aiagent.club
English

AI Agent 指数

当前有 51 个项目满足跨来源主榜门槛;全站共追踪 980 个软件项目。

方法论 v2.0 · 指数快照 2026-09-12 · 新鲜度窗口 2 天

AI Agent 指数

主榜项目至少要有两个当前有效的评分维度,且覆盖两种数据源。综合分 = 可观测采用度(45%)+动量(30%)+关注度(25%);过期或缺失信号不计分。

  1. 1
    langchain GHPyPI

    The agent engineering platform.

    204.9M 可观测/月 146.2k ▲ 461 ★/周 3/3 当前信号

    95
  2. 2
    litellm GHPyPI

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

    341.6M 可观测/月 58.5k ▲ 450 ★/周 3/3 当前信号

    93
  3. 3
    browser-use GHPyPI

    Agents that use the browser.

    31.1M 可观测/月 114.3k ▲ 1.9k ★/周 3/3 当前信号

    92
  4. 4
    firecrawl GHPyPI

    The context API to search, scrape, and interact with the web at scale. 🔥

    6.2M 可观测/月 179.3k ▲ 2.5k ★/周 3/3 当前信号

    89
  5. 5
    langgraph GHPyPI

    Build resilient agents.

    54.5M 可观测/月 41.5k ▲ 403 ★/周 3/3 当前信号

    84
  6. 6
    crewAI GHPyPI

    Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

    20.0M 可观测/月 58.4k ▲ 276 ★/周 3/3 当前信号

    83
  7. 7
    crawl4ai GHPyPI

    🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

    1.4M 可观测/月 82.2k ▲ 689 ★/周 3/3 当前信号

    79
  8. 8
    ai GHnpm

    The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents

    79.2M 可观测/月 26.7k ▲ 110 ★/周 3/3 当前信号

    73
  9. 9
    llama_index GHPyPI

    LlamaIndex is the document processing platform for AI

    9.8M 可观测/月 52.1k ▲ 101 ★/周 3/3 当前信号

    73
  10. 10
    dspy GHPyPI

    DSPy: The framework for programming—not prompting—language models

    5.6M 可观测/月 38.0k ▲ 180 ★/周 3/3 当前信号

    72
  11. 11
    fastmcp GHPyPI

    🚀 The fast, Pythonic way to build MCP servers and clients.

    65.4M 可观测/月 27.6k ▲ 91 ★/周 3/3 当前信号

    71
  12. 12

    The official Python SDK for Model Context Protocol servers and clients

    272.2M 可观测/月 24.3k ▲ 63 ★/周 3/3 当前信号

    71
  13. 13
    mastra GHnpm

    Mastra is the modern TypeScript framework for AI-powered applications and agents.

    5.3M 可观测/月 28.0k ▲ 233 ★/周 3/3 当前信号

    70
  14. 14
    CloakBrowser GHnpmPyPI

    Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.

    1.3M 可观测/月 31.4k ▲ 188 ★/周 3/3 当前信号

    68
  15. 15
    pydantic-ai GHPyPI

    How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

    8.4M 可观测/月 19.9k ▲ 140 ★/周 3/3 当前信号

    64
  16. 16
    agno GHPyPI

    Build, run, and manage agent platforms.

    2.0M 可观测/月 42.1k ▲ 80 ★/周 3/3 当前信号

    63
  17. 17
    chroma GHPyPI

    Search infrastructure for AI

    9.1M 可观测/月 29.3k ▲ 53 ★/周 3/3 当前信号

    63
  18. 18

    The official TypeScript SDK for Model Context Protocol servers and clients

    175.6M 可观测/月 13.4k ▲ 43 ★/周 3/3 当前信号

    63
  19. 19
    cline GHnpm

    Autonomous coding agent as an SDK, IDE extension, or CLI assistant.

    160.5k 可观测/月 67.9k ▲ 349 ★/周 3/3 当前信号

    62
  20. 20
    context7 GHnpm

    Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

    167.1k 可观测/月 61.9k ▲ 243 ★/周 3/3 当前信号

    62
  21. 21

    Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.

    390.5k 可观测/月 31.3k ▲ 142 ★/周 3/3 当前信号

    60
  22. 22
    claude-mem GHnpm

    Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

    57.5k 可观测/月 93.7k ▲ 438 ★/周 3/3 当前信号

    58
  23. 23

    Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

    164.8k 可观测/月 30.9k ▲ 200 ★/周 3/3 当前信号

    56
  24. 24
    langchainjs GHnpm

    The agent engineering platform

    17.7M 可观测/月 18.2k ▲ 19 ★/周 3/3 当前信号

    53
  25. 25
    context-mode GHnpm

    Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.

    62.7k 可观测/月 22.2k ▲ 1.9k ★/周 3/3 当前信号

    52
  26. 26
    haystack GHPyPI

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    675.0k 可观测/月 26.5k ▲ 60 ★/周 3/3 当前信号

    52
  27. 27
    cognee GHPyPI

    Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.

