Open-source agent-framework software
2398 open-source libraries, tools and applications tagged agent-framework, ranked by how closely agent-framework is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
2398 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| firecrawl/open-scouts Open Scouts is an AI-powered web monitoring platform where users create automated 'scouts' that run on a schedule to search the web and sen… | 51 | 1373 | active |
| Lapis0x0/obsidian-yolo YOLO is an agent-native AI assistant plugin for Obsidian that combines chat, writing assistance, knowledge base interaction, and agent orch… | 83 | 1372 | active |
| HazyResearch/minions Minions is a communication protocol and Python framework that lets small on-device LLMs collaborate with frontier cloud LLMs to cut cloud i… | 49 | 1370 | active |
| OpenRaiser/NanoResearch NanoResearch is an autonomous AI research assistant that runs an end-to-end pipeline from a research idea to a complete LaTeX paper. It exe… | 57 | 1369 | active |
| Kuingsmile/word-GPT-Plus Word GPT Plus is a Microsoft Word add-in that integrates LLMs and AI agents directly into Word for generating, translating, summarizing, an… | 83 | 1368 | active |
| ntegrals/10x 10x is an open-source terminal-based AI coding agent that chains multiple LLM models through multi-step 'Superpowers' workflows with smart … | 43 | 1366 | active |
| ThousandBirdsInc/chidori Chidori is an agent framework that runs async TypeScript agents on an embedded pure-Rust JavaScript engine, recording every side effect (LL… | 92 | 1365 | active |
| Team-Commonly/commonly Commonly is an open-source, self-hostable workspace where humans and multiple AI agents (Claude Code, Codex, OpenClaw, or custom runtimes) … | 84 | 1364 | active |
| raroque/boop-agent Boop is a self-hosted iMessage-based personal AI agent that runs on either a Claude Code subscription (via the Claude Agent SDK) or a Codex… | 53 | 1364 | active |
| xlang-ai/OpenAgents OpenAgents is an open platform for using and hosting LLM-powered language agents, featuring a Data Agent for Python/SQL analysis, a Plugins… | 29 | 4863 | maintenance |
| wrtnlabs/autobe AutoBE is an AI-powered backend builder that turns natural language requirements into complete NestJS/TypeScript backend applications with … | 65 | 1361 | active |
| amplifthq/opentag OpenTag is a local-first gateway that lets you mention coding agents like Claude Code, Codex, and Cursor from Slack, GitHub, GitLab, Linear… | 81 | 1359 | active |
| fastclaw-ai/fastclaw FastClaw is a lightweight AI agent runtime written in Go, distributed as a single binary. It acts as an agent factory that creates, manages… | 77 | 1359 | active |
| BillHuang2001/evogit EvoGit is a decentralized multi-agent framework that treats software development as an evolutionary process, deploying a population of inde… | 64 | 1358 | active |
| ZJU-REAL/ClawGUI ClawGUI is a unified Python framework for GUI agents covering the full lifecycle: online reinforcement learning training (ClawGUI-RL with G… | 64 | 1356 | active |
| first-fluke/oh-my-agent oh-my-agent is a multi-agent orchestration framework for AI-powered IDEs and CLI coding tools like Claude Code, Codex, and Cursor. It decom… | 79 | 1352 | active |
| poco-ai/poco-claw Poco is a self-hostable AI agent execution platform that serves as a more polished alternative to OpenClaw, powered by a Claude Code-based … | 76 | 1352 | active |
| Abraxas-365/langchain-rust LangChain for Rust is the Rust language implementation of the LangChain framework for building LLM-powered applications through composabili… | 94 | 1350 | active |
| GanyuanRan/Aegis Aegis is a method pack (plugin/skills collection) that makes AI coding agents architecture-aware, baseline-first, evidence-verified, and dr… | 77 | 1347 | active |
