Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 3 of 62

orchestra★ 764

Cognitive Architectures for Multi-Agent Teams

swarm-tools★ 754

🐝 Multi-agent swarm coordination for OpenCode with learning capabilities, agent issue tracking, and management

clawe★ 751

Multi-agent coordination system: think Trello for OpenClaw agents.

arbiter★ 750

Multi-agent framework for design, simulation, and auditing.

hermes-agent-control-room★ 748

Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows

pi-messenger★ 748

Multi-agent communication extension for pi coding agent

hermes-agent-control-room★ 740

Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows

the-delegation★ 735

A no-code 3D playground to explore, design, and interact with Agentic AI systems

cocoplus★ 729

CocoPlus is an Agentic Operating System for Snowflake Coco. It brings structured, multi-agent workflows to data engineering projects — covering everything from project initialization through spec, plan, build, test, review, and ship phases.

langgraph-mcp-agents★ 720

LangGraph-powered ReAct agent with Model Context Protocol (MCP) integration. A Streamlit web interface for dynamically configuring, deploying, and interacting with AI agents capable of accessing various data sources and APIs through MCP tools.

wanman★ 720

wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.

pilotfish★ 718

Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verification guards quality. One-prompt install.

swarmclaw★ 710

Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.

pytorch-maddpg★ 692

A pytorch implementation of MADDPG (multi-agent deep deterministic policy gradient)

MADDPG★ 683

Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".

Emergence-World★ 679

Emergence World: A world designed to reveal what no benchmark can: emergent intelligence.

sympozium★ 675

The Coordination Layer for Multi-Agent AI

hcom★ 665

Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Cursor CLI, OpenCode, Kilo, Pi, Kimi

openswarm★ 662

Your mission control center for a swarm of Ai agents.

openclaw-office★ 651

OpenClaw Multi-Agent 系统的可视化监控与 Skills 开发平台。将 AI 聊天机器人进化为可编程的 Skills 系统——创建、开发、调试和部署可复用的技能,搭配实时虚拟办公室仪表盘监控 Agent 协作。

ccteam★ 648

ccteam turns the coding agents you already run (Claude Code, Codex, Grok, DeepSeek Harness, Kimi, Pi) into one team — any session can spawn, dispatch, and collect work from any vendor on any machine, while you steer it all from Telegram, Lark, or a browser tab. 把你在用的编程 agent 编成一支团队,跨厂商跨机器派活,Telegram/飞书/网页统一指挥。

brainstormers★ 642

This repository hosts a suite of specialized agents designed to power your brainstorming sessions. Each agent brings a unique perspective and tailored approach to generate creative, targeted solutions for diverse challenges. Choose the right agent for your specific brainstorming needs and unlock innovative ideas with precision.

EvoFlow★ 642

进化的工作流 · 由 EvoFlow 研发部 AI 员工持续迭代自我进化 · 智能体员工。官网 www.evovexai.com

klaw.sh★ 635

kubectl for AI Agents

Multi-Agents-Debate★ 624

MAD: The first work to explore Multi-Agent Debate with Large Language Models :D

boss-skill★ 623

Boss Skill - BMAD 全自动研发流水线(多 Agent 编排)

openai-assistant-swarm★ 618

Introducing the Assistant Swarm. An extension to the OpenAI Node SDK to automatically delegate work to any assistant you create in OpenAi through one united interface and manager. Now you can delegate work to a swarm of assistant all specialized with specific tasks you define.

RSIAgent★ 617

A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.

claw-orchestrator★ 616

Run Claude Code, Codex, Antigravity, Grok Build and OpenCode behind one runtime, and a run only counts as done when checks it didn't write pass. Cross-engine fan-out, councils, session handoff, spend caps, MCP server, ACP agent.

