HomeExploreMulti-Agent Frameworks
🕸️

Orchestrate networks of AI agents

Multi-agent frameworks let you wire multiple LLM-powered agents into pipelines, graphs, or crews — each with its own role, memory, and tools. They are the backbone of production agentic systems.

23 frameworks trackedLive dataBrowse all →

Top Multi-Agent Frameworks

Ranked by GitHub stars

See all →
ECC
ActiveJavaScript
90

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

framework
201.9k
AutoGPT
ActivePython
90

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.

framework
184.7k
hermes-agent
ActivePython
85

The agent that grows with you

framework
176.2k
JavaGuide
ActiveJavaScript
85

Java 面试 & 后端通用面试指南,覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

framework
156.0k
open-webui
ActivePython
85

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

framework
139.6k
langchain
ActivePython
85

The agent engineering platform.

framework
138.3k
firecrawl
ActiveTypeScript
85

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

framework
127.2k
gemini-cli
ActiveTypeScript
90

An open-source AI agent that brings the power of Gemini directly into your terminal.

framework
104.8k
awesome-mcp-servers
Active
85

A collection of MCP servers.

framework
88.3k

Recently updated

Active development · pushed in the last 30 days

See all →
hermes-webui
ActivePython
77

Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!

framework
11.6k
lobehub
ActiveTypeScript
90

🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.

framework
78.1k
nacos
ActiveJava
90

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

framework
33.0k
ruflo
ActiveTypeScript
90

🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration

framework
57.3k
oh-my-pi
ActiveTypeScript
82

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

framework
9.5k
kong
ActiveLua
85

🦍 The API and AI Gateway

framework
43.5k
byterover-cli
ActiveTypeScript
76

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

framework
4.8k
ToolUniverse
ActivePython
71

Democratizing AI scientists with ToolUniverse

framework
1.4k
nanobot
ActivePython
85

Lightweight, open-source AI agent for your tools, chats, and workflows.

framework
43.5k

Frequently asked questions about Multi-Agent Frameworks

What is a multi-agent framework?+
A multi-agent framework provides primitives for defining, composing, and running multiple LLM-powered agents that collaborate to solve complex tasks. Examples include LangGraph, CrewAI, AutoGen, and Smolagents.
What is the best multi-agent framework in 2025?+
LangGraph leads production deployments (18k+ stars, used by Replit and LinkedIn). CrewAI is the fastest path to a working crew of agents. AutoGen is best for research and human-in-the-loop scenarios.
LangGraph vs CrewAI — which should I use?+
LangGraph offers fine-grained control via a state machine graph — ideal for production workflows with complex branching. CrewAI is higher-level and faster to prototype with, but less flexible for edge cases.
Can I use multi-agent frameworks without LangChain?+
Yes. AutoGen, Smolagents, and OpenAI Agents SDK are framework-agnostic. LangGraph can also run standalone without the rest of the LangChain ecosystem.

Explore related categories

💻Coding Agents📚RAG & Retrieval📊LLM Observability