| sashiko-dev/sashiko Sashiko is an agentic code review system for the Linux kernel that ingests patches from mailing lists, GitHub PRs, GitLab MRs, or local git… | 61 | 1346 | active |
| ace-agent/ace ACE is a Python framework for Agentic Context Engineering that lets language models self-improve by treating contexts as evolving playbooks… | 58 | 1344 | active |
| louisho5/picobot Picobot is a lightweight, self-hosted AI agent distributed as a single ~9MB Go binary with persistent memory, tool calling, skills, and mes… | 80 | 1342 | active |
| pullfrog/pullfrog Pullfrog is an open-source, model-agnostic GitHub bot that runs coding agents (Claude, Codex, etc.) inside your repo's GitHub Actions. It t… | 82 | 1340 | active |
| a-real-ai/pywinassistant PyWinAssistant is an open-source agentic framework that acts as a Computer-Using-Agent, operating Windows 10/11 graphical user interfaces e… | 17 | 1340 | active |
| BytedTsinghua-SIA/CUDA-Agent CUDA-Agent is a large-scale agentic reinforcement learning system from ByteDance Seed and Tsinghua that trains LLMs to generate high-perfor… | 53 | 1338 | active |
| Intuition-Lab/personal-model Personal Model (Persome) is a local-first macOS runtime that captures focused cross-app activity and builds an evidence-linked personal mem… | 76 | 1337 | active |
| tjboudreaux/cc-thinking-skills A catalog of 28 portable Agent Skills that give AI coding agents structured reasoning procedures based on mental models like first principl… | 63 | 1335 | active |
| nvk/llm-wiki A plugin that lets AI agents (Claude Code, OpenAI Codex, OpenCode, portable agents) compile and maintain LLM-curated knowledge bases as pla… | 74 | 1334 | active |
| modelscope/sirchmunk Sirchmunk is an agentic, embedding-free search engine that turns raw files into a self-evolving knowledge base in real time, without vector… | 81 | 1333 | active |
| anyme123/Any-code Any Code is a cross-platform desktop GUI application (built with Tauri, React, and Rust) that wraps AI coding CLIs like Claude Code, OpenAI… | 64 | 1331 | active |
| uluckyXH/OpenMOSS OpenMOSS is a self-hosted multi-agent collaboration platform that organizes AI agents (built on OpenClaw/Claude Code) into an autonomous 'A… | 64 | 1331 | active |
| open-gsd/gsd-pi GSD Pi is a local-first, terminal-based autonomous coding agent that plans, implements, verifies, and tracks project work using spec-driven… | 82 | 1330 | active |
| AutumnWhj/ChatGPT-wechat-bot A WeChat bot that connects to ChatGPT/OpenAI's API so your WeChat account can reply to messages with AI-generated answers. It supports priv… | 50 | 4715 | maintenance |
| aws-samples/bedrock-chat Bedrock Chat (BrChat) is a multilingual generative AI chat platform built on Amazon Bedrock, deployable via AWS CDK. It supports chat, cust… | 96 | 1324 | active |
| AgentKit AgentKit is Coinbase Developer Platform's framework- and wallet-agnostic toolkit that gives AI agents a crypto wallet and the ability to pe… | 66 | 1324 | active |
| Fugtemypt123/VIGA VIGA is an analysis-by-synthesis code agent that reconstructs 3D scenes and slide layouts from images by generating and executing Blender P… | 51 | 1323 | active |
| utkusen/sast-skills A collection of LLM agent skills that turn coding assistants like Claude Code, Codex, Opencode, and Cursor into a SAST (static application … | 46 | 1322 | active |
| coollabsio/jean Jean is a local-first desktop application (built with Tauri, React, and Rust) that provides a unified workspace for managing multiple codin… | 78 | 1321 | active |
| ConardLi/easy-llm-cli Easy LLM CLI is an open-source command-line AI agent forked from Gemini CLI that works with multiple LLM providers, including Gemini, OpenA… | 45 | 1319 | active |