Maze★ 608

A distributed framework for LLM agents

graphbit★ 596

GraphBit is the world’s first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.

hive★ 595

Browser-native hive-mind for CLI coding agents — Claude Code, Codex, Gemini, and OpenCode collaborate as real PTY processes via a team protocol.

dontbemichael★ 595

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

openteams★ 593

Plan, Build, and Ship — with a team of AI agents instead of one

opencode-workspace★ 584

Bundled multi-agent orchestration harness for OpenCode. One install, complete control.

maestro-flow★ 577

Intent-driven workflow orchestration for multi-agent AI development — adaptive lifecycle engine, self-reinforcing knowledge graph, and visual dashboard for Claude Code, Gemini, Codex & more

Agent-Kernel★ 576

A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs

MARTI★ 575

[ICLR 2026] A Framework for LLM-based Multi-Agent Reinforced Training and Inference

ISEK★ 572

A decentralized agent network for building collaborative, LLM-powered agent-to-agent (A2A) systems.

Avernet★ 571

Distributed agent coordination platform where agents live, connect, coordinate, execute, and evolve together.

MASFactory★ 567

A Graph-Centric Framework for Orchestrating Multi-Agent Systems with Vibe Graphing.

open-multi-agent-canvas★ 565

The open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research

amux★ 565

The agent control plane: run Claude Code, Codex and Gemini CLI agents in parallel with a shared task board, schedules and usage-limit recovery. Native iPhone, iPad and Mac apps plus a web dashboard. Self-host (Rust + SQLite, Tailscale remote access) or use amux Cloud. MIT + Commons Clause.

llm_multiagent_debate★ 559

ICML 2024: Improving Factuality and Reasoning in Language Models through Multiagent Debate

Aurogen★ 548

"Aurogen🍊: The Multi-Agent Evolution of OpenClaw."

fastagency★ 546

The fastest way to bring multi-agent workflows to production.

GenerativeAgentsCN★ 546

本项目为Generative Agents项目的重构+深度汉化版本,旨在为中文用户提供一个利于维护的基础版本,以便后续实验或功能拓展。

runner★ 542

Where terminal agents work together. Claude Code, Codex, Copilot CLI and pi on the same task, in one mission, each keeping its own TUI in a real terminal.

opencode-swarm★ 537

Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.

Multi-Agent-Transformer★ 524
a2a-java★ 515

Official Java SDK for the Agent2Agent (A2A) Protocol

mateclaw★ 514

🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.

agent-kanban★ 506

An agent-first task board, Take human out of the loop.

conductor★ 506

A CLI tool for defining and running multi-agent workflows with the GitHub Copilot SDK and Anthropic Agents SDK.

hermes-multi-agent-workflow★ 505
GoBigger★ 504

[ICLR 2023] Come & try Decision-Intelligence version of "Agar"! Gobigger could also help you with multi-agent decision intelligence study.

SOMAS★ 502

A Trusted Human-Multi-Agent Reinforcement Learning Interaction Framework

warp-drive★ 502

Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU (JMLR 2022)

gobii-platform★ 500

Your easy to use, always-on AI workforce 👾

BookWorm★ 498

The practical implementation of Aspire using Microservices, AI-Agents

opencrew★ 498

Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack,让 AI 团队各司其职、自主稳定迭代。

agentspan★ 498

Agentspan is now part of Orkes Conductor

ard-spec★ 498

Agentic Resource Discovery (ARD) specification

a2a-inspector★ 494

Validation Tools for A2A Agents

flink-agents★ 494

Flink Agents is an Agentic AI framework based on Apache Flink

multi-agent★ 491

A multi-agent travel assistant system built using the **Agent2Agent (A2A)** protocol and **MCP (Model Context Protocol)**

claude-swarm★ 490

Multi-agent orchestration for Claude Code — decompose tasks, coordinate agents, visualize everything in a rich terminal UI

ai-agency-agents★ 490

Open Agency is an open-source AI workforce featuring specialized agents for development, growth, research, strategy, and creativity. Each agent is designed to deliver practical results through focused expertise and structured workflows.

maestro-orchestrate★ 489

Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parallel subagents, persistent sessions, and built-in code review, debugging, security, SEO, accessibility, and compliance tools

pi-interactive-subagents★ 483

Interactive subagents for pi — spawn, orchestrate, and manage sub-agent sessions in cmux terminals

azure-ai-travel-agents★ 483

A robust enterprise application sample (deployed on ACA) that leverages MCP and multiple AI agents orchestrated by Langchain.js, Llamaindex.TS and Microsoft Agent Framework.