    147.0k 可观测/月 30.6k ▲ 157 ★/周 3/3 当前信号

    51
  28. 28
    FunASR GHPyPI

    Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

    355.6k 可观测/月 20.3k ▲ 98 ★/周 3/3 当前信号

    51
  29. 29
    OpenSandbox GHPyPI

    Secure, Fast, and Extensible Sandbox runtime for AI agents.

    320.1k 可观测/月 15.1k ▲ 148 ★/周 3/3 当前信号

    51
  30. 30
    agent-device GHnpm

    Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

    457.8k 可观测/月 4.5k ▲ 145 ★/周 3/3 当前信号

    49
  31. 31

    Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.

    108.2k 可观测/月 10.9k ▲ 1.9k ★/周 3/3 当前信号

    49
  32. 32
    ddgs GHPyPI

    A metasearch library that aggregates results from diverse web search services

    6.0M 可观测/月 3.0k ▲ 30 ★/周 3/3 当前信号

    45
  33. 33
    n8n-mcp GHnpm

    A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you

    324.9k 可观测/月 22.9k ▲ 34 ★/周 3/3 当前信号

    45
  34. 34

    MCP server to provide Figma layout information to AI coding agents like Cursor

    246.6k 可观测/月 15.8k ▲ 63 ★/周 3/3 当前信号

    44
  35. 35
    PageIndex GHPyPI

    📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

    60.5k 可观测/月 35.6k ▲ 87 ★/周 3/3 当前信号

    43
  36. 36
    fastapi_mcp GHPyPI

    Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!

    4.0M 可观测/月 12.0k ▲ 5 ★/周 3/3 当前信号

    42
  37. 37

    Token-efficient MCP adapter for Pi coding agent

    1.1M 可观测/月 1.5k ▲ 32 ★/周 3/3 当前信号

    37
  38. 38

    A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.

    272.1k 可观测/月 6.4k ▲ 28 ★/周 3/3 当前信号

    34
  39. 39

    Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.

    19.9k 可观测/月 11.0k ▲ 156 ★/周 3/3 当前信号

    33
  40. 40

    Exa MCP for web search and web crawling!

    190.9k 可观测/月 5.0k ▲ 23 ★/周 3/3 当前信号

    31
  41. 41

    🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

    118.4k 可观测/月 7.4k ▲ 38 ★/周 3/3 当前信号

    30
  42. 42
    agentops GHPyPI

    Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

    183.5k 可观测/月 5.8k ▲ 7 ★/周 3/3 当前信号

    27
  43. 43

    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.

    76.0k 可观测/月 2.7k ▲ 27 ★/周 3/3 当前信号

    21
  44. 44
    PocketFlow GHPyPI

    Pocket Flow: 100-line LLM framework. Let Agents build Agents!

    25.4k 可观测/月 11.2k ▲ 12 ★/周 3/3 当前信号

    20
  45. 45

    AI Agent-first JS 逆向 MCP Server:有头 Chrome 调试、断点、网络/WebSocket 分析、Patchright 反检测,可选 CloakBrowser。

    6.9k 可观测/月 2.7k ▲ 40 ★/周 3/3 当前信号

    15
  46. 46
    mcp-searxng GHnpm

    Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client

    37.1k 可观测/月 1.2k ▲ 22 ★/周 3/3 当前信号

    15
  47. 47

    법제처 국가법령정보를 LLM에서 바로 조회하는 MCP 서버. 법령·판례·조례 검색과 인용 검증 | MCP server for Korean law — search statutes, precedents, and ordinances, and verify citations

    15.9k 可观测/月 2.6k ▲ 20 ★/周 3/3 当前信号

    12
  48. 48
    Vision-Agents GHPyPI

    Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

    7.9k 可观测/月 8.1k ▲ 5 ★/周 3/3 当前信号

    12
  49. 49
    neo GHnpm

    Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.

    21.0k 可观测/月 3.3k ▲ 2 ★/周 3/3 当前信号

    11
  50. 50
    mirascope GHPyPI

    The LLM Anti-Framework

    22.9k 可观测/月 1.5k ▲ 2 ★/周 3/3 当前信号

    10
  51. 51
    loki-mode GHnpm

    Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.

    13.7k 可观测/月 1.1k ▲ 3 ★/周 3/3 当前信号

    5

观察池 · 929

这些项目已被追踪,但当前还没有足够的跨来源证据进入正式排名。它们仍可被发现,但不与主榜混排。

  1. Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.

    474 ▲ 1 ★/周 2/3 当前信号

    未排名
  2. 5ire GH

    5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .

    5.3k ▲ 2 ★/周 2/3 当前信号

    未排名
  3. 9router GH

    Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits.