| LiteLLM-Labs/litellm-agent-control-plane LiteLLM Agent Control Plane is a self-hosted platform that provides one unified API and UI for creating and running AI agents across multip… | 59 | 1318 | active |
| evilsocket/nerve Nerve is a simple Agent Development Kit (ADK) for building, running, evaluating, and orchestrating LLM-based agents using YAML definitions … | 10 | 1318 | active |
| run-bigpig/jcp JCP (韭菜盘) is a cross-platform desktop application built with Wails, Go, and React that provides AI-driven analysis of Chinese A-share stock… | 10 | 1318 | active |
| tsinghua-fib-lab/AgentSociety AgentSociety is an LLM-native agent simulation framework for building large-scale multi-agent simulations of social and urban environments.… | 86 | 1317 | active |
| moazbuilds/claudeclaw ClaudeClaw is a lightweight, open-source Claude Code plugin that turns Claude Code into an always-on personal assistant daemon. It executes… | 54 | 1317 | active |
| darwin-lau/langmanus LangManus is a community-driven Python framework for building hierarchical multi-agent AI automation systems, where a supervisor coordinate… | 22 | 1317 | active |
| SanMuzZzZz/LuaN1aoAgent LuaN1aoAgent is an autonomous AI-driven penetration testing agent built in TypeScript on the Pi SDK, using graph-based cognitive reasoning … | 77 | 1316 | active |
| HugeCatLab/ChatTutor ChatTutor is a visual and interactive AI tutoring application that gives LLMs the ability to teach on an electronic whiteboard. It combines… | 49 | 1315 | active |
| wild-card-ai/agents-json agents.json is an open specification built on OpenAPI that formally describes contracts for API and agent interactions, translating OpenAPI… | 36 | 1315 | active |
| LangChat/langchat LangChat is a Java-based enterprise AIGC platform for building AI knowledge bases, chatbots, and agent applications with multi-provider LLM… | 67 | 1313 | active |
| steipete/claude-code-mcp An MCP server that wraps the Claude Code CLI in one-shot mode, exposing a single claude_code tool so any MCP client (e.g. Cursor, Claude De… | 10 | 1313 | active |
| dohooo/helmor Helmor is an open-source, local-first desktop workbench for orchestrating multiple AI coding agents in parallel, each in its own isolated g… | 70 | 1309 | active |
| greyhaven-ai/autocontext Autocontext is a recursive self-improving harness that runs AI agents against evaluations, retains useful lessons, and produces traces, rep… | 60 | 1309 | active |
| pyang5166/gbro-collage-broll An agent skill that turns short voiceover lines into editorial halftone paper-collage B-roll videos using Gemini Omni Flash first/last-fram… | 51 | 1308 | active |
| DimiMikadze/orca Orca is an AI agent application for deep LinkedIn profile analysis that scrapes posts, comments, reactions, and interaction networks, then … | 76 | 1306 | active |
| libgdx/gdx-ai gdxAI is a Java artificial intelligence framework for game development, designed as a libGDX extension but usable independently. It provide… | 32 | 1305 | stable |
| minsight-ai-info/AI-Search-Hub AI Search Hub is an open-source Skill that aggregates native AI search capabilities from platforms like Gemini, Grok, Doubao, and Yuanbao i… | 47 | 1304 | active |
| zkat/big-brain big-brain is a Utility AI library for the Bevy game engine, written in Rust. It lets developers define data-driven AI behaviors for game en… | 10 | 1304 | active |
| neo4j/neo4j-graphrag-python The official Neo4j first-party Python library for building graph retrieval-augmented generation (GraphRAG) applications. It provides retrie… | 92 | 1303 | active |
| Puppyone Puppyone is a Git-native context drive for AI agents: a persistent, version-controlled file workspace with per-agent scoped permissions, ex… | 76 | 1301 | active |
| huangkiki/dailypaper-skills A set of Claude Code skills that automates a daily research paper pipeline: fetching new papers from HuggingFace Daily, Trending, and arXiv… | 60 | 1301 | active |
