xlang-ai
★ 3,143OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
AI 频道AI 智能体 
★ 3,080
★ 2,659
开源 AI 智能体
AI 智能体是一种用大模型决定下一步做什么的程序：它会调用浏览器、代码解释器或 API 等工具，反复执行，直到任务完成。这里的项目既有用来搭建自己智能体的框架，也有能写代码、浏览网页或运行业务流程的现成智能体。
怎么选
比较时看三点：能用哪些模型——只支持一家服务商，还是任何兼容 OpenAI 接口的端点（包括本地模型）；怎么限制智能体能做的事——沙箱、审批步骤、权限清单；以及它能否在步骤之间、会话之间保留记忆。会执行代码或命令行的智能体应该在沙箱里运行，给它访问你电脑的权限之前先确认这一点。
Star 最多的项目
第 217–240 个，共 426 个cosmicstack-labs
★ 3,133mercury-agent
Soul-driven AI agent with permission-hardened tools, token budgets, and multi-channel access. Runs 24/7 from CLI or Telegram.
zjunlp
★ 3,116LLMAgentPapers
Must-read Papers on LLM Agents.
TanStack
★ 3,113ai
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
wquguru
★ 3,107harness-books
📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev
decodingai-magazine
★ 3,087second-brain-ai-assistant-course
Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.
Templates and workflow for generating PRDs, Tech Designs, and MVP and more using LLMs for AI IDEs
GH05TCREW
★ 3,077pentestagent
PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.
amitshekhariitbhu
★ 3,073ai-engineering-interview-questions
Your Cheat Sheet for AI Engineering Interview – Questions and Answers.
SharpAI
★ 3,062DeepCamera
Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent — watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.
eracle
★ 2,999OpenOutreach
Open-source AI agent for B2B lead generation — describe your product, it finds the people who fit, explains why each one does, and emails them from your mailbox. Self-hosted CLI, one install.
vercel-labs
★ 2,983opensrc
Fetch source code for npm packages to give AI coding agents deeper context
PenglongHuang
★ 2,939chinese-novelist-skill
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
ax-llm
★ 2,924ax
The pretty much "official" DSPy framework for Typescript
OpenMind
★ 2,911OM1
Modular AI HAL (Hardware Abstraction Layer) for Robots
LLMQuant
★ 2,875quant-mind
QuantMind is an agent-native knowledge extraction and retrieval framework for quantitative finance.
sopaco
★ 2,829deepwiki-rs
Turn code into clarity. Generate accurate technical docs and AI-ready context in minutes—perfectly structured for human teams and intelligent agents.
oritera
★ 2,800Cairn
A AI general-purpose state-space search engine, validated first on autonomous penetration testing.
automata
★ 2,716aicodeguide
AI Code Guide is a roadmap to start coding with AI
wanikua
★ 2,701danghuangshang
Open-source multi-agent collaboration system inspired by Chinese governance — deploy and coordinate specialized AI agents with OpenClaw.
jgravelle
★ 2,687jcodemunch-mcp
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Windy3f3f3f3f
★ 2,680claude-code-from-scratch
Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~5000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
brightdata
★ 2,646brightdata-mcp
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.