    28.5k ▲ 1.3k ★/周 2/3 当前信号

    未排名
  4. Agent Skills as a Memory Layer

    3.7k ▲ 2 ★/周 2/3 当前信号

    未排名
  5. AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

    24.4k ▲ 135 ★/周 2/3 当前信号

    未排名
  6. Adala GH

    Adala: Autonomous DAta (Labeling) Agent framework

    1.6k ▲ 7 ★/周 2/3 当前信号

    未排名
  7. adk-go GH

    An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

    8.8k ▲ 15 ★/周 2/3 当前信号

    未排名
  8. An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

    1.7k ▲ 6 ★/周 2/3 当前信号

    未排名
  9. adk-js GH

    An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

    1.4k ▲ 8 ★/周 2/3 当前信号

    未排名
  10. An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

    21.5k ▲ 88 ★/周 2/3 当前信号

    未排名
  11. aeon GH

    The most autonomous AI agent framework: runs unattended on GitHub Actions, self-healing skills, drives Claude Code, Grok, Codex & more. No approval loops. Configure once, forget forever.

    724 ▲ 9 ★/周 2/3 当前信号

    未排名
  12. ag-ui GH

    AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

    15.9k ▲ 117 ★/周 2/3 当前信号

    未排名
  13. ag2 GH

    AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

    4.9k ▲ 16 ★/周 2/3 当前信号

    未排名
  14. agency GH

    A fast and minimal framework for building agentic systems

    490 2/3 当前信号

    未排名
  15. 🎭 277 个即插即用的 AI 专家角色 — 支持 Claude Code/Cursor/Copilot 等 20 种工具,覆盖工程/设计/营销/金融等 20 个部门。含 64 个中国市场原创智能体(小红书/抖音/微信/飞书/钉钉/Qt 上位机/机械设计)。搭配编排器 agency-orchestrator,一句话即可让多位专家按 DAG 自动协作。

    20.6k ▲ 276 ★/周 2/3 当前信号

    未排名
  16. 🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队,几分钟交付完整方案;验收自动核验,网页 / 桌面 / Docker 全渠道。

    2.2k ▲ 33 ★/周 2/3 当前信号

    未排名
  17. agent GH

    Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀

    1.8k ▲ 11 ★/周 2/3 当前信号

    未排名
  18. The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

    1.3k 2/3 当前信号

    未排名
  19. A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

    13.5k ▲ 145 ★/周 2/3 当前信号

    未排名
  20. Agent Framework Samples - showcasing ways in which agent framework can be utilized.

    375 ▲ 4 ★/周 2/3 当前信号

    未排名
  21. AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.

    6.2k ▲ 43 ★/周 2/3 当前信号

    未排名
  22. A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs

    516 ▲ 7 ★/周 2/3 当前信号

    未排名
  23. Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.

    661 2/3 当前信号

    未排名
  24. The absolute trainer to light up AI agents.

    18.1k ▲ 74 ★/周 2/3 当前信号

    未排名
  25. Run and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.

    11.7k ▲ 709 ★/周 2/3 当前信号

    未排名
  26. Agent-S GH

    Agent S: an open agentic framework that uses computers like a human

    12.3k ▲ 38 ★/周 2/3 当前信号

    未排名
  27. Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync

    355 2/3 当前信号

    未排名
  28. Flexible and powerful framework for managing multiple AI agents and handling complex conversations

    7.8k ▲ 3 ★/周 2/3 当前信号

    未排名
  29. Your Company Agentic Operating System

    763 ▲ 21 ★/周 2/3 当前信号

    未排名
  30. You're the boss, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/OpenCode/Cursor/Grok/GitHub Copilot/Kiro/Z.AI/MiniMax/Kimi(200+ models, 75+ LLM providers, free models no auth). Build your AI company with multiple teams

    2.1k ▲ 37 ★/周 2/3 当前信号

    未排名
  31. A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

    3.7k ▲ 11 ★/周 2/3 当前信号

    未排名
  32. Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.

    3.4k ▲ 23 ★/周 2/3 当前信号

    未排名
  33. AgentFlow: In-the-Flow Agentic System Optimization

    2.0k ▲ 8 ★/周 2/3 当前信号

    未排名
  34. https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习|数据合成

    9.5k ▲ 251 ★/周 2/3 当前信号

    未排名
  35. agentic GH

    An agentic workflow tool that provides context engineering support for opencode

    639 ▲ 2 ★/周 2/3 当前信号

    未排名
  36. Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪

    2.0k ▲ 5 ★/周 2/3 当前信号

    未排名
  37. A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.

    4.1k ▲ 50 ★/周 2/3 当前信号

    未排名
  38. TypeScript AI AI Function Calling Framework enhanced by compiler skills.

    1.0k ▲ 1 ★/周 2/3 当前信号

    未排名
  39. Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.

