixes proxy startup failures and window sizing on scaled displays.
DSPy 3.4.0
DSPy 3.4.0 introduces Jev integration with three experimental decision types and native LM engines.
EC2 C8i and C8i-flex instances
Amazon EC2 C8i and C8i-flex instances are now available in additional regions.
EC2 M8i and M8i-flex instances
Amazon EC2 M8i and M8i-flex instances are now available in additional regions.
EC2 R8i and R8i-flex instances
Amazon EC2 R8i and R8i-flex instances are now available in additional regions.
FastMCP v4.0.10
Task-enabled tools now work behind search transforms and CodeMode.
Flutter Replay Screenshots
Session Replay for Flutter Android can use configurable screenshot resolution, JPEG quality, and native-screen pixel formats.
Genie Code document processing
Genie Code can now build end-to-end document processing pipelines by orchestrating parsing, classification, extraction, and validation.
Genie One MCP server
The Genie One MCP server is now generally available as a Databricks-provided MCP Service in Unity Gateway.
GitHub Actions query result cap
GitHub Actions API and UI now report "2,500+" when workflow run query results exceed 2,500 records.
GitHub Copilot CLI 1.0.89-4
Copilot CLI pre-release 1.0.89-4 adds Auto routing tier suggestions and configurable direct plugin installs.
Google Calendar time zones
Google Calendar on the web now displays up to three time zones, up from two.
Kilo Code JetBrains 7.1.8
JetBrains 7.1.8 adds checkpoints settings, companion skill installs, CycloneDX SBOMs, and OAuth client ID metadata support.
Kilo Code v7.8.1
Publishes CycloneDX SBOMs and supports public HTTPS pages in localhost previews.
LangSmith Custom Apps
LangSmith Custom Apps lets users build, publish, and run custom UIs on LangSmith data directly inside LangSmith.
Langfuse v4.45.4
v4.45.4 refreshes embedded Langfuse skills and skips Azure LLM connection tests.
Langfuse v4.46.0
v4.46.0 adds side-by-side experiment comparison, formatted JSON, skill management, and 100-row tracing tables.
LiteLLM v1.100.3
LiteLLM v1.100.3 released with 7445 commits to main since this release.
Memorystore for Valkey 9.1
Memorystore for Valkey 9.1 is generally available with up to 3x QPS at microsecond latency.
Nemotron 3 Diarization on DigitalOcean
NVIDIA Nemotron 3 Diarization model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit.
OpenHands v1.24.0
v1.24.0 adds toggling all workspace folders, scoped OpenAI subscription caches, and read-only shared automation conversations.
Pixel Canary on AI Gateway
Pixel Canary is available as stealth/pixel-canary on AI Gateway, free for a limited time, with 90.3% Next.js eval baseline.
Pydantic AI v2.50.0
Adds DecisionModel and exposes OpenAI service_tier in provider details.
Pydantic AI v2.51.0
Adds OpenAI GPT-Live support with OpenAILiveModel and exposes context_window_used.
Railway Free VMs
Free VMs with 2 vCPU and 2 GB RAM are available via ssh railway.new with no account required.
Raycast External Model Providers
Raycast v2.5 lets extensions provide their own AI models to AI Chat.
RunPod Serverless GPU and SGLang
RunPod now supports up to four 80GB GPUs per worker and offers an SGLang quick deploy endpoint.
Storage Intelligence advisor
Storage Intelligence advisor is generally available along with expanded storage batch operations capabilities.
Tags for Databricks assets
Tags for dashboards, notebooks, Databricks apps, and Genie Agents are now generally available.
Vercel Container Registry GitHub Action
New vercel/vcr-action/login action authenticates with GitHub OIDC and pushes container images to VCR.
Vercel Sandbox memory observability
Sandbox memory usage data now available in dashboard and CLI, reporting average, P75, and P95 memory.
runpod-python 0.10.0 Local API Server
runpod-python 0.10.0 adds a local API server for testing worker handlers via --rp_serve_api.
xAI Grok 4.7 in OCI Generative AI
xAI Grok 4.7 is now available on demand in OCI Generative AI with a 500,000-token context window.
Amazon GameLift Servers
GameLift Servers is now available in 5 new regions and 8 Local Zones.
Amazon RDS for MySQL Extended Support
Amazon RDS for MySQL Extended Support adds minor versions 5.7.44-rds.20260902 and 8.0.46-rds.20260908.
Amazon RDS for PostgreSQL post-quantum TLS
Amazon RDS for PostgreSQL now supports post-quantum TLS key exchange.
Android Studio BYOA
Android Studio Canary now supports Bring Your Own Agent with Claude Agent, OpenAI Codex, and Google Antigravity.
Azure Instant Access for VM restore points
Azure Instant Access for VM restore points is generally available.
Model Armor Melbourne
Model Armor prompt injection and jailbreak detection filters are available in Melbourne with data residency enforcement.
harness-cli v0.1.3
harness-cli v0.1.3 replaces setup Q&A with Quickstart, Customize, and Export, and adds /tools.
huggingface_hub v1.33.0
huggingface_hub v1.33.0 adds a validating progress bar for large Xet uploads and simpler skills installs.
huggingface_hub v2.0.0
huggingface_hub v2.0.0 replaces its HTTP dependency with httpx2.
langchain-openai 1.6.6
langchain-openai 1.6.6 released with a fix that raises on error events in the stream path.
ComfyUI v0.37.2
ComfyUI v0.37.2 released with no specific numeric change stated.
Connect routing step data in lake
Amazon Connect Customer now provides routing step data in the analytics data lake.
Gemini Notebook in Google Docs
Google Docs can now ground AI prompts in existing Gemini Notebook sources with inline citations.
Gemini Omni 1.1 Flash in Vids
Gemini Omni 1.1 Flash is now in Google Vids with 1080p generation and upscaling, rolling out starting .
GitHub Actions Node 20 retirement
GitHub Actions runners now use Node 24, and Node 20 is no longer available.
GitHub Copilot Local Sandboxing
GitHub Copilot app adds per-project local sandboxing for filesystem, network, and credential access, off by default.
GitHub Copilot OTel support
GitHub Copilot app now supports OpenTelemetry configuration through enterprise-managed settings.
Google Admin temporary roles
Admins can assign roles for predefined durations such as 30 days or a custom expiration date and time.
Google Meet occupancy counting
Occupancy counting is available for Android-based Logitech Gen 2 room hardware starting with Rally Board 65.
LiteLLM v1.100.2
LiteLLM released version 1.100.2.
LiteLLM v1.101.1
Released LiteLLM v1.101.1.
LiteLLM v1.102.1
LiteLLM v1.102.1 released with 4148 commits since previous release.
LiteLLM v1.99.3
LiteLLM released version 1.99.3.
Vercel Blob stores
Store creation limits of 100/500/1,000 are removed; creation is billed at $5.00 per million on Pro.
claude-code v2.1.281
Claude Code v2.1.281 adds gateway support for desktop policy blocks, Bedrock IAM role assumption, and Bedrock guardrails.
codex rust-v0.156.1
Release 0.156.1 of the codex Rust crate is tagged.
langchain-anthropic 1.7.4
langchain-anthropic 1.7.4 adds Opus 5.5 and GPT-6 profile augmentations.
langchain-openai 1.6.5
langchain-openai 1.6.5 adds Opus 5.5 and GPT-6 profile augmentations and mid-conversation tool changes.
llama.cpp v0.5.0
llama.cpp v0.5.0 adds HRM-Text support, MiMo-V2.6 and HunyuanOCR conversion, and multi-address HTTP binding.
vLLM v0.30.1rc0
vLLM v0.30.1rc0 adds MI355 dense NVFP4 and MoRI kernel mirrors.
