What changed in the agent stack

2026-10-07 · github.com/vercel/ai

Patch Changes - 6f6b9c0: fix(ai): reject pending result promises and cancel the pending stream when the abort signal fires - d3bcad9: feat(provider): report decision refusals as refusal answers - Updated dependencies [d3bcad9] - @ai-sdk/provider@4.0.24 - @ai-sdk/gateway@4.0.106…

2026-10-06 · github.com/anthropics/claude-agent-sdk-python

Internal/Other Changes - Updated bundled Claude CLI to version 2.1.292 - CI: security hardening for GitHub Actions workflows that call Claude — egress-firewall runner, network allow list, auto permission mode, and a check workflow to enforce them ( 1329) - CI: raised PyPI per-fi…

2026-10-06 · github.com/anthropics/claude-code

What's changed - Added --marketplace to claude plugin install : adds the marketplace if needed, under the same policy checks as claude plugin marketplace add , then installs the plugin from it - Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effor…

2026-10-06 · github.com/google-gemini/gemini-cli

What's Changed fix(cli): display retry progress indicator during connection recovery ( 28340) by @amelidev in https://github.com/google-gemini/gemini-cli/pull/29468 Changelog for v0.61.0-preview.1 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29469 Cha…

2026-10-06 · github.com/github/github-mcp-server

Highlights :sparkles: More and more agents are supporting Code Mode or Programmatic Tool Calling so we have added support for structured outputs and output schemas to help do this effectively. These schemas are only advertised to clients advertising MCP 2026-07-28 spec support (…

2026-10-06 · github.com/langchain-ai/langgraph

Changes since 1.2.13 release(langgraph): 1.2.14 ( 9215)

2026-10-06 · github.com/mistralai/mistral-vibe

Added - The app-server can discover built-in plugins from roots an embedding application ships, alongside the ones inside the package. - Vibe Code warns when the selected model cannot view attached images. - Vibe Code sessions list their background processes in a side panel with…

2026-10-06 · github.com/sst/opencode

Core Improvements - Added canonical redirects and JSON and Markdown data formats for agent-readable stats. Bugfixes - xAI tool results now include supported images, while unsupported image formats are skipped. (@Jaaneek) Thank you to 3 community contributors: - @dc85: - docs(web…

2026-10-06 · github.com/OpenHands/OpenHands

1.25.0 (2026-10-06) What's Changed Features feat: outline the back navigation control on settings sub-pages by @errmakov in https://github.com/OpenHands/OpenHands/pull/17587 feat(settings): bulk-add provider models as LLM profiles by @georgeglarson in https://github.com/OpenHand…

2026-10-06 · github.com/strands-agents/harness-sdk

python/v1.58.1 Auto-drafted from commits in python/v1.58.0..python/v1.58.1 , grouped by conventional-commit type. Edit on the release page after publish if you want a polished writeup; the canonical release notes live on the website. 🚀 Features - feat(mcp/ts): restore legacy ta…

2026-10-05 · github.com/openai/codex

Bug Fixes - Preserve SYSTEMROOT , TEMP , and TMP when launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment. Changelog - 51121: Backport Windows remote MCP environment…

2026-10-05 · github.com/mastra-ai/mastra

Highlights Tool Context Can Read the Full Conversation ( agent.getMessages() ) Tools now have access to the current conversation state via context.agent.getMessages() in both standard and durable agent loops, including remembered messages and in-run responses—enabling richer, co…

2026-10-05 · github.com/modelcontextprotocol/typescript-sdk

Package Version --- --- @modelcontextprotocol/client 2.3.1 @modelcontextprotocol/server 2.3.1 @modelcontextprotocol/core 2.3.1 @modelcontextprotocol/server-legacy 2.3.1 @modelcontextprotocol/codemod 2.3.1 @modelcontextprotocol/node , express , hono , fastify unchanged Changes -…

2026-10-05 · github.com/earendil-works/pi

New Features - Tool patterns and --no-mcp : --tools and --exclude-tools accept patterns, for example --tools read,codemode,'mcp radius ' keeps only one MCP server's tools. --tools now keeps MCP tools unless an entry starts with mcp , and --no-mcp turns off MCP for one run. See T…

2026-10-05 · github.com/QwenLM/qwen-code

Bundled CLI Version This SDK release bundles CLI version: 0.25.0 Source: CLI built from source (same branch/ref as SDK) --- Bundled CLI Version This SDK release bundles CLI version: 0.24.7 Source: CLI built from source (same branch/ref as SDK) --- Bundled CLI Version This SDK re…

