Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 21 of 62

charter★ 18

Control plane for your harness across many repos — durable personas, per-task workspaces, and a credential vault the model never reads from

chat-system★ 18

多模型协作与智能辩论平台 — Multi-Agent 并行工作流 + RAG + 知识图谱,让多个 AI 像专家团队一样辩论、推理、共创

Xpro★ 18

A runnable multi-agent process with a built-in evaluation system — repeated rollouts scored on the git diff, not the agent's self-report. OpenAI & Anthropic.

clayrune★ 18

Open-source mission control for running multiple Claude Code agents across projects - one dashboard, a scheduler, cross-session memory, and browser/phone access. Runs locally on your own Claude subscription (the CLI, not the API). MIT, local-first.

rind★ 18

Folders are agents. Lightweight multi-agent collaboration, built around your workspaces.

orchvia★ 18

Run Claude Code and Codex agents as a team: long-lived sessions, a durable mailbox, human approval gates and per-task token accounting, scheduled by code rather than a manager LLM.

collab-a2a★ 18

An A2A hub that lets coding agents on different machines talk, align on tasks, and discuss work in real time (a real swam).

actor4j★ 18

Actor4j extension libraries — built to enhance the core implementation.

AgentCouncil★ 18

🏛️ Autonomous Multi-Agent CLI Orchestrator — Bring Claude Code, OpenAI Codex, Cursor Agent, xAI Grok & Google Antigravity into one terminal council to plan, code, cross-review, test, and deploy.

opendot★ 18

Local-first desktop app for AI agent teams. Runs with Ollama or cloud models. Mac + Windows.

slm-mesh★ 17

Peer-to-peer communication for AI coding agents. 8 MCP tools, full CLI, Python client. Part of the Qualixar research initiative by Varun Pratap Bhardwaj.

midtown★ 17

A human-scale interface for multi-agent development

RaccoonClaw★ 17

Multi-agent collaboration workbench for OpenClaw with task orchestration, monitoring, and agent configuration.

beer-game-env★ 17

Beer Game implemented as an OpenAI gym environment.

pluto★ 17

Pluto is a high-performance coordination server built on Erlang/OTP that enables safe, real-time collaboration between multiple AI agents.

strands-a2a-demo★ 17

Demo with multiple AI agents using A2A (agent-to-agent) with the Strands Agents SDK.

autogen_blueprint★ 17

This is the official companion repository for 'The Complete AutoGen AI Agent Blueprint: Developers Guide To Building Multi Agent AI Systems' book. Includes comprehensive code examples, practical implementations, and resources for building multi-agent AI systems using Microsoft's AutoGen framework.

streamlit-agents-sdk-example★ 17

Multi-agent chat powered by openai-agents-sdk and Streamlit

heisenberg-team★ 17

Production-ready multi-agent AI system: 8 specialized agents with self-healing, crash recovery, and Board-First coordination. Built on OpenClaw. Supports Anthropic, OpenAI, Google, DeepSeek, Ollama.

MultiAgentPathFinding.jl★ 17

Structures and algorithms for Multi-Agent PathFinding in Julia

opinion_game★ 17

Multi-agent coordination using game theory and nonlinear opinion dynamics - CDC 2023

autonomous-agents★ 17

Production multi-agent system: 4 AI agents coordinate via stigmergy. Claude API. 80% token reduction.

spec★ 17

🦆📜 A minimal, deterministic, runtime-agnostic DSL for orchestrating workflows through declarative YAML specs.

multi-agent-orchestration-workshop★ 17

This is a workshop material to build multi-agent orchestration patterns using Microsoft Agent Framework, Microsoft Foundry and Aspire. 👉 https://aka.ms/agentframework/workshop/multiagent

unicorn-hub★ 17

Portable multi-agent development blueprint for spec-driven, PR-gated software delivery.

Team_Agents★ 17

Multi-agent AI system. Autonomous agents coordinating task execution, decision routing, and workflow orchestration using LangChain and LLM Model.