    1.7k ▲ 3 ★/周 2/3 当前信号

    未排名
  40. Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

    27.2k ▲ 42 ★/周 2/3 当前信号

    未排名
  41. Agently GH

    [GenAI Application Development Framework] 🚀 Build GenAI application quick and easy 💬 Easy to interact with GenAI agent in code using structure data and chained-calls syntax 🧩 Use Event-Driven Flow *TriggerFlow* to manage complex GenAI working logic 🔀 Switch to any model without rewrite application code

    1.7k ▲ 5 ★/周 2/3 当前信号

    未排名
  42. An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI application development framework.

    640 ▲ 1 ★/周 2/3 当前信号

    未排名
  43. agentos GH

    TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.

    623 ▲ 2 ★/周 2/3 当前信号

    未排名
  44. Build and run agents you can see, understand and trust.

    31.4k ▲ 636 ★/周 2/3 当前信号

    未排名
  45. Build distributed, production-grade, long-running agents.

    5.6k ▲ 130 ★/周 2/3 当前信号

    未排名
  46. A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

    455 ▲ 1 ★/周 2/3 当前信号

    未排名
  47. The AI Agent Workforce Platform. Run a hundred AI coding agents across your own machines — schedule, isolate, and steer them all from one console.

    2.3k ▲ 3 ★/周 2/3 当前信号

    未排名
  48. AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.

    985 ▲ 3 ★/周 2/3 当前信号

    未排名
  49. large population models

    647 2/3 当前信号

    未排名
  50. agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

    2.4k ▲ 4 ★/周 2/3 当前信号

    未排名
  51. Agenvoy GH

    Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets Claude Code, Codex and any MCP client build and share them.

    512 ▲ 31 ★/周 2/3 当前信号

    未排名
  52. agi GH

    The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.

    2.1k ▲ 16 ★/周 2/3 当前信号

    未排名
  53. AgileRL GH

    Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.

    951 ▲ 1 ★/周 2/3 当前信号

    未排名
  54. agmsg GH

    Cross-vendor messaging for CLI AI coding agents — let Claude Code, Codex, Gemini & Copilot talk to each other in one team. Bash + SQLite, no daemon, no framework.

    1.5k ▲ 9 ★/周 2/3 当前信号

    未排名
  55. agor GH

    Agor - team command center for all things agentic

    1.4k ▲ 8 ★/周 2/3 当前信号

    未排名
  56. 大厂发布的AI落地实践、顶尖实验室的最新论文、工业界的真实踩坑记录

    3.7k ▲ 3 ★/周 2/3 当前信号

    未排名
  57. 🚀 2026 最系统的 AI Agent 速成指南|智能体实战教程 · 完整学习路径 + 实战项目 + 面试题库 · 对标大模型应用开发工程师岗位 · 覆盖LangChain / LangGraph / Coze / Dify / MCP / skills / LLM / RAG / 提示词 · 企业级部署与微调 · 从0到企业级落地 + 从学习到上线项目 + 面试准备一体化

    4.5k ▲ 165 ★/周 2/3 当前信号

    未排名
  58. Repo for AI Agents The Definitive Guide

    1.6k ▲ 48 ★/周 2/3 当前信号

    未排名
  59. AI 时代的伯克希尔:基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

    16.3k ▲ 99 ★/周 2/3 当前信号

    未排名
  60. Claude Code + OpenClaw + Codex + WorkBuddy 中文教程 | 50篇完整教程 + 1张速查卡 | 80万+内容量 | 1500+实操示例 | AI Coding / Agent 四线学习路径(编程+助手+Agent+办公)

    6.0k ▲ 59 ★/周 2/3 当前信号

    未排名
  61. Multi-agent team operating system for Claude Code. 108 MCP tools, 40+ agent templates, 10 lifecycle hooks, 7 pipeline workflows. Persistent teams, structured meetings, task wall, real-time React dashboard. No LangChain/AutoGen — pure CC native integration.

    357 ▲ 1 ★/周 2/3 当前信号

    未排名
  62. The control plane for AI coding agents.

    1.6k ▲ 5 ★/周 2/3 当前信号

    未排名
  63. 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程,分享 OpenClaw 保姆级教程、大模型玩法(DeepSeek / GPT / Gemini / Claude / GLM)、最新 AI 资讯、Prompt 提示词大全、AI 知识百科(Agent Skills / RAG / MCP / A2A)、AI 编程教程(Harness Engineering)、AI 工具用法(Cursor / Claude Code / TRAE / Codex / Copilot)、AI 开发框架教程(Spring AI / LangChain)、AI 产品变现指南,帮你快速掌握 AI 技术,走在时代前沿。本项目为开源文档 aiguide,已升级为鱼皮 AI 导航网站

    19.8k ▲ 272 ★/周 2/3 当前信号

    未排名
  64. AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.

    618 2/3 当前信号

    未排名
  65. The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

    41.9k ▲ 1.0k ★/周 2/3 当前信号

    未排名
  66. AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude, Codex or any AI Agent from one dashboard. Move Agents between computers and locations

    780 ▲ 19 ★/周 2/3 当前信号

    未排名
  67. CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.