dragonclaw★ 483

Dragonclaw: Maybe the best openclaw client. Built with Electron+SQLite, it doesn't touch OpenClaw's code but adds multi‑agent, high‑concurrency, DAG workflows. No prompt tuning needed (pre‑optimized). One‑click install with built‑in cloud service (replaceable).

mahilo★ 482

mahilo: Multi-Agent Human-in-the-Loop Framework is a flexible framework for creating multi-agent systems that can each interact with humans while sharing relevant context internally.

registry-broker-skills★ 480

AI agent skills for the Universal Registry - search, chat, and register 72,000+ agents across 14+ protocols. Works with Claude, Codex, Cursor, OpenClaw, and any AI assistant.

openclaw-enterprise★ 480

The Enterprise-grade Control Plane for modern agentic workloads

Puppetmaster★ 478

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

OneManCompany★ 474

Build Your Agent Company with OMC

AgileCoder★ 467

[FORGE 2025] Incorporating Agile methodology into agents to create complex real-world softwares

registry★ 467

Registry of agents implementing the Agent Client Protocol (ACP)

agent-host-protocol★ 464

Synchronized multi-client state for AI agent sessions

openagents★ 463

Agents 2.0

cohub★ 463

A living space where people and agents create, play, and build together.

WarAgent★ 461

WarAgent: LLM-based Multi-Agent Simulation of World Wars

Multi-agent-RL★ 458

Projects from basic algorithms to MARL. Implements MADDPG,MATD3,MA/HAPPO in Predator-Prey pursuit games with PettingZoo MPE environments.

evolving-agents★ 458

A director agent that learns how your team works: it plans by walking your CLAUDE.md and memory as linked statements, delegates to Claude Code or local models, and keeps each lesson as a gated, versioned patch. Measured: 0.929 vs 0.589.

openclaw-agents★ 457

🐾 One-command multi-agent setup for OpenClaw — 9 specialized AI agents, group routing, safe config merge.

research-agents-3.0★ 456

Autogen + GPTs - build a swarm AI researchers

TabTin★ 456

A workspace where people and multiple AI agents work together.

Hojo-AgenticOS★ 454
evolving-agents★ 453

Your toolkit for autonomous, evolving agent ecosystems. Create, execute, govern, and evolve agents that learn from experience, collaborate, build new capabilities, and operate safely within defined guardrails.

vexjoy-agent★ 451

VexJoy AI Agent with Jev Intelligent Routing - /do routes plain-English requests to the right specialist agent and gates the work with reviews, tests, and a learning loop.

deeprl_network★ 450

multi-agent deep reinforcement learning for networked system control.

team-tasks★ 448

Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration

multi-agent-concierge★ 447

An example of multi-agent orchestration with llama-index

OpenStory★ 445

An LLM-powered multi-agent framework for simulating interactive, evolving story worlds.

pi-dash★ 444

AI Agent Orchestration Platform

Operant★ 444

Operant Beta:以多模型分工、按需通信、分层审批和经验复用为核心设计,在本机组织可追溯的 Agent 协作,并通过模块化架构扩展能力。

tucano★ 438

Your team of AI agents, on your Mac, Windows or Linux. Agents that talk in channels, write code, review each other and use your tools, on the Claude Code, Codex, OpenCode or Pi you already have. Anything that touches the real world waits for your yes.

agent-bridge★ 434

A local bridge for bidirectional collaboration between Claude Code and Codex. 连接 Claude Code 与 Codex 的本地实时协作桥接工具。

safe-agentic-workflow★ 431

SAW — SAFe Agentic Workflow AI Agent Harness for Multi-Agent Team Workflows Built on SAFe methodology (Scaled Agile Framework), adapted for AI agent teams (Now With AI-DLC!) Works for any team with repeatable processes: Software, Marketing, Research, Legal, Operations.

More in Agent frameworks & infrastructure