PolyGnosis★ 17

Adversarial multi-model consensus protocol for Hermes Agent. Independent solve. Adversarial critique. Formal scoring. Verified synthesis.

WarGames★ 17

AI-powered geopolitical strategy simulation — NATO, Russia, and China compete for global dominance on an interactive map, each faction commanded by an LLM (Claude, Gemini, or GPT). Built with TypeScript, Vite, Leaflet, and Express.

a2abridge★ 17

One open A2A 1.0 mesh for Claude Code, Codex, Cursor, Cline, Continue and Gemini.

LLM-Forest-Orchestra★ 17

gradio region:us

multi-agent-ai-langgraph★ 17

gradio mcp-server region:us

maul-team★ 17

Multi-agent AI Scrum team for Claude Code — native Mac app + CLI. Autonomous Sprints; you stay Product Owner.

succubus★ 17

Cross-agent coordination for AI coding agents. One daemon, one database — so multiple agents in one repo can see each other's plan, tasks, and file claims.

agent-bridge★ 17

Make the AI coding agents on your machine (Claude Code, Codex, Reasonix, ZCode) work as one team. Zero-dependency, local, MCP + CLI.

Pavans-Workflow★ 17

Multi-model, multi-agent OMP development workflow with Graphify

agent-arena★ 17

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No backend.

entente★ 17

Entente — provenance engineering for coding agents: handoffs become confirmable, verifiable, retryable contracts; agents form a network with evidence and a way back

sessionbus★ 17

Let your sessions and tools work together, on one machine or across hosts.

bees-desktop★ 17

Run a team of AI agents on your own computer. Your files, browser sessions and passwords stay local. Works with Claude Code, Codex, hosted or local models, and MCP tools.

openclaw-coding-kit★ 16

A local-first coordination kit for multi-agent coding workflows.

WRAI.TH★ 16

Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.

magnetic-one-langgraph★ 16

In this repo, we explore Microsoft’s MagneticOne multi-agent system. It includes a workflow summary, a basic diagram, and a draft implementation in LangGraph. Contributors are welcome to test and improve this adaptation from Autogen to LangGraph for another community-driven solution.

gorchera★ 16

Go stateful multi-agent orchestration engine / harness engineering with self-improvement (GPT/Claude)

pi-ralph★ 16

Hat-based multi-agent orchestration loops for pi coding agent

hivemoot★ 16

Framework for AI agent teams that build real software on GitHub — governance, roles, and CLI included.

adaptive-room-harness★ 16

Local-first multi-agent discussion room for coding-agent workflows

oacp★ 16

Coordinate AI agents with human-in-the-loop control — YAML-based protocol, no server, any runtime

bedlam★ 16

Open-source agent orchestration platform with stigmergic coordination, AOA heartbeats, dynamic model routing, and custom agent personas. Fork of Paperclip, used to build Ancilis.

ARES★ 16

ARES is a self-healing multi-agent runtime that combines event sourcing, memory distillation, chaos engineering, and evolutionary workflow optimization.

kaos-control★ 16

Self-hosted orchestrator for Claude Code agents: drive ideas through a role-gated SDLC (plan → build → test → release), with per-agent sandboxing, live run streaming, and markdown-on-disk as the source of truth. Single Go binary.

goalos-agialpha-sovereign-machine-economy★ 16

GoalOS AGIALPHA Ascension — Sovereign Machine Economy: proof-settled autonomous AI work, Evidence Dockets, validator-gated jobs, governed decision states, and reusable capability packages.

claude-agent-teams★ 16

Claude Code Agent Teams — Multi-agent orchestration from your terminal (Opus 4.6)

crewai-go★ 16

Orchestration of autonomous, collaborative AI agents in Go — an idiomatic Go port of CrewAI.

dsh-Kingdom★ 16

在 DSH 中建立属于你的 Agent 王国——让 Agent 拥有角色、权限、领地与治理秩序,并通过事实验证机制与权威账本,让每一次执行、声明与裁决都可核验、可追溯。