Amazon EMR 7.14
Amazon EMR 7.14 is now available.
C++ whole codebase indexing
C++ code intelligence in GitHub Copilot CLI now supports whole codebase indexing, enabled by default.
Claude Opus 5.5
Claude Opus 5.5 is now the default Opus model with 1M context and $4/$20 per Mtok.
Claude Opus 5.5 in GitHub Copilot
Claude Opus 5.5 is available in GitHub Copilot and billed at provider list pricing under usage-based billing.
Claude Opus 5.5 on AI Gateway
Claude Opus 5.5 is available on AI Gateway with a 1M-token context window and 128K max output tokens.
Claude Opus 5.5 on AWS GovCloud
Claude Opus 5.5 is now available on AWS GovCloud (US).
ComfyUI v0.37.1
ComfyUI v0.37.1 tagged on with no numbered change listed.
Confluence for Google Chat
Confluence integration for Google Chat is available now to all Google Workspace customers.
Drives for Vercel Sandbox
Drives for Vercel Sandbox are now in public beta on Hobby, Pro, and Enterprise with a default maximum size of 1 TiB.
GPT-6 Sol and GPT-6 Luna
OpenAI GPT-6 Sol and GPT-6 Luna are now generally available on Amazon Bedrock.
GPT-6 Sol and Luna in Copilot
GPT-6 Sol and GPT-6 Luna are now selectable in GitHub Copilot across Pro, Pro+, Max, Business, and Enterprise plans.
GPT-6 Sol and Luna on AI Gateway
GPT-6 Sol and GPT-6 Luna are now available on Vercel AI Gateway at a lower price than GPT-6 Astra.
Genie One MCP
Genie One MCP is now generally available.
Google Sheets pivot table sorting
Google Sheets pivot tables now support manual reorder and custom sort, available to all Workspace customers.
LiteLLM v1.102.0
LiteLLM v1.102.0 tagged with no numbered change listed.
Mac mini and Mac Studio
Mac mini with M6 starts at $899, Mac Studio with M5 Ultra starts at $5,499, with up to 4.3x faster AI performance.
NVIDIA P100 EOS on Compute Engine
NVIDIA P100 GPUs on Compute Engine reached end of support and are shut down.
Ollama v0.34.3
Ollama v0.34.3 adds Nemotron H vision model support on Apple Silicon with MLX and fixes HuggingFace model pulls.
langchain-anthropic 1.7.3
langchain-anthropic 1.7.3 released with structured output routing fix and mid-conversation system message support.
langchain-deepseek 1.1.1
langchain-deepseek 1.1.1 released with dependency bumps and strict mode routing fix.
langchain-fireworks 1.6.2
langchain-fireworks 1.6.2 released with test fixes and dependency bumps.
langchain-openai 1.6.4
langchain-openai 1.6.4 released with refreshed OpenAI model profile data.
langchain-openrouter 0.2.9
langchain-openrouter 0.2.9 released with dependency bump anyio 4.13.0 to 4.14.2.
vLLM v0.30.0
vLLM v0.30.0 fixes DeepGEMM CUDA 12.9 release builds.
AI Gateway Jev support
AI Gateway now supports Jev through TypeSafe clients, HTTP API, and AI SDK.
Amazon EVS FedRAMP Class C
Amazon EVS is now in scope for FedRAMP Class C.
Apigee X maintenance
Apigee instances below 1-18-0-apigee-4 will be updated within seven to 21 days.
Azure Sphere OS 26.09
Azure Sphere OS version 26.09 is now generally available.
ComfyUI v0.37.0
ComfyUI v0.37.0 is now available.
GitHub Enterprise credential inventory exports
Enterprise owners can export all credentials via CSV or paginated REST API.
Google Sheets manual calculation
Editors can pause automatic recalculation and trigger a sheet-wide update manually.
Grok 4.7 on Vercel AI Gateway
Grok 4.7 is available on AI Gateway with a 500K token context window and 40% off through .
MiMo V2.6 on AI Gateway
MiMo V2.6 Pro, Flash, and Pro UltraSpeed are available with 1M token context and up to 128K output tokens.
Open WebUI v0.11.4
Slim image is now about 175 MB, 89% smaller than the last release.
Python Workers
Python Workers are now generally available on Cloudflare.
Vercel Connect Microsoft Teams
Vercel Connect now includes a managed connector for Microsoft Teams, available from the dashboard or CLI.
Workday for Google Sheets
Workday for Google Sheets is a new add-on available in the Google Workspace Marketplace.
langchain-core 1.6.4
langchain-core 1.6.4 released with deprecation of chat message history.
langchain-openai 1.6.3
langchain-openai 1.6.3 released with support for GPT-6 request constraints.
langchain-typesafe
langchain-typesafe 0.0.1a3 released with TypeSafeClassifier and experimental middleware.
iPhone 18 Pro lineup
Apple debuted iPhone 18 Pro and iPhone 18 Pro Max, Apple Watch Series 12, Apple Watch Ultra 4, and AirPods 5 at Apple Store locations worldwide on Friday, .
Expert Intelligence in Notebook
Google Workspace introduced Expert Intelligence in Gemini Notebook, featuring more than 100,000 books from major publishers that users can add as sources for grounded responses, infographics, audio overviews, and quizzes.
Gemini Notebook learning tools
Gemini Notebook added an audio recorder, real-time conversation in nearly 100 languages, interactive learning overviews, new quiz formats, and short video overviews in more than 80 languages.
Notebooks in Gemini
Notebooks in Gemini are now available to students, educators, and professionals, letting users add up to 10 sources to a notebook and combine the Gemini app with Gemini Notebook for study guides and video overviews.
Ubuntu 26 runner image
The Ubuntu 26.04 runner image for GitHub Actions is now fully supported on x64 and arm64, and the ubuntu-latest label will migrate from Ubuntu 24.04 to Ubuntu 26.04 between and November 19, 2026.
Workflow execution protections
Workflow execution protections for GitHub Actions are generally available with workflow file targeting, insights, and a REST API, and a default rule disables pull_request_target for public repositories, enforced on .
Ollama v0.34.2
Ollama v0.34.2 added first-run setup with sign-in or local options, an ollama://apps shortcut, and fixed excessive memory growth during long generations with MLX speculative decoding.
Claude Code v2.1.277
Claude Code v2.1.277 added AGENTS.md support, a CLAUDE_GATEWAY_PROXY_IS_EGRESS_BOUNDARY flag, and fixed sessions hanging with no result after internal errors, now reporting the error and exiting with code 1.
Codex rust-v0.155.0
Codex rust-v0.155.0 added experimental voice conversations with live transcripts, Touch ID verification for MCP requests, and AWS credential export commands for Amazon Bedrock.
Codex rust-v0.155.1
Codex rust-v0.155.1 fixed new local TUI sessions leaving reasoning summaries disabled by default, which had caused request rejection by providers that do not support them.
vLLM v0.30.0rc2
vLLM v0.30.0rc2 tagged a bugfix to avoid receive reports for notification-only requests in NIXL.
LangChain 1.4.2
LangChain 1.4.2 fixed preserving model-generated tool calls in human-in-the-loop tool call edits and added a notice to ToolMessage.
Zed v1.20.2
Zed v1.20.2 fixed payment errors from non-Zed model providers incorrectly prompting users to upgrade to Zed Pro, and fixed different snippet extensions for the same language canceling each other.
AWS Continuum Updates
AWS Continuum now supports credential testing and accessible domain suggestions.
Amazon SNS 1 MiB payloads
Amazon SNS now supports message payloads up to 1 MiB.
Code coverage ruleset REST API
GitHub now allows managing the Restrict code coverage repository ruleset option via generally available REST API.
