51 projects currently qualify for the cross-source index; 980 software projects remain tracked in total.
Methodology v2.0 · index snapshot 2026-09-12 · 2-day freshness window
Ranked projects have at least two current score dimensions across two source types. Score = observed adoption (45%) + momentum (30%) + attention (25%); stale or missing signals receive no weight.
The agent engineering platform.
204.9M observed/mo 146.2k ★ ▲ 461 ★/wk 3/3 current signals
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 observed/mo 58.5k ★ ▲ 450 ★/wk 3/3 current signals
Agents that use the browser.
31.1M observed/mo 114.3k ★ ▲ 1.9k ★/wk 3/3 current signals
The context API to search, scrape, and interact with the web at scale. 🔥
6.2M observed/mo 179.3k ★ ▲ 2.5k ★/wk 3/3 current signals
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
20.0M observed/mo 58.4k ★ ▲ 276 ★/wk 3/3 current signals
🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
1.4M observed/mo 82.2k ★ ▲ 689 ★/wk 3/3 current signals
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 observed/mo 26.7k ★ ▲ 110 ★/wk 3/3 current signals
LlamaIndex is the document processing platform for AI
9.8M observed/mo 52.1k ★ ▲ 101 ★/wk 3/3 current signals
DSPy: The framework for programming—not prompting—language models
5.6M observed/mo 38.0k ★ ▲ 180 ★/wk 3/3 current signals
🚀 The fast, Pythonic way to build MCP servers and clients.
65.4M observed/mo 27.6k ★ ▲ 91 ★/wk 3/3 current signals
The official Python SDK for Model Context Protocol servers and clients
272.2M observed/mo 24.3k ★ ▲ 63 ★/wk 3/3 current signals
Mastra is the modern TypeScript framework for AI-powered applications and agents.
5.3M observed/mo 28.0k ★ ▲ 233 ★/wk 3/3 current signals
Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed.
1.3M observed/mo 31.4k ★ ▲ 188 ★/wk 3/3 current signals
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
8.4M observed/mo 19.9k ★ ▲ 140 ★/wk 3/3 current signals
Build, run, and manage agent platforms.
2.0M observed/mo 42.1k ★ ▲ 80 ★/wk 3/3 current signals
The official TypeScript SDK for Model Context Protocol servers and clients
175.6M observed/mo 13.4k ★ ▲ 43 ★/wk 3/3 current signals
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
160.5k observed/mo 67.9k ★ ▲ 349 ★/wk 3/3 current signals
Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
167.1k observed/mo 61.9k ★ ▲ 243 ★/wk 3/3 current signals
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 observed/mo 31.3k ★ ▲ 142 ★/wk 3/3 current signals
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 observed/mo 93.7k ★ ▲ 438 ★/wk 3/3 current signals
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 observed/mo 30.9k ★ ▲ 200 ★/wk 3/3 current signals
The agent engineering platform
17.7M observed/mo 18.2k ★ ▲ 19 ★/wk 3/3 current signals
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 observed/mo 22.2k ★ ▲ 1.9k ★/wk 3/3 current signals
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 observed/mo 26.5k ★ ▲ 60 ★/wk 3/3 current signals
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 observed/mo 30.6k ★ ▲ 157 ★/wk 3/3 current signals
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
355.6k observed/mo 20.3k ★ ▲ 98 ★/wk 3/3 current signals
Secure, Fast, and Extensible Sandbox runtime for AI agents.
320.1k observed/mo 15.1k ★ ▲ 148 ★/wk 3/3 current signals
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 observed/mo 4.5k ★ ▲ 145 ★/wk 3/3 current signals
Stealth headless browser for AI agents — bypass Cloudflare, bot detection, and anti-scraping. Drop-in Puppeteer/Playwright replacement.