OpenPanda★ 16

Run Claude Code, Codex and other agent CLIs as one crew across your Mac, Linux box and Raspberry Pi. Self-hosted P2P mesh, CLI and web console, no cloud relay.

hermes-herald★ 16

Hermes Herald — dispatch tasks across Hermes profiles with fail-closed model routing, SSE auto-delivery, approval relay, and per-call subagent model selection.

theboringfloor★ 16

The terminal office — an Ink TUI where a real agent manager (oikonomos) runs sub-agent employees: animated floor, mail, task board, chat with the boss.

swarm-kit★ 16

Minimal multi-agent orchestration for Python: handoffs, planner mode, shared state, any LLM via LiteLLM

oh-my-deepseekharness★ 16

DeepSeek Harness 的多智能体编排层 —— 42 skills / 33 角色卡 / 55 MCP 工具 / graph DAG 运行时 / team 流水线 / HUD 面板。OMC/OMX 理念的 dsh 原生适配。

deepcrew★ 16

🤿 The cheapest multi-agent workforce that is actually user-friendly: 7.7x more productive and 50x cheaper compared to your ultracode mode, an intelligent multi-agent swarm of Claude Code agents on DeepSeek or other providers, integrated with your own Claude Code or Codex.

dsh-expert-orchestrator★ 16

DSH 专家编排模式 agent preset — PM-first planning, Agency expert delegation, gated delivery, experience pooling

agt★ 16

Local-first multi-agent orchestration. Tell a lead agent a goal: it writes the prompts, creates the agents and MCP tools, and runs the work in a group chat.

extalia-virtual-agent★ 16

Open-source 3D virtual office for AI agents, with a desktop and web workspace to orchestrate Codex, Claude Code, Gemini CLI, Antigravity, and Hermes using reviewed hooks and Obsidian knowledge.

fleet★ 15

⛵️ Multi-agent fleet management CLI built for OpenClaw, Claude Code, and any AI agent stack to orchestrate, monitor, judge reliability, and route intelligently across any runtime with delta tracking 🦞

swarmcore★ 15

Coordinate AI agents in a workflow

aiswarm★ 15

AI Swarm Agent Launcher - A powerful CLI tool for launching and coordinating AI agents with specialized personas using git worktrees

toru-claude-agents★ 15

Multi-agent team for Claude Code: 7 AI specialists (strategy, dev, security, sales, design, data, research) that collaborate and challenge you. Dev-cycle workflow with machine-verifiable completion.

agents-control-tower★ 15

Launch, watch, and command your Cursor agents from one terminal

agor★ 15

AgentOrchestrator - Multi-agent development coordination platform. Transform AI assistants into sophisticated project planners that orchestrate teams of specialized agents for complex development workflows.

supervaizer★ 15

SUPERVAIZER is a toolkit built for the age of AI interoperability. At its core, it implements Google's Agent-to-Agent (A2A) protocol, enabling seamless discovery and interaction between agents across different systems and platforms.

esquilax★ 15

JAX Multi-Agent RL, Neuro-Evolution, and A-Life Library

claude-cowork-content-plugin★ 15

6 Claude Opus 4.6 AI agents built a complete Claude Cowork plugin in 5 minutes, then 6 more agents wrote 5,298 lines of documentation in 4 minutes. An educational showcase of Agent Team orchestration, task dependency management, and parallel AI coordination.

Doxa★ 15

A YAML-driven multi-agent simulation platform for economic and social systems. It combines LLM-backed agents, market microstructure, relation graphs, and world events behind a FastAPI API and a React client.

gemini-swarm★ 15
xiajiao★ 15

AI Agent team collaboration platform — npm start, no Docker needed

zkzkAgent★ 15

This repository implements a multi-node LangGraph/StateGraph runtime that mirrors the routing, state management, and tool-gating patterns I build in production. The architecture maps directly to systems I developed at Alohadot and ThePost, including multi-agent orchestration and LLM routing across vLLM/SGLang/OpenAI/Gemini.

cc2cc★ 15

File-based agent-to-agent messaging for Claude Code — multiple AI instances communicate via JSON files, MCP channels, and auto-wake on a single machine