Copilot weekly releases
GitHub Copilot adds generally available usage metrics for VS Code Agents and budget request approval for Business and Enterprise plans.
EC2 X8i in São Paulo
Amazon EC2 X8i instances are now available in the South America (São Paulo) Region.
ECS Express Mode Graviton
ECS Express Mode now supports AWS Graviton ARM64 workloads.
GitHub Copilot model deprecation
GitHub Copilot will deprecate Gemini 3.7 Flash, GPT-5.5, GPT-5.4, GPT-5.4 mini, GPT-5 mini, and Grok 4.5 on .
RTB Fabric AZ affinity
AWS RTB Fabric now supports configurable Availability Zone affinity.
Resilience Hub capabilities
AWS Resilience Hub adds three new capabilities.
AWS Batch bulk job cancellation
AWS Batch now supports bulk job cancellation and termination.
Agentic CLI usage metrics
GitHub Copilot CLI reports now include agentic activity metrics for skills, custom agents, MCP servers, slash commands, and plugins.
Amazon Corretto 27
Amazon Corretto 27 is now generally available, a new long-term support JDK distribution.
Oracle DB@GCloud Turin
Oracle Database@Google Cloud is now available in europe-west12 (Turin, Italy) for Exadata Database Service.
Vercel Marketplace
Native Marketplace resources can now connect to custom environments on Pro and Enterprise plans.
Vercel Sandbox Harbor evals
Harbor evals can now run on Vercel Sandbox with each trial in an isolated Firecracker microVM, enabling parallelization beyond local machine limits.
AWS Client VPN
AWS Client VPN now supports MacOS 27 Golden Gate.
Amazon SageMaker AI
Amazon SageMaker AI now supports serverless model customization for NVIDIA Nemotron 3.5 Lightning.
AWS PrivateLink
AWS PrivateLink is now available for Pro and Enterprise teams as part of Advanced Networking, with the first connection included and each additional connection costing $30 per month plus $0.04 per GB data transfer.
Adaptive Intelligence
Cloudflare launched Adaptive Intelligence on , a bot detection engine that makes getting through so slow and costly that attacks stop being worth running, analyzing more than a trillion requests a day.
Claude Code v2.1.261
Claude Code v2.1.261 adds bashOutputMaxChars and taskOutputMaxChars settings up to 128K characters, a /skill-doctor command to show unused skills, and fixes for Remote Control sessions and Bedrock setup.
Gemini custom instructions
Custom instructions for Gemini in Workspace now apply across Ask Gemini in Drive, Ask Gemini in Chat, and the Gemini side panel in Slides, Sheets, and Gmail, with rollout starting .
Google Pics
Google Pics is generally available starting , bringing AI image generation and object-based editing into Google Workspace with upscaling to 2K or 4K and editing from Google Docs or Slides.
Ollama v0.33.3
Ollama v0.33.3 adds image and audio support for Gemma 4 on the MLX engine, reports cached prompt tokens, and honors GGUF model defined default parameters.
Workspace Studio new steps
Workspace Studio Flows adds four automation steps: Move Drive file, Copy Drive file, Send a Chat reply, and Reply to email, with admin controls rolling out starting .
Zed v1.18.0
Zed v1.18.0 adds support for GPT-5.6's 1M-token context window on Amazon Bedrock, Gemini 3.5 Flash-Lite, Grok 4.5 and Grok 4.6, and inline debugger values for C and C++.
Cursor agents in Sandbox
Cursor Cloud Agents can now run in Vercel Sandbox, providing isolated Firecracker microVMs for each agent request.
Vulnerability Discovery
Cloudflare announces early access to Vulnerability Discovery and Remediation, using OpenAI Daybreak models to detect and propose fixes for codebase vulnerabilities.
Google Vids summaries
Google Vids now turns Google Docs, PDFs, and Word files into AI-generated video summaries, available now on Rapid Release.
GLM 5.3 Flash
GLM 5.3 Flash from Z.ai is now available on AI Gateway as zai/glm-5.3-flash, a multimodal coding model with a 1M-token context window that accepts text and image inputs and supports function calling, structured output, and streaming.
Hy4 Preview on AI Gateway
Hy4 Preview from Tencent is now available on AI Gateway, an open-source Mixture-of-Experts model with 770B total parameters and 49B active per token, serving a context window of 1M tokens.
Ling 3.0 Flash Fin
Ling 3.0 Flash Fin from Inclusion AI is now available on AI Gateway and free to use through , with a 256K-token context window, up to 32K output tokens, and support for reasoning and function calling.
Qwen 3.8 Flash
Qwen 3.8 Flash from Alibaba is now available on AI Gateway as alibaba/qwen3.8-flash, taking text and images as input with a 1 million token context window and up to 65k tokens in a response.
Speed Insights free tier
Speed Insights now has a free tier available on every plan for any number of projects, including 10,000 events per team every 30 days, with the paid product renamed Speed Insights Plus.
Vercel Connect
Vercel Connect is now generally available on all plans and in v0, replacing stored long-lived provider secrets with short-lived scoped tokens requested at runtime, with 100+ preset connectors and pricing at $3 per 1,000 token requests and $0.95 per 1,000 triggers on Pro.
Vercel Sandbox regions
Vercel Sandbox now runs globally starting with four regions: iad1, sfo1, cle1, and cdg1, with region selection on all plans and failover regions configurable for Pro and Enterprise teams.
Drive AI classification
Gemini-based data classification in Google Drive is now in open beta, automating file labeling to enforce DLP policies at scale.
Drive CSE preview beta
Google Drive now supports direct previewing of client-side encrypted PDF and image files in beta, eliminating unnecessary downloads.
Workspace weekly recap
Google Workspace announced updates including Meet hardware UI, Chat member list controls, and data import for Microsoft Teams and OneDrive.
Mac mini M6/M5 Pro
Apple's new Mac mini with M6 delivers up to 4x faster AI performance, 2x faster storage and graphics, and 40 percent faster CPU. M5 Pro supports up to 64GB unified memory. Pre-orders start today, availability .
Deployment Storage
Vercel introduces Deployment Storage billed at $0.10 per GB per month with Hobby teams including up to 10 GB, keeping deployment files available for inspection and instant rollback in seconds with no rebuild.
Fish Audio free
Fish Audio models arrive on AI Gateway with every model free for 30 days through , including text-to-speech normally priced at $15.00 per million characters and speech-to-text at $0.36 per hour of audio.
GLM 5.3
GLM 5.3 from Z.ai is available on AI Gateway with improvements over GLM 5.2 at complex software engineering and multi-step agent tasks while producing fewer output tokens, keeping a 1M token context window and 128K maximum output.
Bot Preference Sync
Cloudflare's Bot Preference Sync, available to all customers from Free to Enterprise, updates robots.txt to match your AI bot configuration for Search, Agent, and Training traffic.
DeepSeek V4 Flash Vision
DeepSeek V4 Flash Vision Experimental is now on AI Gateway, accepting images alongside text, with tool use, reasoning, and caching unchanged.
DeepSeek V4 Pro updated weights
DeepSeek V4 Pro now runs on updated weights on AI Gateway, used by default when you call deepseek/deepseek-v4-pro.
Exa web search free
Exa web search is now free on AI Gateway through , and it is now the default web search for eve agents.
Grok 4.6 on AI Gateway
Grok 4.6 from SpaceXAI is now available on AI Gateway with a 500K token context window and text and image inputs.
Vercel CLI 100+ services
You can now integrate 100+ services through Vercel Connect from the CLI, passing the service name to create a connector and attach it to your project.
Vercel Managed Images
Vercel Managed Images introduces versioned, open-source base images, with new sandboxes defaulting to vercel/sandbox/universal:latest on Ubuntu 26.04 with Node.js 24 and Python 3.14.
