Best Multi-Agent Top 20
Top 20 most popular open-source Multi-Agent projects, ranked by GitHub Stars.
agency-agents
121.0k StarsAgency Agents is a curated collection of specialized AI agent personas with prompts, tools, and best practices for assembling multi-agent teams.
Awesome LLM Apps
116.2k Stars100+ AI Agent and RAG apps you can actually run — clone, customize, and ship. A great reference for quickly building LLM-powered applications.
MoneyPrinterTurbo
94.5k StarsGenerate short videos with one click using AI LLM. Multi-step automation workflow from script generation to video composition.
TradingAgents
90.0k StarsTradingAgents is a multi-agent trading framework built with LangGraph that mirrors real-world trading firm dynamics with specialized LLM-powered agents for fundamental analysis, sentiment analysis, risk management, and more.
OpenHands
78.9k StarsOpenHands is an open-source AI software engineering agent platform that can automatically execute development tasks, modify code, and support collaborative iteration.
MetaGPT
69.1k StarsThe Multi-Agent Framework for building the first AI Software Company, enabling natural language programming with multi-role collaboration for automated requirement analysis, design, coding, and testing.
MetaGPT
69.1k StarsMetaGPT is a multi-agent framework that combines collaborative intelligence with software-engineering SOPs so agents cooperate like a real software company to ship code and docs.
MetaGPT
69.1k StarsMulti-agent framework that encodes a software company's org chart into LLM workflows to auto-produce code.
MetaGPT
69.1k StarsOpen-source framework that orchestrates multi-agents as a software company.
MiroFish
67.6k StarsMulti-agent swarm intelligence engine that extracts seed information from the real world, constructs a high-fidelity parallel digital world with thousands of agents, and predicts future trajectories through social evolution simulations.
Ruflo
62.3k StarsThe leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, distributed swarm intelligence, RAG integration, and native Claude Code/Codex integration.
AutoGen
59.4k StarsMicrosoft AutoGen is a multi-agent conversation framework that lets you create multiple agents to collaborate through dialogue and solve complex tasks.
AutoGen
59.4k StarsMicrosoft Research's open-source multi-agent programming framework.
CrewAI
54.6k StarsCrewAI is a multi-agent framework for orchestrating role-playing, autonomous AI agents that collaborate like a team to tackle complex tasks.
CrewAI
54.6k StarsRole-based multi-agent Python framework for task orchestration.
CrewAI
54.6k StarsA multi-agent collaboration framework where AI agents form crews to accomplish complex tasks together. Role definition, task assignment, tool sharing, and process orchestration.
CrewAI
54.6k StarsA multi-agent collaboration framework where AI agents form crews to accomplish complex tasks together. Role definition, task assignment, tool sharing, and process orchestration.
CowAgent
45.7k StarsCowAgent (formerly chatgpt-on-wechat) is a powerful AI assistant framework built on LLMs with autonomous planning, tool use, long-term memory, multi-agent collaboration, and multi-channel integration for WeChat, Feishu, DingTalk, and more.
BettaFish
41.6k StarsAn accessible multi-agent sentiment analysis assistant that breaks filter bubbles, reveals true public opinion, and predicts trends — built from scratch without external frameworks.
Agents
37.4k StarsIntelligent automation and multi-agent orchestration for Claude Code. Supports automated workflows, task coordination, and intelligent agent system building.
Related Articles
Agent Tool-Call Fault Tolerance: Timeouts, Retries, Fallbacks, Idempotency
A systematic guide to seven tool-call fault tolerance patterns: timeout hierarchy, exponential backoff with jitter, circuit breakers, fallback provider chains, recoverable error classification, structured validation, and idempotency keys -- keeping agents stable in unstable real-world environments.
Agent Workflow Orchestration in Practice: Production Patterns from DAG to State Machines
Most agent workflows fail at the orchestration layer, not the model. A practical comparison of DAG, state machine, and visual builder approaches with production-ready code for error handling, human approval gates, and conditional branching.
2025 AI Agent Framework Selection Guide
An in-depth comparison of mainstream AI agent frameworks including LangChain, LangGraph, CrewAI, and AutoGen to help you choose the best development stack.