2026-10-04 · github.com/letta-ai/letta-code

What's Changed fix(sandbox): let memory subagents write their scratchpad by @cpacker in https://github.com/letta-ai/letta-code/pull/4952 revert: remove automatic reply relay from core channels ( 4043) by @cpacker in https://github.com/letta-ai/letta-code/pull/4956 docs(channels)…

2026-10-03 · github.com/ag2ai/ag2

What's Changed fix(mcp): derive model output schemas from serialization by @asts-top in https://github.com/ag2ai/ag2/pull/3317 fix(tenki): upgrade sdk and preserve timeout failures by @camcalaquian in https://github.com/ag2ai/ag2/pull/3329 chore(deps): bump gitpython from 3.1.59…

2026-10-03 · github.com/openclaw/openclaw

OpenClaw v2026.9.8 58 commits · 43 pull requests · 21 contributors Changes included in this release The release notes and changelog contain the same content, presented in two formats: - Release notes — formatted for people, with expandable sections. - Changelog — plain Markdown…

2026-10-03 · github.com/pydantic/pydantic-ai

What's Changed ⚠️ Compatibility Notes Handle draft-7 list-form items in JsonSchemaTransformer , TestModel and Mistral streamed output, and make TestModel accept boolean subschemas and cap prefixItems at maxItems by @dsfaccini in https://github.com/pydantic/pydantic-ai/pull/9560…

2026-10-02 · github.com/google/adk-python

2.11.0 (2026-10-01) Highlights This release adds graceful cancellation and tool confirmation to workflows, a tool for consulting another model mid-task, and a built-in SQLite memory service. Execution cancellation : Pass an abort signal to Runner , Workflow , and nodes to stop a…

2026-10-07 · Simon Willison

<p><strong><a href="https://wikimediafoundation.org/news/2026/10/05/openai-rogue-agent-activities-found-on-wikimedia-projects/">OpenAI “rogue” agent activities found on Wikimedia projects</a></strong></p> Given how tempting a target wikis are for rogue agent…

2026-10-06 · OpenAI News

Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.

2026-10-06 · GitHub Blog

We're rebuilding GitHub's Git infrastructure while GitHub keeps running, creating a foundation for agent-scale software development. The post Building Git infrastructure for agent-scale development appeared first on The GitHub Blog .

2026-10-06 · Cursor changelog

See and reply to the local agents running on your computer from the Cursor iOS app.

2026-10-06 · GitHub Changelog

If your Copilot usage metrics have shown agent activity or agent lines of code falling while Copilot usage kept growing, we& 8217;ve found the cause, and a fix is rolling out& 8230; The post Update your IDE to restore agent activity in Copilot usage metrics a…

2026-10-05 · AWS Machine Learning blog

Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrieval answers poorly. Run the same query through both paths,…

2026-10-05 · AWS Machine Learning blog

Multi-agent systems need deeper guarantees than fluent responses: they must select the right tools, respect constraints, and explain their decisions. Learn how to build a Strands-based multi-agent supply chain decisioning system and evaluate it with Amazon Be…

2026-10-05 · Cloudflare blog

We celebrated our 16th birthday with 46 announcements across open source, post-quantum security, AI agents, and developer platform upgrades. Here’s a day-by-day roundup of everything we shipped.

2026-10-05 · AWS Machine Learning blog

Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference optimization and benchmarking. Describe what you want, and…

2026-10-05 · AWS Machine Learning blog

Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in the AWS GovCloud (US) Regions. Learn how to use them with Claude Code, Anthropic's agentic coding tool, for compliance-aligned, AI-assisted development on regulated and ITAR wo…

2026-10-03 · Hugging Face blog

2026-10-02 · OpenAI News

Learn how startups can choose GPT-6 models, tune reasoning effort, improve prompts and skills, coordinate tools, and prepare workflows for production.

2026-10-02 · AWS Machine Learning blog

Claude Desktop on Amazon Bedrock is limited to the model's knowledge cutoff without web search. In this post, we walk through connecting Claude Desktop to Web Search using Amazon Bedrock AgentCore Gateway, with JWT-based inbound authentication through AWS IAM…

2026-10-02 · GitHub Blog

Learn to direct AI agents, critically review their output, and keep technical judgment at the center of your workflow. The post AI is changing developer work. Here are three skills to strengthen. appeared first on The GitHub Blog .

2026-10-02 · Hugging Face blog

2026-10-02 · OpenAI News

Chatham Financial uses Codex and GPT-5.6 to build technology and redesign workflows, cutting trade validation from 30 minutes to under 4.