| datalayer/jupyter-mcp-server A Model Context Protocol (MCP) server that lets AI agents connect to, edit, and execute Jupyter Notebooks in real time. It supports STDIO a… | 82 | 1300 | active |
| Agentshire/Agentshire Agentshire is an OpenClaw/QClaw plugin that turns AI agents into living 3D NPCs inside a customizable low-poly game town. It combines a rea… | 59 | 1298 | active |
| cclank/news-aggregator-skill A Python-based agent skill that aggregates news from 44+ sources (tech, finance, AI, international) and generates AI-summarized daily brief… | 50 | 1297 | active |
| rinadelph/Agent-MCP Agent-MCP is a TypeScript framework for building coordinated multi-agent AI systems over the Model Context Protocol (MCP). It provides a pe… | 51 | 1295 | active |
| codefuse-ai/codefuse-chatbot CodeFuse-ChatBot is an open-source AI assistant for the software development lifecycle, combining a multi-agent scheduling framework with D… | 28 | 1295 | active |
| Xiangyue-Zhang/auto-deep-researcher-24x7 An open-source Python framework where LLM agents autonomously run deep learning experiments 24/7, covering hypothesis formation, code imple… | 50 | 1293 | active |
| huytieu/COG-second-brain COG is a self-evolving second brain built from markdown files, Git, and AI agent skills, with 33 skills, 10 agents (6 workers plus 4 read-o… | 83 | 1289 | active |
| ChesterRa/cccc CCCC is a Python-based multi-agent orchestrator that coordinates coding agents (Claude Code, Codex CLI, ChatGPT Web, Gemini CLI, and 13+ ot… | 81 | 1286 | active |
| AI-Builder-Club/skills A Claude Code plugin marketplace distributing skills for building 'loop engineers' — autonomous agents that trigger themselves, do work, ve… | 56 | 1283 | active |
| fatwang2/search2ai A proxy service that adds online search, news, and webpage summarization capabilities to any OpenAI-compatible LLM API via function calling… | 85 | 1281 | active |
| bug0inc/passmark Passmark is an open-source TypeScript library that extends Playwright to run end-to-end browser regression tests written in plain English. … | 58 | 1280 | active |
| gomate-community/TrustRAG TrustRAG is a configurable and modular Retrieval-Augmented Generation (RAG) framework in Python built around the principle of reliable inpu… | 50 | 1280 | active |
| kellyvv/PhoneClaw PhoneClaw is a mobile-native local AI agent framework that turns phones into on-device agent runtimes, running Gemma models via LiteRT and … | 71 | 1279 | active |
| jasperproject/jasper-client Client code for the Jasper voice computing platform, an open source platform for building always-on, voice-controlled applications. It prov… | 32 | 4515 | maintenance |
| openai/symphony Symphony is an open‑source orchestrator that turns project‑management boards into a control plane for AI coding agents. It spawns autonomou… | 79 | 27381 | experimental |
| openclaw/lobster Lobster is an OpenClaw-native workflow shell that turns skills and tools into typed, JSON-first pipelines with built-in approval gates and … | 84 | 1277 | active |
| wong2/weixin-agent-sdk A TypeScript SDK that bridges any AI agent backend into WeChat via a simple Agent interface, with QR-code login and a message loop. It also… | 48 | 1276 | active |
| pipeboard-co/meta-ads-mcp A Model Context Protocol (MCP) server that lets AI assistants like Claude, ChatGPT, Perplexity, and Cursor manage Meta Ads (Facebook/Instag… | 80 | 1275 | active |
| meniku/NPBehave NPBehave is an event-driven behavior tree library for building code-based AI in Unity 3D. It stays in its current state instead of re-trave… | 24 | 1275 | stable |
| ipa-lab/hackingBuddyGPT HackingBuddyGPT is a Python framework that helps ethical hackers and security researchers use LLMs and LLM-based autonomous agents for pene… | 66 | 1274 | active |