108.2k observed/mo 10.9k ★ ▲ 1.9k ★/wk 3/3 current signals
A metasearch library that aggregates results from diverse web search services
6.0M observed/mo 3.0k ★ ▲ 30 ★/wk 3/3 current signals
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
324.9k observed/mo 22.9k ★ ▲ 34 ★/wk 3/3 current signals
MCP server to provide Figma layout information to AI coding agents like Cursor
246.6k observed/mo 15.8k ★ ▲ 63 ★/wk 3/3 current signals
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
60.5k observed/mo 35.6k ★ ▲ 87 ★/wk 3/3 current signals
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
4.0M observed/mo 12.0k ★ ▲ 5 ★/wk 3/3 current signals
Token-efficient MCP adapter for Pi coding agent
1.1M observed/mo 1.5k ★ ▲ 32 ★/wk 3/3 current signals
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
272.1k observed/mo 6.4k ★ ▲ 28 ★/wk 3/3 current signals
Ekko Studio is a local-first AI workspace for multi-agent chat, coding, and visual workflows, available on desktop and the web.
19.9k observed/mo 11.0k ★ ▲ 156 ★/wk 3/3 current signals
Exa MCP for web search and web crawling!
190.9k observed/mo 5.0k ★ ▲ 23 ★/wk 3/3 current signals
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.
118.4k observed/mo 7.4k ★ ▲ 38 ★/wk 3/3 current signals
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 observed/mo 5.8k ★ ▲ 7 ★/wk 3/3 current signals
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 observed/mo 2.7k ★ ▲ 27 ★/wk 3/3 current signals
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
25.4k observed/mo 11.2k ★ ▲ 12 ★/wk 3/3 current signals
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 observed/mo 2.7k ★ ▲ 40 ★/wk 3/3 current signals
Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client
37.1k observed/mo 1.2k ★ ▲ 22 ★/wk 3/3 current signals
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 observed/mo 2.6k ★ ▲ 20 ★/wk 3/3 current signals
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 observed/mo 8.1k ★ ▲ 5 ★/wk 3/3 current signals
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 observed/mo 3.3k ★ ▲ 2 ★/wk 3/3 current signals
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 observed/mo 1.1k ★ ▲ 3 ★/wk 3/3 current signals
Tracked projects that do not yet have enough current, cross-source evidence for a formal rank. They remain discoverable without being mixed into the main index.
Personal AI assistant for work inside corporate constraints, built on coding agents and the tools, sessions, and permissions you already have.
474 ★ ▲ 1 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
8.8k ★ ▲ 15 ★/wk 2/3 current signals
An open-source, code-first Java toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
1.7k ★ ▲ 6 ★/wk 2/3 current signals
An open-source, code-first Typescript toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
1.4k ★ ▲ 8 ★/wk 2/3 current signals
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
21.5k ★ ▲ 88 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
15.9k ★ ▲ 117 ★/wk 2/3 current signals
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
4.9k ★ ▲ 16 ★/wk 2/3 current signals
🎭 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 ★/wk 2/3 current signals
🚀 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 ★/wk 2/3 current signals
Ship your code, on autopilot. An open source agent that lives on your machines 24/7 and keeps your apps running. 🦀
1.8k ★ ▲ 11 ★/wk 2/3 current signals
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 current signals
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
13.5k ★ ▲ 145 ★/wk 2/3 current signals
Agent Framework Samples - showcasing ways in which agent framework can be utilized.
375 ★ ▲ 4 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs
516 ★ ▲ 7 ★/wk 2/3 current signals
Give Claude/Cursor email powers. 27 MCP tools — inbox, send, reply, contacts, search. Free, no signup.
661 ★ 2/3 current signals
The absolute trainer to light up AI agents.
18.1k ★ ▲ 74 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Agent S: an open agentic framework that uses computers like a human
12.3k ★ ▲ 38 ★/wk 2/3 current signals
Discover and compare open-source Agent Skills, tools & MCP servers — with quality scoring, trending analysis, and automated GitHub sync
355 ★ 2/3 current signals
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
7.8k ★ ▲ 3 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
3.7k ★ ▲ 11 ★/wk 2/3 current signals
Amazon Bedrock Agentcore accelerates AI agents into production with the scale, reliability, and security, critical to real-world deployment.
3.4k ★ ▲ 23 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
An agentic workflow tool that provides context engineering support for opencode
639 ★ ▲ 2 ★/wk 2/3 current signals
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
2.0k ★ ▲ 5 ★/wk 2/3 current signals
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
4.1k ★ ▲ 50 ★/wk 2/3 current signals
TypeScript AI AI Function Calling Framework enhanced by compiler skills.