    407 ▲ 1 ★/周 2/3 当前信号

    未排名
  68. One Query. All Search Skill. 聚合 Gemini、Grok、豆包、元宝等平台原生 AI 搜索能力,免费获取科技趋势、行业舆情、热点追踪、旅行规划、日常问题统一接进自己的 Agent 与工作流,指定链接免费爬取

    1.3k ▲ 6 ★/周 2/3 当前信号

    未排名
  69. aichat GH

    All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

    10.4k ▲ 7 ★/周 2/3 当前信号

    未排名
  70. aideml GH

    AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.

    1.5k ▲ 13 ★/周 2/3 当前信号

    未排名
  71. aiden GH

    Aiden — Autonomous AI agent that operates your computer with prompts: browser control, terminal execution, workflows, tools, recovery systems, and persistent memory. Built solo. AGPL-3.0.

    826 ▲ 21 ★/周 2/3 当前信号

    未排名
  72. aider GH

    aider is AI pair programming in your terminal

    48.9k ▲ 147 ★/周 2/3 当前信号

    未排名
  73. AIlice GH

    AIlice is a fully autonomous, general-purpose AI agent.

    1.4k ▲ 4 ★/周 2/3 当前信号

    未排名
  74. This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

    9.6k ▲ 41 ★/周 2/3 当前信号

    未排名
  75. AINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops. AINL is a compact, graph-canonical, AI-native programming system for (READ: README)

    669 2/3 当前信号

    未排名
  76. AionUi GH

    Open-source 24/7 Cowork app for OpenClaw, Hermes, Claude Code, Codex, OpenCode and 20+ more CLI Agent | Customize your assistants | Team them up|Star if you like it!

    32.8k ▲ 173 ★/周 2/3 当前信号

    未排名
  77. 35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

    4.5k ▲ 206 ★/周 2/3 当前信号

    未排名
  78. alook GH

    Rooms for people and agents.

    1.2k ▲ 9 ★/周 2/3 当前信号

    未排名
  79. alphora GH

    A Production-Ready Framework for Building Composable AI Agents

    350 ▲ 1 ★/周 2/3 当前信号

    未排名
  80. 817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 29 security domains · Apache 2.0

    32.6k ▲ 419 ★/周 2/3 当前信号

    未排名
  81. Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

    65.9k ▲ 295 ★/周 2/3 当前信号

    未排名
  82. end to end app store screenshot creation using AI

    6.9k ▲ 47 ★/周 2/3 当前信号

    未排名
  83. AI Agent for testing Android, iOS, and Web apps. Get Started in 5 Minutes. Arbigent's intuitive UI and powerful code interface make it accessible to everyone, while its scenario breakdown feature ensures scalability for even the most complex tasks.

    638 ▲ 1 ★/周 2/3 当前信号

    未排名
  84. Arbor GH

    A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.

    1.1k ▲ 8 ★/周 2/3 当前信号

    未排名
  85. arc-kit GH

    The Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistants

    2.2k ▲ 8 ★/周 2/3 当前信号

    未排名
  86. MCP Server Framework and Tool Development library for building custom capabilities into agents.

    1.0k ▲ 3 ★/周 2/3 当前信号

    未排名
  87. Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

    4.3k ▲ 10 ★/周 2/3 当前信号

    未排名
  88. ArcReel GH

    AI Agent 驱动的开源可自部署视频工作台:将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿,支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production

    4.4k ▲ 75 ★/周 2/3 当前信号

    未排名
  89. AReaL GH

    The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

    5.7k ▲ 20 ★/周 2/3 当前信号

    未排名
  90. argent GH

    An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion.

    2.8k ▲ 407 ★/周 2/3 当前信号

    未排名
  91. arkon GH

    Arkon: Enterprise AI Knowledge Hub & MCP Server. Self-hosted knowledge base for teams to manage RAG contexts, access policies, and AI skills. Connect Claude and other LLMs via Model Context Protocol (MCP) for automated, secure organizational knowledge integration.

    1.3k ▲ 65 ★/周 2/3 当前信号

    未排名
  92. ART GH

    Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

    10.7k ▲ 13 ★/周 2/3 当前信号

    未排名
  93. A swarm of disposable agents for unattributable web interaction

    472 2/3 当前信号

    未排名
  94. AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.

    2.3k ▲ 23 ★/周 2/3 当前信号

    未排名
  95. AstrBot GH

    AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

    40.4k ▲ 354 ★/周 2/3 当前信号

    未排名
  96. astrid GH

    Astrid is a portable, capability-secure operating system for composable software.

    10.3k 2/3 当前信号

    未排名
  97. Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.

    9.0k ▲ 75 ★/周 2/3 当前信号

    未排名
  98. Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.

