Open source
Libraries, tools and repos: releases you depend on and projects gaining stars.
pydantic/pydantic-ai v2.55.0: v2.55.0 (2026-10-09)
<!-- Release notes generated using configuration in .github/release.yml at main -->
langchain-ai/langchain langchain-openai==1.7.0
chore(deps): bump langgraph-sdk from 0.4.4 to 0.4.6 in /libs/partners/openai (#41096)
VideoParameter Golf with AutoResearch — Vayum Arora, Zhengyao Jiang, Dixing Xu & Dhruv Srikanth, Weco AI
Zhengyao Jiang introduces autoresearch as repeated proposals and evaluations, and Dixing Xu explains the team's Aiden system and its contributions to OpenAI's Parameter Golf challenge.
anthropics/claude-code v2.1.294
Fixed prompt and agent hooks written as instructions (such as "Block commands that...") allowing what they should block
Python 3.15.0 added to actions/python-versions
Now that this has landed, you can add "3.15" to a GitHub Actions testing matrix to run tests against the new Python 3.15.0 release.
browser-use/browser-use 0.13.11
This release includes Browser Use toolsets for Claude, available at browseruse.integrations.toolsetsforclaude.
[AINews] Pi 1.0, Pi Durable, and AIE NYC
Last call for regular tickets for AI Engineer NYC!
GTKottman/mortiflix-oss: A motion design studio on your own machine: Claude makes the video step by step, you approve every stage. Bring your own Claude Code or API
A motion design studio on your own machine: Claude makes the video step by step, you approve every stage.
AI Native by Design: Lessons Learned from Building NVIDIA TensorRT Model Connect
Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT...Parallel work, model-family isolation, reversible changes, and GPU-backed validation shaped an open source project designed around coding agents NVIDIA TensorRT Model Connect is an open source collection of AI model reference implementations in C++, built on top of NVIDIA TensorRT.
crewAIInc/crewAI 1.15.24
Add crewai eval to print a markdown brief when run by an agent
Together Link: open models in the harness you already use. Start with one command today.
Together Link brings frontier open models like GLM 5.3 and Kimi K3 into the coding agent your team already uses, cutting model spend by over 50%.
Farol
The macOS terminal that shows which coding agent needs you
langchain-ai/langchain langchain-core==1.6.9
feat(core): accept a callable in withretry (#41158)
pydantic/pydantic-ai v2.54.0: v2.54.0 (2026-10-02)
<!-- Release notes generated using configuration in .github/release.yml at main -->
ttok 0.4
ttok is my CLI tool for counting tokens, using OpenAI's open source tiktoken library.
Can a Cloud-Native Harness Make Agents Reliable Beyond the Desktop?
Since that’s easiest to implement locally, many coding agents started out as terminal tools and then desktop apps (Claude Code famously began as a CLI tool).
pydantic/pydantic-ai clai2-bleeding: CLAI2 bleeding
Sdists rebuilt from main for /update on the CLAI bleeding channel.
pydantic/pydantic-ai v2.52.0: v2.52.0 (2026-09-29)
This release fixes one security issue in webfetch.
langchain-ai/langchain langchain-openai==1.6.7
chore(model-profiles): refresh model profile data (#40924)
pydantic/pydantic-ai v2.53.0: v2.53.0 (2026-10-01)
This release fixes one security issue in ConcurrencyLimitedModel.
langchain-ai/langchain langchain-anthropic==1.7.5
fix(anthropic): support Claude Sonnet 5.5 compatibility (#40882)
openqodex/openqodex: Open source AI code review for Claude Code and Codex, before you push. Scanners (SAST, secrets, dependencies, lint) on the lines you changed
Open source AI code review for Claude Code and Codex, before you push.
strands-agents/box: Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with defau
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network.
langchain-ai/langchain langchain-fireworks==1.7.0
hotfix(fireworks): replace unavailable integration test model (#40890)
QingYunA/answer-me-with-html: 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。
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。 Language: JavaScript.
justxor/claude-code-pro-course: Claude Code PRO — полный курс и гайд на русском: CLAUDE.md, settings, skills, subagents, hooks, MCP, плагины, CI. 8 лабораторных, библиотека
Claude Code PRO — полный курс и гайд на русском: CLAUDE.md, settings, skills, subagents, hooks, MCP, плагины, CI.
Chengjun023/agent-smith: Token 超支?快给史密斯打电话! Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.
Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.
langchain-ai/langchain langchain-core==1.6.6
fix(anthropic): support Claude Sonnet 5.5 compatibility (#40882)
Router0824/OpsPilot-AI: Open-source AI operations workspace for meetings, knowledge, decisions, tasks, risks, workflows, and organizational memory.
Open-source AI operations workspace for meetings, knowledge, decisions, tasks, risks, workflows, and organizational memory.
edenfunf/reelmimic: 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.
Topics: 2d-animation, ai-agents, ai-video, animation, claude-code, codex, multi-agent, style-transfer, video-generation.
langchain-ai/langchain langchain==1.4.3
feat(langchain): support Bedrock Mantle chat models in initchatmodel (#40837)
mariagorskikh/open-instinct: Open Instinct: an open-source Instinct. A personal agent you text on iMessage, with its own computer and a trusted network of other agents.
A personal agent you text on iMessage, with its own computer and a trusted network of other agents.
kkjiangk/agent-py: Personal AIOps engineering project with durable workflows, scoped hybrid retrieval, reliable event delivery, and verified API/browser contra
Personal AIOps engineering project with durable workflows, scoped hybrid retrieval, reliable event delivery, and verified API/browser contracts.
jiwoochris/artex-ko: ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0)
ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0) Language: Go.
Louis-CFM/coucou: 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, Ant
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.
FengZhenfei/carrel: Ontology-Augmented Generation for AI agents.
Topics: agent-skills, ai-agents, chinese, claude-code-skill, codex-skill, document-parsing, knowledge-graph, knowledge-graphs, mineru, neo4j, ontology, opensearch, qdrant, rag, retrieval-augmented-generation.
Dreamer-Toby/STEPQuant: STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization Language: Python.
nanaism/yomiyasu: 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
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 Language: Python.
whirlchat/whirl: The AI chat app that sweats the details. Every top model, real memory, living documents, and your own tools.
The AI chat app that sweats the details.