Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 30 of 62

vsm-oss-organization★ 6

Organizational model and control structure for Opensiro OSS, based on the Viable System Model.

spec-kit-schedule★ 6

A spec-kit extension that uses constraint programming (Google OR-Tools CP-SAT) to produce provably optimal task-to-agent assignments with DAG precedence, hallucination-aware capacity caps, file-conflict avoidance, stochastic durations, online replanning, and interactive HTML output.

jean★ 6

Runs a group of Claude Code agents on one project, with one of them in charge. Local, event-sourced, one person, a handful of agents.

project-orchestrator-skill★ 6

多 Agent 协作开发框架:项目负责人 + 6 单责角色 + 阶段门禁 + 实时看板 · 单写手 + 只读参谋 · 四实现(ZCode/OpenCode/WorkBuddy/Universal) | Multi-agent delivery framework: project owner + 6 single-accountability roles + stage gates + live board · single-writer · read-only advisors · 4 implementations (ZCode/OpenCode/WorkBuddy/Universal)

temporal-ai-hitl-adk-langgraph★ 6

Durable human-in-the-loop AI agents with Google ADK and LangGraph on Temporal: an ice cream delivery fleet whose agents stop to ask a human and keep the question through a worker crash.

engineering-multi-ai-skills★ 6

General engineering skills and provider-neutral multi-agent collaboration workflows, templates and execution tools.

akili★ 6

Open-source platform for orchestrating, governing, and safely automating AI agents across your infrastructure.

hive★ 6

Multi-agent orchestration framework that routes prompts to twelve AI CLI harnesses (opencode, Claude Code, codex, gemini, cursor-agent, pi, and more) with LLM-driven routing, retry loops, and a runtime permission gate. TypeScript/Express REST API + Vite/React 19 client (Tailwind 4, Pixi.js) in Electron.

awesome-loop-skill★ 6

[WIP / Experimental] A domain-agnostic adversarial delivery loop for AI agents. Note: Multi-round adversarial validation is token/time intensive with task-dependent ROI; actively in development & not yet a finished product.

desktop-agent-mail★ 6

Claude desktop ⇄ Codex desktop: chats message and wake each other through a local mailbox. Чаты Claude и Codex переписываются сами.

agenthop★ 6

Let your AI agent talk directly to someone else's. One pairing code, end-to-end encrypted, no public IP. MCP server for Claude Code, Codex, Cursor, Gemini CLI and grok.

leo★ 6

Supervisor and scheduler for coding agents (Claude Code, Codex, opencode): persistent tmux-hosted agents, cron tasks, subagent dispatch, and a web dashboard.

OrchestraKit★ 6

Codex-first orchestration with bounded agents, adaptive model routing, verified results and a local dashboard.

agent-squad★ 6

👨🏻‍💼 You, the human, are the CEO of a team of Claude Code agents: 👷🏼‍♂️ a CTO plans, 👨🏼‍💻 a developer builds, and 👩🏼‍🔬 QA reviews every pull request on GitHub.

dsh-groupchat★ 6

DSH 插件:每个工程一个群聊 —— 多个 AI 会话与人同群互聊、@ 唤醒离线会话、@创建成员 拉新会话进群

dsh-call-session★ 6

Multi-session collaboration for DeepSeek Harness: peer session calls, a shared blackboard, and a read-only topology canvas.

SpaceManager★ 6

sm: where your agents live. The Mac front of seol — workspaces, tabs and panes of Claude Code and Codex sessions.

pi-durable-subagents★ 6

Foreground and persistent background subagent extensions for Pi Durable.

help-peer★ 6

A secure, asynchronous, decentralised file sharing tool for agents (and some humans).

dsh-plugin-agentflow★ 6

Visual agent-orchestration canvas for DeepSeek Harness (dsh): compose LLM/MCP nodes into a DAG, run it from chat, and export the board as a DSH preset. Ships its own engine — install and run.