Vercel CDN ECH
Vercel CDN now supports Encrypted Client Hello (ECH) for domains managed by Vercel DNS, encrypting the SNI in the TLS handshake.
CT Monitoring GA
Cloudflare made Certificate Transparency Monitoring generally available, now filtering out Cloudflare-issued certificates to reduce noise for over 650,000 customer domains.
Agent Plugins 1.0.0
Agent Plugins 1.0.0 is publicly available as an open, vendor-neutral standard for packaging Agent Skills and MCP servers into portable plugins, supported at launch across ChatGPT and Codex, Cursor, GitHub Copilot, Kiro, and VS Code.
Vercel Sandbox quotas
Vercel Sandbox default quotas on Pro and Enterprise plans rose from 2,000 to 10,000 concurrent sandboxes and from 200 or 400 vCPUs per minute to a dynamic rate up to 5,000 vCPUs per minute.
v0 API
The new v0 API is generally available, giving programmatic headless access to v0's app-building agent that generates an app, starts a dev server in a Vercel Sandbox, and returns a preview URL you can embed.
Custom Agent sharing
Notion now lets you share context with Custom Agents directly from the Share menu, without clicking over to the agent's settings.
DeepSeek V4 Flash
DeepSeek V4 Flash now runs on updated weights by default on AI Gateway, scoring 82.7 on Terminal-Bench, up 25.8 points from 56.9 in the April preview, with no change to the model ID or your code.
Faster Vercel deployments
Vercel deployments are now up to 7 seconds faster end to end, with up to 5 seconds of fixed platform overhead removed from every build and up to 2 seconds more saved from the newest Vercel CLI.
Grok Voice Think Fast 2.0
Grok Voice Think Fast 2.0 from xAI is now available on AI Gateway as a speech-to-speech voice model that reasons in parallel with speech and fires tool calls sooner with fewer reasoning tokens.
Sign in with ChatGPT
Sign in with ChatGPT adds your ChatGPT account as an authentication option for Vercel, available when adding the Vercel plugin to ChatGPT and when signing in to Vercel or v0.
AI Meeting Notes triggers
Notion's AI Meeting Notes can now trigger Custom Agents to update trackers, post recaps, or file tickets automatically.
High contrast mode
Notion added high contrast mode as a display option, available on desktop and web.
Apple Upgrade leasing
Apple Upgrade offers leasing for iPhone starting at $17.99 per month, Apple Watch at $11.99, Mac at $24.99, and iPad at $11.99, provided by Klarna.
AI Gateway service tiers
AI Gateway now supports service tiering with default, priority, and flex tiers, where priority costs about 1.8 to 2 times default pricing and flex costs about 0.5 times default pricing.
Gemini 3.6 Flash
Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now available on AI Gateway with no platform fee on inference.
Laguna S 2.1
Laguna S 2.1 from Poolside is now available on AI Gateway in free and paid versions, with the paid version supporting a 1M token context window.
Ling 3.0 Flash
Ling 3.0 Flash from Ant Group is now available on AI Gateway and is free to use for the next three weeks, through August 3rd.
Python precompiled bytecode
Vercel now compiles Python functions to bytecode at build time, and cold starts for the median-sized function dropped from 2.8 seconds to 1.3 seconds in benchmarks.
Vercel Connect preset connectors
Vercel Connect now includes preset connectors for over 100 services, including Shopify, Resend, Sanity, Okta, Workday, and Jira.
Workflow extended durations
Workflow steps on Pro and Enterprise plans can now run for up to 30 minutes, up from 800 seconds, using extended function durations in beta.
Claude Opus 5 on AI Gateway
Claude Opus 5 is now available on AI Gateway with model fallbacks for safety blocks and fast mode via speed: 'fast'.
Notion Workers credits
Notion Workers usage is now visible in the credits dashboard, free to try during beta on Business and Enterprise plans.
Apple Maps for Ford UEV
Apple Maps will power navigation in Ford's Universal Electric Vehicle Platform via MapKit for Automotive SDK, coming in 2027.
GLM 5.2 discount
GLM 5.2 is 35% off on AI Gateway through when routed through Novita, then stays available at standard provider rates with no markup.
Immutable static asset caching
Vercel now reuses static files across deployments for frameworks that output content-addressed assets, with 17% fewer CDN requests, 24% fewer bytes transferred, deployments up to 30% faster, and up to 60% reduction in global TTFB.
Vercel Blob consistent reads
Vercel Blob now supports consistent reads on private storage with useCache: false, guaranteeing a read reflects the newest write instead of a cached version that can persist for up to 60 seconds after an overwrite.
Vercel CLI project linking
The Vercel CLI now resolves your team before discovering projects, then searches only in that team, making linking faster and more predictable with Vercel CLI 55 as a major version bump with breaking changes.
Flags SDK 10x faster
Flags SDK and Vercel Flags now evaluate multiple feature flags in bulk around 10x faster by reducing microtask queue overhead and creating fewer promises.
Vercel acquires Better Auth
Vercel acquires Better Auth, the open source TypeScript authentication library with 4.7M+ weekly npm downloads and more than 850 contributors, with the team continuing work on Agent Auth for scoped, revocable agent identity.
Lovable apps on Vercel
Vercel now supports Lovable applications with zero configuration, automatically detecting TanStack Start and deploying via Nitro, with every change syncing to GitHub triggering a new deployment.
Notion Agents iOS app
Notion released an iOS app for Notion Agents, letting users put agents to work from anywhere, like prepping for meetings or capturing ideas on the go.
5GB Functions
Vercel Functions now support Node.js and Python deployments up to 5GB in package size on Fluid compute, a 20x increase over the previous 250MB limit, in public beta.
AI Gateway audio support
AI Gateway now supports voice and audio models in beta via AI SDK 7, letting you build realtime voice agents, generate speech from text, and transcribe audio to text with the same observability, spend controls, and bring-your-own-key support as other models.
Fable 5 on AI Gateway
Access to Claude Fable 5 has been restored on AI Gateway following the US Government's decision to lift export controls, with updated safety classifiers and model fallbacks recommended for routine coding and debugging tasks.
Notion 3.6
Notion 3.6 lets you assign tasks to Claude and Cursor as External Agents from a shared board, adds speaker labels to AI Meeting Notes, and gives Notion Agents read and write access to PPTX, XLSX, DOCX, and more.
Sandbox FUSE support
Vercel Sandbox now supports FUSE, letting you mount S3 buckets, network filesystems, or any other FUSE-compatible driver as a regular path inside a running Sandbox.
Vercel Private Blob
Vercel Private Blob is now generally available for all plans, with private stores, Signed URLs scoped to a single operation and pathname for up to 7 days, and OIDC authentication with no static read-write token in your environment.
xAI audio models
xAI's audio models are now live on AI Gateway, with realtime voice via xai/grok-voice-think-fast-1.0, text to speech via xai/grok-tts, and speech to text via xai/grok-stt, all available through the AI SDK 7 release.
Vercel Services
Vercel Services, now in public beta, lets you run multiple frameworks in one Vercel Project with atomic deployments and internal service communication.
500 concurrent builds for Pro
Pro teams can now run up to 500 concurrent builds, up from 12, with on-demand concurrent builds enabled by default for Pro and Enterprise and billing only for build minutes used.
AI SDK 7
AI SDK 7, with over 16 million weekly downloads, adds reasoning control, tool and runtime context, provider file and skill uploads, MCP Apps, a terminal UI, tool approvals, WorkflowAgent durability, timeouts, and sandbox support.
eve Agent Runs observability
Agent Runs now appears automatically in the Vercel dashboard for every eve project, surfacing trigger, duration, and token usage per session, with retention of 12 hours on Hobby, 1 day on Pro, and 3 days on Enterprise, extendable to 30 days with Observability Plus.
