Awesome Agent Orchestration
English | 中文
The most comprehensive curated list of Agent Orchestration, Multi-Agent Systems, Swarm Intelligence, and LLM Agent frameworks. Includes AutoGen, CrewAI, MetaGPT, LangGraph, Swarms, A2A Protocol, MCP Protocol and more.
⭐ Star this repo if it helps you find AI Agent frameworks!
What is Agent Orchestration?
Agent Orchestration is the practice of coordinating multiple AI agents (LLM agents, autonomous agents) to work together on complex tasks. It enables:
Scalability : Handle complex workflows by distributing tasks across specialized agents
Specialization : Each agent can focus on a specific domain or task
Robustness : Fault tolerance through agent redundancy and recovery
Emergent Capabilities : Complex behaviors arising from simple agent interactions
Real-World Applications : From software development to research automation
Multi-Agent System (MAS) : A system composed of multiple interacting intelligent agents
Swarm Intelligence : Collective behavior emerging from simple agent interactions
Agentic AI : AI systems that can autonomously plan and execute complex tasks
Agent Communication Protocol : Standards like A2A (Agent-to-Agent) and MCP (Model Context Protocol) for agent interoperability
Multi-Agent Orchestration Frameworks
Project
Description
Stars
AutoGen
Microsoft's framework for building multi-agent conversational systems
CrewAI
Role-based multi-agent framework for building AI teams
MetaGPT
Multi-agent framework for software development with role assignment
agentUniverse
Enterprise-level multi-agent framework
Langroid
Multi-agent programming framework with message-passing
Phidata
Multi-modal agent framework with built-in tools and UI
OpenAgents
Open platform for deploying language agents
AgentVerse
Platform for running multiple LLM agents in simulated environments
agency-swarm
Reliable multi-agent orchestration framework
OpenAI Swarm
Educational lightweight multi-agent orchestration framework
Microsoft Agent Framework
Framework for building, orchestrating and deploying AI agents
OpenAI Agents Python
Lightweight powerful framework for multi-agent workflows
Haystack
Open-source AI orchestration for context-engineered LLM applications
LLMStack
No-code multi-agent framework for LLM agents and workflows
LazyLLM
Easiest way for building multi-agent LLM applications
MindSearch
LLM-based multi-agent framework for web search engine
TradingAgents
Multi-agent LLM financial trading framework
Shannon
Production-oriented multi-agent orchestration framework
Solace Agent Mesh
Event-driven framework for multi-agent AI systems
Pipelex
Declarative language for composable AI workflows
CodeFuse-muAgent
Innovative agent framework driven by KG Engine
L2MAC
LLM Automatic Computer Framework
Patchwork
Agentic AI framework for enterprise workflow automation
Swarm Intelligence Frameworks
Project
Description
Stars
Swarms
Production-grade multi-agent infrastructure platform
Swarm
Lightweight multi-agent orchestration framework
Swarm-Tools
Tool for coordinating AI agents with learning capabilities
Ruflo
Leading agent orchestration platform for Claude
swarms-rs
Enterprise-grade multi-agent orchestration in Rust
Lux
Open-source framework for multi-agent swarmed intelligence
AutoRT
Embodied foundation models for robotic agents
Graph-Based Workflow Frameworks
Project
Description
Stars
LangGraph
Build stateful multi-agent applications with LangChain
LangChain
Modular framework for LLM application chaining
LlamaIndex
Data-centric agent framework for RAG
Semantic Kernel
Microsoft orchestration SDK for .NET/Python
Lightweight & Specialized Agents
Project
Description
Stars
SmolAgents
Minimalist library for code-writing agents
Auto-GPT
Pioneering autonomous agent with self-prompting
BabyAGI
Simple autonomous task management
GPT-Engineer
Agent for generating full projects from specs
BMTools
Tool/API registry for agents
Type-Safe & Modern Frameworks
Project
Description
Stars
PydanticAI
Type-safe agent framework using Pydantic models
DeepAgents
Production-grade autonomous agents on PydanticAI
Subagents
Subagent delegation framework for PydanticAI
Flux0
Multi-agent deployment framework with session management
Mamba Agents
Simple extensible AI Agent framework
TypeScript & Node.js Frameworks
Project
Description
Stars
openai-swarm-node
Node.js implementation of OpenAI's Swarm framework
Network-AI
TypeScript/Node multi-agent orchestrator with shared state
megazord
Claude Code framework for multi-agent coordination
Voltmachines
Multi-agent framework built on VoltAgent
agent-swarm-kit
TypeScript library for framework-agnostic multi-agent systems
ai-orchestra
Lightweight orchestration for AI Agents around Vercel's streamText
Project
Description
Stars
openai-agents-go
Lightweight powerful framework for multi-agent workflows in Go
swarm-go
Ergonomic lightweight multi-agent orchestration in Go
rs-graph-llm
High-performance framework for interactive multi-agent workflows in Rust
Swift, Ruby & Elixir Frameworks
Project
Description
Stars
SwiftSwarm
Swift framework for lightweight multi-agent orchestration
Swarm
Lightweight agent orchestration framework in Swift
ruby-openai-swarm
Ruby-based framework for multi-agent orchestration
swarm_ex
Elixir library for lightweight AI agent orchestration
shifts
Elixir framework for composing autonomous AI agent workflows
Project
Description
Stars
neuron-ai
PHP agentic framework for production-ready AI applications
swarm-ai
Java multi-agent orchestration with Spring AI
Workflow & Pipeline Frameworks
Project
Description
Stars
circuit
Drag-and-drop agent workflow builder
routilux
Event-driven workflow orchestration for Python
CraftFlow
Workflow orchestration for RAG and multi-agent collaborations
sentinels
Laravel package for agent-based task orchestration
titan-orchestrator
Distributed orchestrator bridging DevOps and Agentic AI
Agent Communication Protocols
Google's A2A protocol enables secure, interoperable communication between autonomous agents across frameworks and vendors.