    1.0k ▲ 14 ★/周 2/3 当前信号

    未排名
  99. Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket, SSE, gRPC, or WebTransport/HTTP3. Speaks MCP, A2A, and AG-UI.

    3.8k ▲ 1 ★/周 2/3 当前信号

    未排名
  100. ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

    16.0k ▲ 281 ★/周 2/3 当前信号

    未排名
  101. 🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

    1.3k 2/3 当前信号

    未排名
  102. A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents

    750 ▲ 6 ★/周 2/3 当前信号

    未排名
  103. AutoCVE GH

    Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.

    1.4k ▲ 8 ★/周 2/3 当前信号

    未排名
  104. autogen GH

    A programming framework for agentic AI

    60.9k ▲ 126 ★/周 2/3 当前信号

    未排名
  105. AutoGPT GH

    AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

    187.3k ▲ 126 ★/周 2/3 当前信号

    未排名
  106. AutoHarness: Automated Harness Engineering for AI Agents

    374 ▲ 5 ★/周 2/3 当前信号

    未排名
  107. An autonomous HR agent that can answer user queries using tools

    462 2/3 当前信号

    未排名
  108. AWorld GH

    Search, understand, reproduce, and improve an idea with ease

    1.2k ▲ 2 ★/周 2/3 当前信号

    未排名
  109. Composable building blocks for full-stack AWS apps — define infrastructure and runtime code together with end-to-end type safety using TypeScript, local mocking, and native client codegen for Kotlin, Swift, and Dart.

    392 ▲ 5 ★/周 2/3 当前信号

    未排名
  110. babyagi GH

    22.4k 2/3 当前信号

    未排名
  111. Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem

    6.7k ▲ 64 ★/周 2/3 当前信号

    未排名
  112. Build production-ready AI agents in both Python and Typescript.

    3.4k ▲ 9 ★/周 2/3 当前信号

    未排名
  113. beevibe GH

    The agent-native OS for companies.

    345 2/3 当前信号

    未排名
  114. The open‑source AI Agents Governance & Orchestration framework: write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run

    1.2k ▲ 65 ★/周 2/3 当前信号

    未排名
  115. 微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。

    42.2k ▲ 39 ★/周 2/3 当前信号

    未排名
  116. Standards for building agents, better

    1.6k ▲ 1 ★/周 2/3 当前信号

    未排名
  117. bifrost GH

    Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

    8.0k ▲ 176 ★/周 2/3 当前信号

    未排名
  118. Bindu GH

    Bindu: The identity, communication, and payments layer for AI agents.

    9.8k ▲ 79 ★/周 2/3 当前信号

    未排名
  119. blades GH

    Blades is a Go-based multimodal AI Agent framework.

    814 ▲ 3 ★/周 2/3 当前信号

    未排名
  120. The practical implementation of Aspire using Microservices, AI-Agents

    505 ▲ 1 ★/周 2/3 当前信号

    未排名
  121. 🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.

    1.9k ▲ 213 ★/周 2/3 当前信号

    未排名
  122. AI Multi-Agent Framework in .NET

    3.1k ▲ 1 ★/周 2/3 当前信号

    未排名
  123. boxlite GH

    The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.

    2.3k ▲ 15 ★/周 2/3 当前信号

    未排名
  124. A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

    2.6k ▲ 4 ★/周 2/3 当前信号

    未排名
  125. Browser Harness | Self-healing harness that enables LLMs to complete any task.

    17.5k ▲ 108 ★/周 2/3 当前信号

    未排名
  126. Monitor browser logs directly from Cursor and other MCP compatible IDEs.

    7.3k ▲ 6 ★/周 2/3 当前信号

    未排名
  127. A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

    3.4k ▲ 20 ★/周 2/3 当前信号

    未排名
  128. ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)

    5.0k ▲ 1 ★/周 2/3 当前信号

    未排名
  129. camel GH

    🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

    17.7k ▲ 33 ★/周 2/3 当前信号

    未排名
  130. carbon GH

    Carbon is an open source ERP, MES and QMS for manufacturing. Perfect for complex assembly, contract manufacturing, high volume, and configure to order manufacturing.

    2.4k ▲ 6 ★/周 2/3 当前信号

    未排名
  131. casdoor GH

    An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA, Face ID, Google Workspace, Azure AD

    14.4k ▲ 41 ★/周 2/3 当前信号

    未排名
  132. caura GH

    Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.