2026-10-02 · GitHub Changelog

You can now request a GitHub Copilot code review through the REST and GraphQL APIs and set the review effort level for each request. Balanced is also now the default& 8230; The post Copilot code review: API support and new default effort level appeared first…

2026-10-02 · AWS Machine Learning blog

Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent with multi-turn reinforcement learning (MTRL) on Amazon SageMa…

2026-10-02 · Vercel

Rogo on Vercel 73,000+ deployments in a single month Agent-written code shipped to production in 5 minutes 6 production AI agents automating work from churn analysis to deal desk Zero manual triage during production incidents with agent swarms on AI SDK Rogo…

2026-10-02 · GitHub Changelog

As of today, October 2, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Model& 8230; The post Selected models in GitHub Copilot deprecated a…

2026-09-28 · GitHub · ★ 6,232 · TypeScript

一个自己找热点、自己写日报的网站框架。把信源和精选标准换成你的，它就是你的行业热点站。

2026-09-23 · GitHub · ★ 5,546 · Go

Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.

2026-09-30 · GitHub · ★ 4,709 · Python

Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.

2026-09-27 · GitHub · ★ 3,856 · Swift

A tiny friend in your Mac's notch and on your iPhone that keeps an eye on your AI coding agents: Claude Code, Codex, Cursor, Gemini CLI, Antigravity and more. Approve from the notch or your Lock Screen.

2026-09-29 · GitHub · ★ 2,635 · Python

Open-source dots for the web: an AI agent with its own browser, one that does not get blocked.

2026-09-24 · GitHub · ★ 2,492 · JavaScript

在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 DeepSeek V4.1 Flash、Kimi K3 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, DeepSeek V4.1 Flas…

2026-09-26 · GitHub · ★ 2,353 · TypeScript

Find code by asking what it does. A CLI for coding agents that uses Jev to discover relevant files and source context.

2026-09-08 · GitHub · ★ 2,282 · TypeScript

Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English;…

2026-09-26 · GitHub · ★ 2,183 · HTML

A comprehensive logo-design skill for Claude, Gemini CLI, Codex and other AI agents: principles, process, SVG craft, testing tools and a 1,400+ logo reference library.

2026-10-02 · GitHub · ★ 1,833 · JavaScript

Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。

2026-09-30 · GitHub · ★ 1,648 · Python

AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese

2026-09-28 · GitHub · ★ 1,626 · JavaScript

Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.

2026-09-29 · GitHub · ★ 1,486 · TypeScript

WebGPU components for React, Vue, Svelte, Solid, JS & Framer

2026-09-12 · GitHub · ★ 1,304 · JavaScript

ClearAI is a native DSH plugin that brings the Epistemic Loop to DeepSeek Harness.

2026-09-26 · GitHub · ★ 1,298 · JavaScript

Claude Code skill for short films with no video model: 43 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 (incl. OPUSCAR 98). By Lemomo. Opus5.5 x 43 种影片风格：风格提示词 + 纯代码样片 + 导演与技…

2026-09-23 · GitHub · ★ 1,232 · TypeScript

Take your agent-built product live: hosting, database, domain, email, payments — on your own accounts. Open-source Agent Skill + zero-dependency Node CLI: detect → plan → approve → apply → verify. No GoLive account, bac…

2026-09-16 · GitHub · ★ 1,174 · Python

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

2026-09-08 · GitHub · ★ 1,128 · JavaScript

Enable any LLM to control your computer with cross-platform support, featuring 3D modeling examples and live demos.

2026-09-12 · GitHub · ★ 1,060 · TypeScript

Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.

2026-09-15 · GitHub · ★ 1,024 · Python

An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.

2026-09-29 · Hacker News · 769 points · 647 comments

2026-09-25 · Hacker News · 755 points · 472 comments

2026-09-30 · Hacker News · 686 points · 362 comments

2026-09-23 · Hacker News · 486 points · 284 comments

2026-10-05 · Hacker News · 482 points · 325 comments

2026-09-29 · Hacker News · 426 points · 140 comments

2026-09-27 · Hacker News · 396 points · 269 comments

2026-09-24 · Hacker News · 396 points · 457 comments

2026-10-03 · Hacker News · 379 points · 301 comments

2026-09-23 · Hacker News · 310 points · 218 comments

2026-10-05 · Hacker News · 299 points · 194 comments

2026-09-24 · Hacker News · 267 points · 313 comments

2026-09-24 · Hacker News · 256 points · 198 comments

2026-10-03 · Hacker News · 245 points · 161 comments

2026-09-28 · Hacker News · 230 points · 299 comments

2026-09-26 · Hacker News · 198 points · 188 comments

2026-09-30 · Hacker News · 194 points · 99 comments

2026-10-01 · Hacker News · 188 points · 106 comments

2026-09-26 · Hacker News · 178 points · 47 comments

2026-09-29 · Hacker News · 164 points · 43 comments