Project
Description
Stars
awesome-a2a-agents
Curated list of A2A tools and frameworks
python-a2a
Python implementation of A2A protocol
a2a-net
.NET implementation of A2A protocol
a2a-langgraph
A2A protocol built on LangGraph
nestjs-a2a
NestJS library for A2A protocol
a2a4j
Java implementation of A2A protocol
A2A-MCP-Server
Bridge between MCP and A2A protocols
a2a-x402
A2A protocol with cryptocurrency payments
Routa
Multi-agent coordination platform via MCP/A2A
mangaba_ai
Minimalist AI agents with A2A and MCP
Model Context Protocol (MCP)
An open protocol that enables seamless connection between AI models and external tools/data sources. MCP is becoming the standard for tool-augmented LLM applications.
In hierarchical orchestration, a supervisor agent delegates tasks to specialized sub-agents. This pattern is suitable for complex tasks requiring domain expertise.
Use Cases : Software development teams, research automation, enterprise workflows
Frameworks : AutoGen, CrewAI, LangGraph
Sequential workflows process tasks through a pipeline where each agent completes its step before passing to the next.
Use Cases : Document processing, data transformation pipelines
Frameworks : LangChain, LangGraph
Multiple agents work simultaneously on independent subtasks, with results aggregated afterward.
Use Cases : Research gathering, parallel code generation
Frameworks : Swarms, AutoGen
Multiple expert agents contribute their perspectives, with outputs combined through iterative refinement.
Multiple agents discuss and debate to reach consensus on decisions.
Use Cases : Decision making, complex analysis, creative writing
Framework : AutoGen GroupChat
Communication & Coordination
Langroid : Message-passing based multi-agent framework
AutoGen : Conversational message passing
Shared State / BlackBoard Systems
Swarm Matcher : Agent matching and selection
Message Pool : Shared communication system
Auto Swarm : Self-organizing swarm with automatic task distribution
Agent Delegation : Task delegation and management
Multi-Agent Collaboration
Memory & Long-Term Autonomy
Tool
Description
Langfuse
Open-source LLM engineering platform
Phoenix
Open-source LLM tracing
Opik
Open-source LLM evaluation
Agenta
LLMOps platform for prototyping
Logfire
Pydantic's open-source observability tool
Langtrace
Open-source observability for AI agents
Okahu Monocle
Tracing framework by Linux Foundation
Tool
Description
Memori
SQL Native Memory Layer for LLMs & Agents
Letta
Memory layer for AI agents
Deployment & Infrastructure
Evaluation & Benchmarking
Tool
Description
AgentBench
Evaluates agents across diverse environments
swarms-evals
Evaluation framework for swarm systems
RAGAS
Evaluation framework for RAG systems
Contributions are welcome! Please read the contributing guidelines first.
Fork the repository
Add your resource in the appropriate section
Ensure consistent formatting
Submit a pull request
Popular search terms: AI Agent Framework, Multi-Agent System, Agent Orchestration, Swarm Intelligence, LLM Agent, Claude AI, OpenAI Agents, CrewAI, AutoGen, MetaGPT, LangGraph, Agent Communication Protocol, A2A Protocol, MCP Protocol, Agentic AI, Autonomous Agents, Agent Workflow, AI Automation
AutoGen - Microsoft's multi-agent framework
CrewAI - Role-based multi-agent framework
MetaGPT - Software development multi-agent framework
LangGraph - State-based agent workflow
Swarms - Production-grade multi-agent platform
To the extent possible under law, Your Name has waived all copyright and related rights to this work.
Star this repository if you find it useful!