    498 ▲ 15 ★/周 2/3 当前信号

    未排名
  133. A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

    132.4k ▲ 1.2k ★/周 2/3 当前信号

    未排名
  134. cccc GH

    Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your phone. One pip install, zero infrastructure. A production‑minded orchestrator for 24/7 workflow

    1.2k ▲ 101 ★/周 2/3 当前信号

    未排名
  135. ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

    1.6k 2/3 当前信号

    未排名
  136. chatbot GH

    Chatbot继续沿着LLM前进,近期更新小参数量SLM的和训练脚本,支持本地训练。新增ChatAgent,实现各种有实际场景价值的Agent实现。

    3.6k 2/3 当前信号

    未排名
  137. ChatDev GH

    ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration

    34.3k ▲ 61 ★/周 2/3 当前信号

    未排名
  138. ChatLab GH

    Local-first chat history analyzer with AI. | 本地优先的 AI 聊天记录分析工具

    7.3k ▲ 36 ★/周 2/3 当前信号

    未排名
  139. ChatTTS GH

    A generative speech model for daily dialogue.

    39.8k ▲ 15 ★/周 2/3 当前信号

    未排名
  140. AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs

    51.7k ▲ 227 ★/周 2/3 当前信号

    未排名
  141. chidori GH

    The agent framework where every run is durable, replayable, and resumable by default.

    1.4k 2/3 当前信号

    未排名
  142. 非线智能 NoneLinear - ReLE评测:中文AI大模型能力评测(持续更新):目前已囊括374个大模型,覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型, 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜,也提供规模超200万的大模型缺陷库!方便广大社区研究分析、改进大模型。

    6.4k ▲ 13 ★/周 2/3 当前信号

    未排名
  143. Chorus GH

    The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)

    1.2k ▲ 10 ★/周 2/3 当前信号

    未排名
  144. Chrome DevTools for coding agents

    51.7k ▲ 672 ★/周 2/3 当前信号

    未排名
  145. Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents

    3.5k ▲ 16 ★/周 2/3 当前信号

    未排名
  146. 《御舆:解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析,15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站:

    4.2k ▲ 29 ★/周 2/3 当前信号

    未排名
  147. Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

    25.0k ▲ 152 ★/周 2/3 当前信号

    未排名
  148. Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!

    4.6k ▲ 14 ★/周 2/3 当前信号

    未排名
  149. The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands

    547 ▲ 2 ★/周 2/3 当前信号

    未排名
  150. 45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container. Also includes the dx plugin: skills for everyday dev workflows.

    10.1k ▲ 35 ★/周 2/3 当前信号

    未排名
  151. The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.

    6.0k ▲ 54 ★/周 2/3 当前信号

    未排名
  152. Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

    12.5k ▲ 45 ★/周 2/3 当前信号

    未排名
  153. The missing DevTools for Claude Code — inspect session logs, tool calls, token usage, subagents, and context window in a visual UI. Free, open source.

    3.9k ▲ 14 ★/周 2/3 当前信号

    未排名
  154. Official, Anthropic-managed directory of high quality Claude Code Plugins.

    36.2k ▲ 219 ★/周 2/3 当前信号

    未排名
  155. 67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

    11.4k ▲ 99 ★/周 2/3 当前信号

    未排名
  156. 380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory, research, business operations, commercial & finance, and your daily productivity skills.

    25.9k ▲ 297 ★/周 2/3 当前信号

    未排名
  157. 🦞 OpenClaw & Hermes Agent 多引擎 AI 管理面板 — 内置 AI 助手(工具调用 + 图片识别 + 多模态),一键安装 | Tauri v2 跨平台桌面应用 | 11 种语言

    2.9k 2/3 当前信号

    未排名
  158. ClawX GH

    ClawX is a desktop app that provides a graphical interface for OpenClaw AI agents. It turns CLI-based AI orchestration into a desktop experience without using the terminal. China website is https://clawx.com.cn.

    7.6k ▲ 8 ★/周 2/3 当前信号

    未排名
  159. Autonomous Android and computer use using any LLM (local or remote)

    712 ▲ 2 ★/周 2/3 当前信号

    未排名
  160. Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, Skills Studio, resilient streaming, and long-task recovery controls.

    294 2/3 当前信号

    未排名
  161. Incremental engine for long horizon agents 🌟 Star if you like it!

    11.5k ▲ 58 ★/周 2/3 当前信号

    未排名
  162. The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

    5.1k ▲ 139 ★/周 2/3 当前信号

    未排名
  163. 🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.

    1.6k ▲ 11 ★/周 2/3 当前信号

    未排名
  164. [ICML 2026] Video generation via code

    2.0k ▲ 9 ★/周 2/3 当前信号

    未排名
  165. High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

    43.0k ▲ 686 ★/周 2/3 当前信号

    未排名
  166. CodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows. ⚡️

    2.5k 2/3 当前信号

    未排名
  167. A codex plugin for running optimization loops inside a codebase. It is useful when you have a measurable target and many possible changes to try: test runtime, build speed, bundle size, model loss, Lighthouse scores, memory use, query latency, or any other metric you can print from a script.

    837 ▲ 1 ★/周 2/3 当前信号

    未排名
  168. Self-evolving second brain with 33 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

    1.2k ▲ 11 ★/周 2/3 当前信号

    未排名
  169. An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance

    5.5k ▲ 8 ★/周 2/3 当前信号

    未排名
  170. Command Code AI — the best coding agent for open models.

