Updated October 2026
An AI agent is a program that uses a language model to plan a task, call tools such as a browser, a shell, or an API, and keep going until the job is done. Open source agents let you read the code, run them on your own machines, and swap in any model, including local ones.
This list covers both ready-to-use agents and the frameworks for building your own, from single-agent loops to multi-agent teams. Every project is licensed, actively maintained, and ranked by GitHub stars.
Ranked by GitHub stars and refreshed daily.
by NousResearch
The agent that grows with you
by langchain-ai
The agent engineering platform.
by browser-use
Open-source Python library for AI browser agents, plus Browser Use Cloud: stealth browsers and a hosted agent API.
by google-gemini
An open-source AI agent that brings the power of Gemini directly into your terminal.
by bytedance
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
by ruvnet
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, fe…
by FoundationAgents
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
by mem0ai
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
by Mintplex-Labs
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
by microsoft
A programming framework for agentic AI
by crewAIInc
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
by aaif-goose
an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
by zhayujie
Open-source personal 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-…
by langchain-ai
Build resilient agents.
by agno-agi
Build, run, and manage agent platforms.
by 666ghj
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。
by CopilotKit
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
by agentscope-ai
Build and run agents you can see, understand and trust.
by topoteretes
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
by feder-cr
Open-source, self-hosted alternative to OpenAI Dots, Grok Bot. Built to be undetectable by anti-bot systems.
By GitHub stars, the most popular projects on this list right now are hermes-agent, langchain, and browser-use. The ranking is rebuilt every day from GitHub.
An agent is an app you run to get work done, like a research or browser agent. A framework, such as LangGraph, CrewAI, or AutoGen, is a library for building your own agents: it handles planning loops, tool calls, memory, and handing work between several agents.
Most of them can. Agents that accept an OpenAI-compatible API work with local runtimes such as Ollama, llama.cpp, or vLLM, so prompts and data never leave your machine. Check each project's docs for the models it supports.