Auth0 on Vercel Marketplace
Auth0 is now available on the Vercel Marketplace with automatic provisioning, Next.js SDK support, and configuration sync across Development, Preview, and Production environments.
Blob store Hobby limit
Hobby users can now create up to 100 Blob stores, up from 5, with storage, operations, and transfer limits still applying.
Vercel Functions 30 minutes
Vercel Functions on Node.js and Python runtimes now support execution durations up to 30 minutes for Pro and Enterprise teams, more than 2x the previous 800 second limit.
Vercel Sandbox 24 hours
Vercel Sandboxes can now run uninterrupted sessions for up to 24 hours, up from 5 hours, on all Pro and Enterprise plans.
Workflow SDK cancellation
Workflow SDK 5 beta supports AbortController and AbortSignal across workflow and step boundaries, with signals staying durable across suspensions and deterministic replay.
Vercel Connect
Vercel Connect, now in Public Beta, replaces stored provider tokens with runtime credential exchange, issuing short-lived, task-scoped tokens.
HarnessAgent in AI SDK 7
AI SDK 7 introduces HarnessAgent, a single API for running established agent harnesses including Claude Code, Codex, and Pi, available on the AI SDK canary release.
Workflow SDK on Nitro
Workflow SDK's native Nitro v3 integration is now in beta, with steps running inside the same bundled runtime as the rest of your app and the Nitro dev server serving the workflow web UI at /_workflow.
Vercel Drop
Vercel Drop lets you deploy a file or folder by dragging it into your browser, creating a new project and publishing to production in seconds.
Grok Imagine Video 1.5
Grok Imagine Video 1.5 from xAI is now available on AI Gateway, generating video from an input image with synchronized audio in a single pass and stronger face accuracy and character consistency.
Shopify on Vercel
You can now create a Shopify store directly from Vercel, install the Shopify integration to configure credentials, build with v0, and deploy a production-ready storefront in minutes.
Vercel Blob signed URLs
Vercel Blob now supports time-bound signed URLs scoped to a single operation, pathname, and expiry up to 7 days, with upload URLs supporting multipart for direct browser streaming.
skills.sh API
The skills.sh API is now available, letting you authenticate with your project's Vercel OIDC token and query more than 600,000 skills from the open-source ecosystem at a rate limit of 600 requests per minute.
Nemotron 3 Ultra on AI Gateway
Nemotron 3 Ultra, an open MoE reasoning model with a 1M token context window, is now available on Vercel AI Gateway with throughput up to 350 tokens per second.
Function invocation pricing
Vercel Function invocations move from package-based to per-unit pricing at $0.0000006 per invocation for Pro customers, previously $0.60 per 1M invocations.
Docker in Sandbox
Vercel Sandbox now supports installing and running Docker inside a sandbox, with the example using dnf install docker and starting dockerd.
Search Toolkit
Mistral released Search Toolkit in public preview, a composable framework for building production search pipelines with ingestion, retrieval, and evaluation in one interface.
Merge cells in tables
Notion now lets you merge cells in simple tables, with the option to select multiple cells and open the cell menu to choose Merge cells.
AI Gateway WordPress plugin
The Vercel AI Gateway plugin gives any WordPress site access to hundreds of models from 40+ providers through a single API key, requiring WordPress 7.0.
Claude Opus 4.7 fast mode
Fast mode for Claude Opus 4.7 is available on AI Gateway in research preview, delivering about 2.5x faster output token generation at 6x standard Opus rates, with input at $30 per 1M tokens and output at $150 per 1M tokens.
Node.js 26 on Sandboxes
Vercel Sandbox now supports Node.js version 26 by upgrading @vercel/sandbox to 1.10.2 or later and setting the runtime property to node26.
Claude for Small Business
Claude for Small Business ships with 15 ready-to-run agentic workflows and 15 skills, integrating with QuickBooks, PayPal, HubSpot, Canva, Docusign, Google Workspace, and Microsoft 365.
Notion Developer Platform
Notion launched a Developer Platform with Workers, External Agents API, database sync, and a CLI, letting developers and agents build on Notion infrastructure.
Chat SDK conversation history
Vercel's Chat SDK now supports cross-platform conversation history through transcripts and identity options, letting the same user keep up to 200 messages per user for 30 days across every platform adapter.
Custom Agent Directory
Notion added a Custom Agent Directory in your Library where you can browse all your workspace's agents, pin favorites, and create new ones to automate your team's busywork 24/7.
deepsec
Vercel open sourced deepsec, a security harness powered by coding agents that runs on your own infrastructure, uses Opus 4.7 at max effort and GPT 5.5 at xhigh reasoning, and scales up to 1,000+ concurrent sandboxes on Vercel's codebases.
Chat SDK Messenger
Vercel's Chat SDK adds a Messenger adapter, extending support to Slack, Discord, GitHub, Teams, and Telegram, with messages, reactions, attachments, and postback buttons.
Plan Mode
Notion introduces Plan Mode, where agents ask clarifying questions and build a detailed plan before making significant changes like rewriting pages or bulk database updates.
Hobby retention cap
Starting April 29th, the maximum retention policy for Vercel Hobby plans is capped at 30 days, with deployments outside the retention window automatically removed except the 10 most recent production deployments and any aliased deployments.
Custom Agents in Slack
Custom Agents can now read and reply in private Slack channels, with access controlled by inviting agents to specific channels.
Native Deployment Checks
Vercel now runs lint and typecheck on every deployment in parallel with the build, available to every team, with optional required checks.
Rollups formatting
Notion rollups now support number formatting (USD, EUR, percent, etc.) and decimal places, eliminating formula workarounds.
Codex Labs
OpenAI is launching Codex Labs and partnering with Accenture, Capgemini, CGI, Cognizant, Infosys, PwC, and Tata Consultancy Services to bring Codex to enterprises, with weekly Codex usage growing from more than 3 million to more than 4 million developers in two weeks.
Transformers.js Chrome extension
Hugging Face published a guide on using Transformers.js in a Chrome extension, with a demo powered by Gemma 4 E2B for local AI features.
Hyatt ChatGPT Enterprise
Hyatt has deployed ChatGPT Enterprise across its global corporate and hotel workforce, with departments including finance, marketing, and operations using it to improve guest experience.
Elastic build machines
Elastic build machines are now generally available for all Pro and Enterprise customers, and approximately 80% of projects reduced their costs by switching to smaller build machines while maintaining build speeds.
Notion 3.4 part 2
Custom Agents are now 35-50% cheaper to run, AI Autofill brings them into databases, and initial page render is 28% faster.
Opus 4.7 in Notion
Claude Opus 4.7 is now in Notion, using fewer tokens and making 3x fewer tool errors than before.
Seedance 2.0 on AI Gateway
Bytedance's Seedance 2.0 video generation model is available on AI Gateway in Standard and Fast variants with no provider markup.
Turbo build pricing
Vercel is reducing the price of Turbo build machines by 16%, with all builds now priced at $0.0035 per CPU per minute.
Mail & Calendar settings
Notion added a dedicated tab in settings to connect your calendar and inbox, letting Notion AI handle work across apps like scheduling and drafting emails.
Vercel Flags GA
Vercel Flags is now generally available, offering feature flags with targeting rules and environment controls, plus an SDK for Next.js and SvelteKit.
Notion Agent scheduling
Notion Agent now shows your calendar to help find available time with teammates, compare schedules, and book without leaving the chat.