1.0k ★ ▲ 1 ★/wk 2/3 current signals
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
1.7k ★ ▲ 3 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
[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 ★/wk 2/3 current signals
An open-source LLM based automatically daily news collecting workflow showcase powered by Agently AI application development framework.
640 ★ ▲ 1 ★/wk 2/3 current signals
TypeScript AI agent framework: cognitive memory, runtime tool forging, multi-agent orchestration, 11 LLM providers.
623 ★ ▲ 2 ★/wk 2/3 current signals
Build and run agents you can see, understand and trust.
31.4k ★ ▲ 636 ★/wk 2/3 current signals
Build distributed, production-grade, long-running agents.
5.6k ★ ▲ 130 ★/wk 2/3 current signals
A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.
455 ★ ▲ 1 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
AI writes code. This automates everything else · 24 plugins · 49 agents · 44 skills · for Claude Code, OpenCode, Codex, Cursor, Kiro.
985 ★ ▲ 3 ★/wk 2/3 current signals
agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.
2.4k ★ ▲ 4 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.
951 ★ ▲ 1 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
🚀 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 ★/wk 2/3 current signals
Repo for AI Agents The Definitive Guide
1.6k ★ ▲ 48 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
AI-Hedge-Fund for Crypto 🚀 AI-powered hedge fund for cryptocurrency trading, leveraging LLM agents for intelligent decision-making.
618 ★ 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
CAIPE is an open-source AI platform for building, governing, and operating AI agents and agentic workflows for platform engineering and beyond.
407 ★ ▲ 1 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
1.5k ★ ▲ 13 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
AIlice is a fully autonomous, general-purpose AI agent.
1.4k ★ ▲ 4 ★/wk 2/3 current signals
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
9.6k ★ ▲ 41 ★/wk 2/3 current signals
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 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
A Production-Ready Framework for Building Composable AI Agents
350 ★ ▲ 1 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
65.9k ★ ▲ 295 ★/wk 2/3 current signals
end to end app store screenshot creation using AI
6.9k ★ ▲ 47 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
A generalist autonomous research agent — runs experiments, researches, and iteratively optimizes, autonomously.
1.1k ★ ▲ 8 ★/wk 2/3 current signals
The Enterprise Architecture Governance Harness — strategy, architecture, delivery, and assurance using AI coding assistants
2.2k ★ ▲ 8 ★/wk 2/3 current signals
MCP Server Framework and Tool Development library for building custom capabilities into agents.
1.0k ★ ▲ 3 ★/wk 2/3 current signals
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator
4.3k ★ ▲ 10 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
5.7k ★ ▲ 20 ★/wk 2/3 current signals
An agentic toolkit to control, debug, and profile iOS and Android apps. Made by Software Mansion.
2.8k ★ ▲ 407 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
A swarm of disposable agents for unattributable web interaction
472 ★ 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Astrid is a portable, capability-secure operating system for composable software.
10.3k ★ 2/3 current signals
Enterprise-grade, commercial-friendly agentic workflow platform for building next-generation SuperAgents.
9.0k ★ ▲ 75 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
🔥 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 current signals
A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents
750 ★ ▲ 6 ★/wk 2/3 current signals
Agent-driven automated CVE discovery platform for source code auditing, vulnerability verification, and report generation.
1.4k ★ ▲ 8 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
AutoHarness: Automated Harness Engineering for AI Agents
374 ★ ▲ 5 ★/wk 2/3 current signals
An autonomous HR agent that can answer user queries using tools
462 ★ 2/3 current signals
Search, understand, reproduce, and improve an idea with ease
1.2k ★ ▲ 2 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
22.4k ★ 2/3 current signals
Backlog.md - A tool for managing project collaboration between humans and AI Agents in a git ecosystem
6.7k ★ ▲ 64 ★/wk 2/3 current signals
Build production-ready AI agents in both Python and Typescript.
3.4k ★ ▲ 9 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Bindu: The identity, communication, and payments layer for AI agents.
9.8k ★ ▲ 79 ★/wk 2/3 current signals
The practical implementation of Aspire using Microservices, AI-Agents
505 ★ ▲ 1 ★/wk 2/3 current signals
🤖 Local-assist BOSS Zhipin CLI for AI agents — search, welfare filtering, shortlist, JSON-envelope output; low-risk & compliant by default.