| aiming-lab/Agent0 Agent0 Series is a research framework for training self-evolving LLM agents from zero external data via tool-integrated reasoning and co-ev… | 55 | 1271 | active |
| microsoft/skills-for-fabric A collection of reusable AI assistant skills and MCP systems from Microsoft for working with Microsoft Fabric workloads, APIs, and Power BI… | 83 | 1270 | active |
| MiniMax-AI/OpenRoom VibeApps (OpenRoom) is a browser-based desktop environment with draggable windows and a suite of built-in apps, all controlled by an AI Age… | 50 | 1270 | active |
| math-inc/OpenGauss Open Gauss is a project-scoped workflow orchestrator that gives the `gauss` CLI a multi-agent frontend for Lean 4 theorem proving workflows… | 45 | 1270 | active |
| tembo/tembo Tembo is a cloud platform that runs coding agents (Claude Code, Codex, Cursor, etc.) across your repositories, tickets, and tools with full… | 75 | 1267 | active |
| TencentCloudADP/youtu-graphrag Youtu-GraphRAG is a Python framework for graph-based retrieval-augmented generation that unifies graph schema construction, community detec… | 52 | 1266 | active |
| NVIDIA-NeMo/Gym NeMo Gym is a Python library from NVIDIA for evaluating and improving LLM models and agents using environments. It provides infrastructure … | 81 | 1264 | active |
| SimonSchubert/Kai Kai 9000 is an open-source, cross-platform AI assistant built with Kotlin Multiplatform that runs on Android, iOS, Windows, Mac, Linux, and… | 81 | 1264 | active |
| hashgraph-online/standards-sdk The official HOL Standards SDK for TypeScript, providing reference implementations of Hashgraph Consensus Service (HCS) standards for file … | 87 | 1263 | active |
| CopilotKit/OpenTag OpenTag is an open-source, self-hosted knowledge-work AI agent for Slack and Microsoft Teams, built as the starter application for the Chan… | 78 | 1258 | active |
| plurai-ai/intellagent IntellAgent is a Python framework for diagnosing and optimizing conversational LLM agents through simulated, realistic synthetic user inter… | 55 | 1258 | active |
| AIPexStudio/AIPex AIPex is an open-source (MIT) AI browser automation assistant delivered as a Chrome/Edge extension that runs inside your existing browser w… | 75 | 1256 | active |
| grinev/opencode-telegram-bot A Telegram bot that acts as a secure mobile client for the OpenCode CLI, letting users run and monitor AI coding tasks from their phone whi… | 79 | 1254 | active |
| TIGER-AI-Lab/OpenResearcher OpenResearcher is a fully open-source pipeline for synthesizing long-horizon deep research trajectories using LLM agents with retrieval and… | 51 | 1254 | active |
| EmergenceAI/Agent-E Agent-E is an open-source agent-based system that automates actions on the user's computer, currently focusing on browser automation via na… | 58 | 1252 | active |
| ChristopherKahler/paul PAUL (Plan-Apply-Unify Loop) is a structured development framework for Claude Code that enforces a PLAN → APPLY → UNIFY cycle with acceptan… | 57 | 1251 | active |
| smixs/pohuy A prompt/skill package that makes AI agents respond in idiomatic Russian profanity, compressing verbose explanations into terse, expressive… | 75 | 1250 | active |
| RUC-NLPIR/Search-o1 Search-o1 is a research framework that enhances large reasoning models (like QwQ and R1) with agentic search and retrieval-augmented genera… | 41 | 1247 | active |
| openai/codex-action A GitHub Action that runs OpenAI's Codex CLI inside GitHub Actions workflows, installing the CLI and routing API calls through a secure pro… | 60 | 1246 | active |
| firecrawl/web-agent An open-source TypeScript framework for building autonomous web research agents, layered from a Next.js chat template down to an agent core… | 47 | 1246 | active |