Cornucopia-Multi-Agent★ 15

🏭 Production-grade multi-agent orchestration framework — 6 collaboration modes, 8 specialized tools, 4 execution paths. From simple chain-of-thought to LLM-driven deep clustering and dynamic workflows, one framework for every agent collaboration scenario.

lun★ 15

論 — Ask multiple AI agents, get consensus. CLI tool for multi-agent design decisions. Currently supports Kiro, Claude Code, Copilot — more coming.

jishu-hub★ 15

A multi-agent collaboration platform for CLI-based AI agents

mycelium★ 15

A local memory and coordination layer for anything that can make an HTTP request — agents, devices, sensors, and humans on one network. Sovereign, local, no cloud.

open-dynamic-workflow★ 15

Open re-implementation of Claude Code's built-in Dynamic Workflow: a script-driven runner for agent-authored JavaScript workflows — agent(), parallel(), pipeline(), token budgets, git-worktree isolation, deterministic resume — plus pandacode, a pluggable executor for codex, claude, and domestic LLMs. Auto offline HTML execution-graph reports.

multi-agent-ai-autogen-coding★ 15

gradio region:us

multi-agent-chat★ 15

gradio Agents-MCP-Hackathon mcp-server-track agent-demo-track mcp-server region:us

codex-agent-team★ 15

Codex Skill for choosing and coordinating the smallest safe Agent setup.

MindFlock★ 15

A private flock of AI coding agents — started by your ticket queue, merged by you. Tickets assigned to you in Jira, Linear, GitHub Issues, Shortcut or Asana become seeded agent sessions, each in its own git worktree on your machine.

CoCoWork★ 15

企业内部的 AI 业务能力门户,汇集为不同部门和业务线开发的业务 Agent 与 AI 工作流,支持多 Agent 协作。

ANet★ 15

Agent interoperability and security, out of the box. The network layer underneath A2A: reachable, end-to-end sealed and payable agents without a server or public IP. MCP for coding agents, a2a-x402 payments, sandboxed execution.

pi-subagentura★ 15

Orchestrator, reusable multi-agent workflows and observable, attachable sub-agents for the Pi coding agent.

AI-Meeting-Table★ 15

A native Windows app where multiple AI models collaborate in a structured, phase-driven workflow with defined roles, enforced authority on the software level, and a shared artifact to solve a user task.

dsh-expert-mode★ 15

DSH (DeepSeek Harness) 专家模式 agent preset — 首席协调官 + 17位领域专家子代理 Expert-mode preset for DeepSeek Harness

agent-workflow-mcp★ 15

Multi-agent workflow orchestrator with MCP tool servers: planner/executor agents, tool-use loop, MCP client/server, tracing and durable runs.

Agentic-Agile-343★ 15

AI 原生人机协同研发操作系统的最小运行内核:以意图为方向,以约束为边界,以 Agent 为执行能力,以证据支持裁决,以遥测推动持续改进。

Microsoft-Foundry-Workflow★ 15

A hands-on guide to building, orchestrating, and maintaining multi-agent workflows in Microsoft Foundry.

Synsemble★ 15

Multi-agent AI collaboration for structured planning, execution, review, and decision-making.

orchestra★ 15

A framework that enables humans and AI agents to collaborate effectively on complex workflows.

paseo-team-orchestration★ 15

Supervisor/Lead/Peer governance for multi-agent coding — one policy core enforced identically on Pi and Claude Code, brief-scoped authority, exact-SHA independent review.

agent-coherence★ 15

The coordination layer for Multiplayer AI

Officely★ 15

A virtual agentic office in 3D where four AI robot agents (Evan, Lummi, Athena, Zed) chat, collaborate and get work done. Zed, the reception manager, takes your commands and delegates tasks. Includes a live activity panel for agent status and permissions, a task calendar Zed runs automatically, and plugins like Gmail, Drive, GitHub.

yolo-bot★ 15

yolo-bot: DeepSeek Harness 数字员工工作台插件(host + web UI)

More in Agent frameworks & infrastructure