1.9k ★ ▲ 213 ★/wk 2/3 current signals
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
2.3k ★ ▲ 15 ★/wk 2/3 current signals
A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.
2.6k ★ ▲ 4 ★/wk 2/3 current signals
Browser Harness | Self-healing harness that enables LLMs to complete any task.
17.5k ★ ▲ 108 ★/wk 2/3 current signals
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
7.3k ★ ▲ 6 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
ByteRover CLI (brv) - The portable memory layer for autonomous coding agents (formerly Cipher)
5.0k ★ ▲ 1 ★/wk 2/3 current signals
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
17.7k ★ ▲ 33 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 current signals
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 current signals
ChatDev 2.0: Dev All through LLM-powered Multi-Agent Collaboration
34.3k ★ ▲ 61 ★/wk 2/3 current signals
Local-first chat history analyzer with AI. | 本地优先的 AI 聊天记录分析工具
7.3k ★ ▲ 36 ★/wk 2/3 current signals
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
51.7k ★ ▲ 227 ★/wk 2/3 current signals
The agent framework where every run is durable, replayable, and resumable by default.
1.4k ★ 2/3 current signals
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 ★/wk 2/3 current signals
The Agent Harness for AI-Human Collaboration, inspired by the AI-DLC (AI-Driven Development Lifecycle)
1.2k ★ ▲ 10 ★/wk 2/3 current signals
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
3.5k ★ ▲ 16 ★/wk 2/3 current signals
《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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user!
4.6k ★ ▲ 14 ★/wk 2/3 current signals
The complete guide to Claude Code: CLAUDE.md, hooks, skills, MCP servers, and commands
547 ★ ▲ 2 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
6.0k ★ ▲ 54 ★/wk 2/3 current signals
Code search MCP for Claude Code. Make entire codebase the context for any coding agent.
12.5k ★ ▲ 45 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Official, Anthropic-managed directory of high quality Claude Code Plugins.
36.2k ★ ▲ 219 ★/wk 2/3 current signals
67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.
11.4k ★ ▲ 99 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
🦞 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 current signals
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 ★/wk 2/3 current signals
Autonomous Android and computer use using any LLM (local or remote)
712 ★ ▲ 2 ★/wk 2/3 current signals
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 current signals
Incremental engine for long horizon agents 🌟 Star if you like it!
11.5k ★ ▲ 58 ★/wk 2/3 current signals
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
5.1k ★ ▲ 139 ★/wk 2/3 current signals
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
1.6k ★ ▲ 11 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
CodeMachine is an open-source tool that orchestrates AI coding agents into repeatable, long-running workflows. ⚡️
2.5k ★ 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
An AI-powered custom node for ComfyUI designed to enhance workflow automation and provide intelligent assistance
5.5k ★ ▲ 8 ★/wk 2/3 current signals
Command Code AI — the best coding agent for open models.
3.9k ★ ▲ 44 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
813 ★ ▲ 1 ★/wk 2/3 current signals
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
37.3k ★ ▲ 104 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
426 ★ 2/3 current signals
🌟 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 ★/wk 2/3 current signals
(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 current signals
The official C# SDK for Model Context Protocol servers and clients. Maintained in collaboration with Microsoft.
4.5k ★ ▲ 3 ★/wk 2/3 current signals
Instant recall for coding agents. Search the history already on your machine. Git blame, but for agent sessions.
1.1k ★ ▲ 16 ★/wk 2/3 current signals
Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.
22.5k ★ ▲ 309 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
👾 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 ★/wk 2/3 current signals
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 ★/wk 2/3 current signals
Open-source multi-agent collaboration system inspired by Chinese governance — deploy and coordinate specialized AI agents with OpenClaw.
2.7k ★ 2/3 current signals
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 ★/wk 2/3 current signals
An AI-agent skill that generates browser-editable presentations from multiple visual themes, exportable to HTML, PDF, and PPTX.
8.1k ★ ▲ 508 ★/wk 2/3 current signals
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
71.7k ★ 2/3 current signals
open-source agentic AI data assistant for the next generation of AI + Data products.
19.9k ★ ▲ 57 ★/wk 2/3 current signals
Token conscious database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.
3.5k ★ ▲ 38 ★/wk 2/3 current signals