CVE-2026-23869
A high-severity React Server Components vulnerability with CVSS 7.5 can cause denial of service, and Vercel deployed WAF rules to protect all hosted projects while requiring upgrades to patched versions 15.5.15 and 16.2.3.
Opus 4.6 Fast Mode
Claude Opus 4.6 Fast Mode is available on AI Gateway with 2.5x faster output token speeds at 6x standard Opus rates, $30 per 1M input tokens and $150 per 1M output tokens.
Sandbox 32 vCPU
Vercel Sandbox now supports up to 32 vCPUs and 64 GB of RAM for Enterprise customers running large CPU-bound or memory-heavy applications.
ZDR pricing
Team-wide Zero Data Retention costs $0.10 per 1,000 requests for Pro and Enterprise teams, while per-request ZDR is free and Disallow Prompt Training is free for all users.
Brand Studio
Stability AI launched Brand Studio, a creative production platform with Brand Central for custom Brand ID models, Producer Mode for step-by-step plans, and Precision Inpainting for targeted edits.
Notion AI chat sharing
Notion now lets users share AI chats as read-only links, managed in Settings under Public pages and Shared AI chats.
Notion AI voice input
Voice input for Notion AI is now available on desktop, allowing users to dictate prompts instead of typing.
CDN cache-control headers
New Vercel projects will honor cache-control headers by default when proxying requests to external origins starting April 6th, and existing projects can opt in from the project dashboard.
Observability Plus fee
Vercel eliminated the $10 base fee for Observability Plus for all customers and now charges only for observability events collected.
Vercel Queues 7-day TTL
Vercel Queues now supports a maximum message TTL and delivery delay of 7 days, up from 24 hours, while the default 24-hour TTL and 0-second delivery delay remain unchanged.
axios supply chain attack
The axios npm package was compromised in a supply chain attack discovered on , affecting axios@1.14.1 and axios@0.30.4, and the safe release is axios@1.14.0.
Qwen 3.6 Plus on AI Gateway
Vercel added Qwen 3.6 Plus to AI Gateway, with a 1M context window and improved agentic coding and multimodal capabilities.
AI Gateway Custom Reporting
The Custom Reporting API for AI Gateway is in beta for Pro and Enterprise plans, giving programmatic access to cost, token usage, and request volume across AI Gateway traffic including BYOK requests, with one platform saving over $80K by replacing a third-party proxy.
Notion 3.4
Notion 3.4 adds dashboard view for databases, a redesigned opt-in sidebar, presentation mode in beta for Plus, Business, and Enterprise, a tabs block, image generation, and page archiving.
Vercel plugin for Codex
The Vercel plugin now supports OpenAI Codex and Codex CLI, giving teams access to over 39 platform skills, three specialist agents, and real-time code validation.
MiniMax M2.7 on AI Gateway
MiniMax M2.7 is available on Vercel AI Gateway in standard and high-speed variants, with the high-speed variant delivering the same performance for 2x the cost at about 100 tokens per second.
Sandbox SDK 1.9.0
Vercel Sandbox SDK 1.9.0 lets you set file permissions directly in writeFiles via a mode property, removing the extra chmod round-trip.
Streamdown 2.5
Streamdown 2.5 adds inline KaTeX support, staggered streaming animations with a default 40ms stagger, and fixes for code blocks, CSV exports, and Tailwind v3 compatibility.
Custom skills for Notion AI
Custom skills let you turn repetitive AI tasks into commands, usable from text selection or @mentions in agent chat. Skills are pages, so teams can share and build on them.
Chat SDK
Chat SDK is a TypeScript library that builds bots for Slack, Teams, Google Chat, Discord, Telegram, GitHub, and Linear from one codebase, now with WhatsApp support.
Notion Academy in 6 languages
Notion Academy videos and certifications are now live in Spanish, Portuguese, Japanese, Korean, French, and German.
AI Elements 1.9
AI Elements 1.9 adds a JSXPreview component that renders streaming JSX and closes unclosed tags, a PromptInput sub-component that captures page screenshots, and a Conversation download button.
Vercel Sandbox 1 vCPU
Vercel Sandbox now supports creating Sandboxes with 1 vCPU and 2 GB of RAM for single-threaded or light workloads, with the default remaining 2 vCPUs and 4 GB.
Web Analytics resilient intake
Web Analytics and Speed Insights version 2 introduces resilient intake that dynamically discovers endpoints instead of relying on a single predictable path, available to all teams at no additional cost.
AI Meeting Notes consent
Workspace owners can now enforce a workspace-wide audio consent policy for AI Meeting Notes, playing a consent message at transcription start.
Notion Salesforce search
Notion AI can now search Salesforce accounts, leads, opportunities, and contacts alongside workspace content, via AI connectors in settings.
GPT-5.3 Chat on AI Gateway
GPT-5.3 Chat (GPT 5.3 Instant) is now available on AI Gateway, focusing on tone, relevance, and conversational flow with fewer unnecessary refusals and caveats.
GPT-5.4 in Notion
GPT-5.4 is now available in Notion's model picker, bringing faster responses and better token efficiency for demanding tasks.
GPT-5.4 on AI Gateway
GPT-5.4 and GPT-5.4 Pro are now available on AI Gateway, bringing agentic and reasoning leaps from GPT-5.3-Codex to all domains including knowledge work and coding.
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite from Google is now available on AI Gateway, outperforming 2.5 Flash Lite on overall quality with notable improvements in translation, data extraction, and code completion.
Mercury 2 on AI Gateway
Mercury 2 from Inception is now available on AI Gateway, delivering reasoning-grade quality at real-time latency for agentic loops, coding assistants, voice interfaces, and RAG pipelines.
MiniMax M2.5 in Custom Agents
Custom Agents now support MiniMax M2.5, an open weight model that is up to 10x more cost-efficient for basic tasks, available in the Custom Agent model picker.
Stripe on Vercel
Stripe is now generally available on the Vercel Marketplace and v0, letting you connect a production Stripe account and accept real payments.
Dashboard navigation redesign
Vercel's new dashboard navigation became the default for all users on , with a resizable sidebar, unified tabs, and a mobile floating bottom bar.
GPT 5.3 Codex
GPT 5.3 Codex is available on AI Gateway as a single model that is 25% faster and more token-efficient, built for long-running agentic work across debugging, deployment, and data analysis.
Vercel Queues
Vercel Queues, a durable event streaming system built with Fluid compute, entered public beta for all teams with at-least-once delivery and billing at $0.60 per 1M API operations.
Chat SDK
Vercel open sourced Chat SDK in public beta, a unified TypeScript library for building bots across Slack, Teams, Google Chat, Discord, GitHub, and Linear.
AI Gateway video generation
AI Gateway now supports video generation through AI SDK 6, with four initial video models and 17 variations covering text-to-video, image-to-video, first and last frame, and reference-to-video generation types.
Billing usage cost data API
Vercel now supports programmatic access to billing usage and cost data through the API and CLI, with the new /billing/charges endpoint returning data in the FOCUS v1.3 open-standard format.
Gradio gr.HTML one-shot apps
Gradio 6 shipped gr.HTML with custom templates, scoped CSS, and JavaScript interactivity, letting Claude or any other frontier LLM generate frontend, backend, and state management in a single Python file with no build step.
Recraft V4 on AI Gateway
Recraft V4 is now available on AI Gateway, a text-to-image model built for professional design and marketing use cases with improvements in photorealism, realistic skin, natural textures, and fewer synthetic artifacts.
Runtime Logs search redesign
The Runtime Logs search bar in the project dashboard has been redesigned with structured filters that parse level:error or status:500 into visual pills, smarter suggestions based on actual log data, and automatic conversion of pasted Vercel Request IDs into filters.