    3.9k ▲ 44 ★/周 2/3 当前信号

    未排名
  171. Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.

    1.3k ▲ 8 ★/周 2/3 当前信号

    未排名
  172. An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies using a multi-agent framework. It leverages Google's Gemini 2.5 Flash and OpenAI's GPT-5.1 on the backend for inference.

    2.3k ▲ 2 ★/周 2/3 当前信号

    未排名
  173. Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

    30.1k ▲ 77 ★/周 2/3 当前信号

    未排名
  174. A library for generative social simulation

    1.7k ▲ 21 ★/周 2/3 当前信号

    未排名
  175. Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations

    813 ▲ 1 ★/周 2/3 当前信号

    未排名
  176. open-source coding agent

    35.9k ▲ 106 ★/周 2/3 当前信号

    未排名
  177. The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol

    37.3k ▲ 104 ★/周 2/3 当前信号

    未排名
  178. CORAL GH

    Open-source autoresearch powered by autonomous coding agents. Run Claude Code, OpenCode, and Codex with grading, shared knowledge, and multi-agent evolution. Accepted at COLM 2026.

    976 ▲ 20 ★/周 2/3 当前信号

    未排名
  179. cordum GH

    The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.

    504 ▲ 3 ★/周 2/3 当前信号

    未排名
  180. Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)

    46.9k ▲ 131 ★/周 2/3 当前信号

    未排名
  181. crab GH

    🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/

    426 2/3 当前信号

    未排名
  182. The long-running embedded agent

    743 2/3 当前信号

    未排名
  183. crush GH

    Glamourous agentic coding for all 💘

    28.0k ▲ 100 ★/周 2/3 当前信号

    未排名
  184. crust GH

    🌟 Open Source AI Agent Security Infrastructure — intercepts and blocks dangerous agent behaviors before they happen. Just one command! Join us to build safer Human-AI Symbiosis!

    439 ▲ 1 ★/周 2/3 当前信号

    未排名
  185. crystal GH

    (Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.

    3.1k 2/3 当前信号

    未排名
  186. The official C# SDK for Model Context Protocol servers and clients. Maintained in collaboration with Microsoft.

    4.5k ▲ 3 ★/周 2/3 当前信号

    未排名
  187. ctx GH

    Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.

    1.1k ▲ 16 ★/周 2/3 当前信号

    未排名
  188. cua GH

    Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

    22.5k ▲ 309 ★/周 2/3 当前信号

    未排名
  189. 基于 AI Agent 工作流的修仙世界模拟器,旨在还原智能、开放的仙侠世界。| An open-source Cultivation World Simulator using Agentic Workflow to create a dynamic, emerging Xianxia world.

    2.1k ▲ 12 ★/周 2/3 当前信号

    未排名
  190. TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

    7.0k ▲ 19 ★/周 2/3 当前信号

    未排名
  191. Production-grade MCP server giving Claude 27 security intelligence tools across 21 APIs — CVE lookup, EPSS scoring, CISA KEV, MITRE ATT&CK, Shodan, VirusTotal, and more.

    1.5k ▲ 163 ★/周 2/3 当前信号

    未排名
  192. 👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

    330 ▲ 4 ★/周 2/3 当前信号

    未排名
  193. dagu GH

    Self-hostable workflow orchestrator for teams whose main work isn't orchestration. Declarative YAML over your scripts, SSH commands, containers, etc; keep workflows separate from business logic. One binary, no database, runs on limited H/W resources. Alternative to Airflow / Cron / Job Scheduler.

    3.9k ▲ 105 ★/周 2/3 当前信号

    未排名
  194. Open-source multi-agent collaboration system inspired by Chinese governance — deploy and coordinate specialized AI agents with OpenClaw.

    2.7k 2/3 当前信号

    未排名
  195. Autonomous AI pentesting engine across web, cloud, identity, CI/CD, IaC, databases, Active Directory, Kubernetes, IoT firmware and AI/LLM endpoints (OWASP LLM Top 10). Real exploits with proof for every finding. Privacy gateway: the LLM never sees your real IPs, hosts or creds; nothing leaves your perimeter.

    917 ▲ 27 ★/周 2/3 当前信号

    未排名
  196. An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.

    8.1k ▲ 508 ★/周 2/3 当前信号

    未排名
  197. Daydreams is a set of tools for building agents for commerce

    617 2/3 当前信号

    未排名
  198. daytona GH

    Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

    71.7k 2/3 当前信号

    未排名
  199. DB-GPT GH

    open-source agentic AI data assistant for the next generation of AI + Data products.

    19.9k ▲ 57 ★/周 2/3 当前信号

    未排名
  200. dbhub GH

    Token conscious database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.

    3.5k ▲ 38 ★/周 2/3 当前信号

    未排名

← 返回全部榜单