Skills.sh security audits
Skills on skills.sh now have automated security audits from partners Gen, Socket, and Snyk, allowing rapid scaling to audit over 60,000 skills and counting.
Streamdown 2.3
Streamdown 2.3 ships with a fully cleared bug backlog, applying a unified nested-card design to tables, code blocks, and Mermaid diagrams, with sticky action buttons and plain text code blocks that render immediately.
Streaming Runtime Logs exports
Runtime Logs exports now stream directly to the browser, with all plans able to export up to 10,000 requests per export and Observability Plus subscribers able to export up to 100,000 requests.
Gemini 3.1 Pro on AI Gateway
Gemini 3.1 Pro Preview is now available on AI Gateway, bringing quality improvements across software engineering and agentic workflows with more efficient thinking.
Claude Opus 4.6 in Notion
Notion added Claude Opus 4.6, the strongest model Anthropic has shipped, which breaks complicated requests into concrete steps and produces polished work.
GLM-5 on AI Gateway
GLM-5 from Z.AI is now available on AI Gateway with no other provider accounts required, adding multiple thinking modes and improved long-range planning over GLM-4.7.
MiniMax M2.5 on AI Gateway
MiniMax M2.5 is now available on AI Gateway, planning before it builds and handling full-stack projects across Web, Android, iOS, Windows, and Mac.
Vercel Flags
Vercel Flags entered public beta with targeting rules, user segments, and environment controls in the Vercel Dashboard, priced at $30 per 1 million flag requests.
stale-if-error support
Vercel CDN now supports the stale-if-error Cache-Control directive, serving previously cached responses during 500 errors, network failures, or DNS errors.
New v0
The new v0 can import any GitHub repo, connect to Snowflake and AWS databases, and let anyone on a team open PRs against main and deploy on merge.
Python 3.13 and 3.14
Builds and Functions now support Python 3.13 and Python 3.14 alongside the previously supported Python 3.12, with the default switching to Python 3.14 in the coming months.
SyGra Studio
SyGra 2.0.0 introduces Studio, an interactive environment that turns synthetic data generation into a visual canvas with guided model forms, data previews, and live execution streaming.
TRAE integration
ByteDance's coding agent TRAE now integrates both AI Gateway and direct Vercel deployments, bringing unified AI access and instant production shipping to over 1.6 million monthly active developers.
Turbo build machines default
Turbo build machines are now the default for all new Pro projects and projects upgrading from Hobby to the Pro plan, delivering 30vCPUs and 60GB of memory.
Notion Agent Asana search
Your Notion Agent can now find Asana projects and tasks in seconds, respecting existing Asana permissions.
Codex app
The Codex app for macOS manages multiple agents in parallel, includes skills and Automations, and doubles rate limits on paid plans; over a million developers used Codex in the past month.
Kimi K2.5 on AI Gateway
Kimi K2.5 is now accessible via Vercel AI Gateway with no other provider accounts required, with advanced coding abilities especially for frontend code quality and design expressiveness.
Live model performance metrics
Vercel AI Gateway now displays throughput and latency metrics across hundreds of models, updated every hour, with P50 and P95 latency and throughput available in the model list, model detail pages, and REST API.
Qwen 3 Max Thinking
Qwen 3 Max Thinking is now accessible via Vercel AI Gateway with no other provider accounts required, autonomously selecting built-in search, memory, and code interpreter tools during conversations.
Skills 1.1.1
skills@1.1.1 adds interactive skill discovery with npx skills find, a meta find-skills skill for AI agents, non-interactive mode, support for 27 coding agents, and is now fully open source.
Vercel API CLI command
vercel@50.5.1 adds a new api command giving direct access to the full suite of Vercel APIs from the terminal, with agents like Claude Code inheriting user access permissions automatically.
Vercel Agent in Slack
Vercel Agent investigations now appear directly in Slack alert messages as threaded responses, and 10 investigations are included at no additional cost for Observability Plus subscribers.
Cron jobs 100 per project
Vercel cron jobs no longer have per-team limits, and per-project limits were lifted to 100 on all plans, up from a cap of 20 per project.
Recraft on AI Gateway
Recraft image models V3 and V2 are now available via Vercel's AI Gateway with no other provider accounts required, supporting generateImage in the AI SDK.
Team-level build settings
Vercel build and deployment settings can now be configured at the team level and applied across all projects, with Standard, Enhanced, and Turbo build machines offering 4, 8, and 30 vCPUs respectively.
Vercel Montréal region
Vercel opened a Montréal, Canada region, yul1, that is generally available and handling production traffic, with support for Canadian data residency and Fluid compute.
Custom error pages
Vercel now lets Enterprise teams customize platform error pages with request ID and error code tokens, enabled automatically across all projects.
AWS databases on Vercel
Developers can provision Aurora PostgreSQL, Amazon DynamoDB, and Aurora DSQL directly from the Vercel dashboard, and new AWS teams get a free starter plan with $100 in credits.
OpenResponses API on AI Gateway
Vercel AI Gateway is a day 0 launch partner for the OpenResponses API, supporting text generation, streaming, tool calling, image input, reasoning, and provider fallbacks.
Perplexity web search
Provider-agnostic web search on AI Gateway lets any model search the web in real-time with a single line of code, charged at $5 per 1,000 requests.
Secure Compute self-serve
Vercel's Secure Compute networks are now self-serve via dashboard, API, and Terraform, with Site-to-Site VPN coming soon.
Pixel Portraits template
Vercel released a v0 template that turns a selfie into a 16-bit pixel trading card using GPT Image 1.5 Edit, BRIA RMBG 2.0 background removal, Canvas API compositing, and a custom LoRA trained on pixel art, with the on-site pipeline completing in roughly six seconds.
v0 internal tools
Vercel's v0 AI agent lets business users build and publish internal tools with auditable code, enforced access control, and secure-by-default infrastructure.
Bulk redirects GA
Vercel's bulk redirects are now generally available via UI, API, or CLI without a new deployment, allowing up to one million static URL redirects per project, with Pro plans including 1,000 redirects and Enterprise including 10,000.
Cline on AI Gateway
Cline now runs on the Vercel AI Gateway, and over a week of live A/B testing, P99 streaming latency improved by 10-14% across Cline's most-used models while API error rates dropped by 43.8%.
Dynamic URL prefixes
Vercel now supports dynamic URL prefixes for multi-tenant platforms, allowing a single project to be backed by tens of thousands of domains with prefixes like tenant-123---project-name-git-branch.yourdomain.dev.
Vercel Agent for Marketplace
Vercel Agent in the Dashboard can now interact with installed Marketplace integrations from Neon, Supabase, Dash0, Stripe, Prisma, and Mux, with tools exposed by providers available automatically and authentication handled by Vercel.
Gemini 3 Flash on AI Gateway
Gemini 3 Flash is now available on Vercel's AI Gateway, beating Gemini 2.5 Pro across most benchmarks while using 30% less tokens and being 3x faster.
GPT-5.2 on AI Gateway
Vercel AI Gateway now serves GPT-5.2 Chat, GPT-5.2, and GPT-5.2 Pro with no other provider accounts required.
Node.js 24 on Sandbox
Vercel Sandbox now supports Node.js version 24 via @vercel/sandbox 1.1.0 or above with the runtime property set to node24.
React2Shell auto-fix
Vercel Agent now detects vulnerable React, Next.js, and related RSC packages and automatically generates pull requests with verified fixes for React2Shell CVE-2025-55182 at no cost.
Rust runtime beta
Vercel launches first-class Rust runtime support in public beta with Fluid compute, HTTP response streaming, Active CPU pricing, and an environment variable limit raised from 6KB to 64KB.
Web Analytics dimensions
Vercel Web Analytics now supports splitting data across 11 dimensions including paths, routes, host names, countries, devices, OS, referrers, flags, flag values, event names, and event properties.
React2Shell protections
Vercel releases npx fix-react2shell-next to update affected Next.js apps, with Vercel Agent able to open pull requests that upgrade vulnerable projects and WAF rules filtering known exploit patterns.
Notion Agent forms
Notion Agent can now build forms in seconds, collecting requests, feedback, and surveys without manual form building.
Image-only models on AI Gateway
Vercel AI Gateway now offers image-only models including Black Forest Labs FLUX.2 Flex, FLUX.2 Pro, FLUX.1 Kontext Max, FLUX.1 Kontext Pro, FLUX 1.1 Pro Ultra, FLUX 1.1 Pro, FLUX.1 Fill Pro, and Google Imagen 4.0 Generate, Fast Generate, and Ultra Generate.
Streamdown 1.6
Vercel Streamdown 1.6 is now available with memoization, LRU caching, optimized string operations, removal of regexes, lazy-loaded Code Blocks, Mermaid, and Math components, a rebuilt code highlighting system, a custom markdown renderer, and Static Mode.
vercel open CLI command
You can now open your current project in the Vercel Dashboard directly from the command line using vercel open, available in vercel 48.10.0 or newer.
Gemini 3 Pro
Gemini 3 Pro is now accessible via Vercel's AI Gateway with no other provider accounts required, using the model ID google/gemini-3.0-pro-preview.
Gemini 3 Pro in Notion
Gemini 3 Pro is now available in Notion, giving the Notion Agent access to Google's latest model alongside those from OpenAI and Anthropic.
Grok 4.1 Fast
Grok 4.1 Fast Reasoning and Grok 4.1 Fast Non-Reasoning are now accessible via Vercel's AI Gateway with no other provider accounts required, and both have a 2M context window.
Vercel Agent investigations
Vercel Agent investigations are now included in Observability Plus, adding 10 investigations to every billing cycle at no extra cost to the subscription.
Vercel Firewall UI
Vercel launched improvements to the Firewall UI, including an updated Overview page for DDoS attacks and a new Traffic page to drill into top sources of traffic by IPs, request paths, JA4 digests, ASN, and user agents.
Nano Banana Pro on AI Gateway
Nano Banana Pro (Gemini 3 Pro Image) is now available on Vercel's AI Gateway with no other provider accounts required, supporting higher resolution and multi-image input limits.
GPT-5.1 Codex on AI Gateway
Vercel AI Gateway now serves GPT-5.1 Codex and GPT-5.1 Codex mini with no other provider accounts required.
GPT-5.1 on AI Gateway
Vercel AI Gateway now serves GPT-5.1 Instant and GPT-5.1 Thinking with no other provider accounts required.
Notion Agent reads CSVs
Notion Agent can now read CSVs up to 1,000 rows to create analyses or visualize data as charts or boards.
BotID Deep Analysis
BotID Deep Analysis, Vercel's advanced bot protection system, is free for all Pro and Enterprise customers from to , and uses thousands of telemetry points for real-time client-side checks.
Edge Config pricing
Vercel Edge Config Reads and Writes are moving from package-based to per-unit pricing on the Pro plan, with reads at $0.000003 per read and writes at $0.01 per write.
Skew Protection lifetime
Vercel Skew Protection max age can now persist for the entire lifetime of your deployments, removing the previous limits of 12 hours on Pro and 7 days on Enterprise.
Vercel Sandbox CLI
Vercel introduced the Sandbox CLI, a command-line interface for managing isolated compute environments built on the Docker CLI model, supporting Node.js node22 and Python python3.13 workloads.
v0 Snowflake integration
Vercel announced a Snowflake integration for v0 that lets you connect v0 to Snowflake, ask questions about your data, and build data-driven Next.js applications that deploy directly to Snowflake, with data never leaving your Snowflake environment.
BotID Deep Analysis
Vercel BotID Deep Analysis detected a 500% traffic spike from 40-45 new browser profiles cycling through proxy nodes and blocked the bot network in 5 minutes with no manual intervention.
Bun runtime
Vercel Functions now support Bun in Public Beta, with internal testing showing Bun reduced average latency by 28% in CPU-bound Next.js rendering workloads compared to Node.js.
Microfrontends
Vercel microfrontends are generally available, serving nearly 1 billion routing requests per day with over 250 teams deploying, priced at $250 per additional project per month and $2 per million routing requests.
Claude for Financial Services
Anthropic expanded Claude for Financial Services with an Excel add-in, new connectors, and 6 Agent Skills, topping the Finance Agent benchmark at 55.3% accuracy.
Microfrontends preview links
Preview links between microfrontends projects now serve all routes in the group, eliminating 404s and automatically linking deployments built from the same commit or branch.
Sandbox extendTimeout
Vercel Sandbox now has an extendTimeout method to extend a running sandbox beyond its initial timeout, with Pro and Enterprise plans supporting up to 5 hours and Hobby up to 45 minutes.
Server Actions firewall
Vercel Firewall and Observability Plus now support custom rules targeting specific Server Action names, such as rate limiting app/auth/actions.ts#getUser to 100 requests per minute per IP address, starting with Next.js 15.5.
Turbo build machines
Turbo build machines are available for all paid plans with 30 vCPUs and 60GB of memory, aimed at Turbopack builds and large monorepos that run tasks in parallel.
Trace Drains on Marketplace
Vercel Drains now send traces and logs from projects to Marketplace observability providers including Braintrust, Dash0, Statsig, and Kubiks, with more providers coming soon.
Claude Haiku 4.5 on AI Gateway
Vercel's AI Gateway now offers Claude Haiku 4.5 with no other provider accounts required, matching Sonnet 4's performance at lower cost and faster speeds.
ChatGPT apps on Vercel
Vercel now supports building and deploying ChatGPT apps with Next.js, using MCP natively in the OpenAI sandbox.
uv Python builds
Vercel now uses uv as the default package manager for all Python builds, making builds 30-65% faster and adding support for uv.lock and pyproject.toml dependency files.
Parental controls
OpenAI launched parental controls for ChatGPT, letting parents link accounts, set quiet hours, disable voice, memory, image generation, and opt out of training.
CDN request collapsing
The Vercel CDN now collapses over 3M requests per day on cache miss, on top of 90M collapsed requests from background revalidations, using node and regional distributed locks with three second timeouts.
External API queries
Observability Plus query builder now supports custom queries on request counts or time to first byte for external API calls such as fetch requests to an AI provider, with TTFB breakdowns by average, min, max, p75, p90, p95, and p99.
Zero-config FastAPI
FastAPI is now supported with zero-configuration on Vercel, using Fluid compute with Active CPU pricing by default.
Vercel Bloom filter routing
Vercel replaced a slow JSON parsing operation with a Bloom filter in its global routing service, reducing memory usage by 15% and improving time-to-first-byte from the 75th percentile and above by 10%.
Vercel Drains
Vercel Log Drains are now Vercel Drains, exporting OpenTelemetry traces, Web Analytics events, and Speed Insights metrics alongside logs, with data billed at $0.50 per GB on Pro and Enterprise plans.
Vercel Fluid cold starts
Vercel delivers zero cold starts for 99.37% of all requests through scale to one, Fluid compute, predictive scaling, bytecode caching, and rolling releases, with single instances handling peaks above 250 concurrent requests.
Vercel build cache
Vercel improved its build cache performance by downloading parts of the cache in parallel using a worker pool, decreasing build initialization time by 30% on average and reducing build times by up to 7 seconds for all plans.
AI code reviews beta
Vercel Agent can now conduct code reviews with validated suggestions, available in public beta for all Pro and Enterprise teams with a $100 Vercel Agent credit.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.