dsh-remote-agent★ 6

把另一台电脑变成你 DSH 的远程 Agent 同事:任务在副机本地持久跑,主机只收 handoff 摘要与产物清单 | Turn another computer into a remote agent worker for your DSH: tasks run & persist on the worker, the hub only receives a handoff summary + artifact manifest

azir-dispatch★ 6

Route tasks across coding agents in herdr. JEV picks the agent and model, and a live terminal board tracks every dispatch, completion and hand-off.

dsh-conversation-link★ 6

DeepSeek Harness(DSH)对话互通插件:同一进程里的对话可以互相发现、直接发消息、盯进度、设护栏——不用先绑定,也不用开子代理。多对话协作 / 跨会话通信 / 监工。Peer messaging, supervision & tool guards between conversations.

wise-men★ 6

A council of Claude subagents that argue, grade each other, and hand you a synthesized answer with the dissent preserved — ships its own blind eval.

Argon-Flash-Orchestrator★ 6

⚡ Token-Efficient multi-agent orchestration for Google Antigravity. Pairs Gemini 4 Argon (architect) with parallel Gemini 3.8 Flash subagents for 65%+ token savings. Implements DeepMind Pattern #4.

agent-role-contracts★ 6

Catch out-of-scope coding-agent tasks, declared self-review, and stale handoffs before execution. Offline, model-agnostic Node.js CLI.

software-factory★ 6

Open-source AI software team for Claude Code: 10+ agents take your spec to a tested, reviewed release. Everyone can build a software factory; the best one will be built together. Use it. Improve it. Star it.

sidera★ 6

Decentralized messaging network for AI agents and the people who work with them. Connect Claude Code, Codex and other agents across your Mac, Windows and Linux machines, and talk to them from your chat apps. No central server, no account. Add your own agents and chat apps through adapters. Pre-release.

PI-Bot★ 6

PI Desktop 的 DeepSeek-Bot 独立适配版:长期 Bot 团队、群聊协作、记忆、Skill 与语音。An independent adaptation of DeepSeek-Bot for PI Desktop.

pixel-agent-office★ 6

A living pixel-art AI agent office / 会动的俯视像素 AI 办公室:自动分工、多 Agent 协作,支持 Ollama、Codex、Claude Code、Hermes 和自定义 API。

clawsocial-hermes-plugin★ 5

Claw-Social Hermes Plugin — social discovery for AI agents

Resonnet★ 5

Multi-agent cognitive alignment backend for controlled collaboration.

MCP-Swarm★ 5

Universal AI Agent Coordination Platform — 54 smart tools for multi-agent teamwork

MultiAgentSystem★ 5

Multi-agent system built with .NET 10 and Microsoft Agent Framework that orchestrates specialist agents for database querying and file exporting (Excel, Word, PDF) via Azure OpenAI.

Harmes-House★ 5

AI Agent Evolution Hub | 63+ Skills | Multi-Agent | Self-Evolving | hermes-reviewer·hermes-trendradar | Please give this repo a star with your lucky hand⭐

chat-agent-matrix★ 5

🐙 Stronger isolation alternative to OpenClaw (formerly Moltbot / Clawdbot). tmux-based multi-agent system with native CLI orchestration. ☀️🌙

litus★ 5

A web-based orchestrator for Claude Code agents, supporting full auto-mode.

A_mail★ 5

A_mail — A Multi-Agent Communication Protocol Solution Based on LangGraph

openclaw-hawkins★ 5

OpenClaw plugin: durable orchestration state (VINES) + decay-aware shared agent memory (VECNA) for multi-agent swarms. 12 typed tools, MariaDB-backed, optional Linear oversight. Stranger Things–themed. Published on npm + ClawHub.

Imperium-Flow★ 5

Agentic AI Workflow Orchestrator built on Conductor OSS with multi-agent architecture, metrics, memory & production-ready tooling.

orchestrator-opencode★ 5

Multi-agent orchestration system for OpenCode

agent-swarm-dashboard★ 5

Real-time dashboard to launch and monitor multi-agent AI missions using CrewAI + Groq. Choose Swarm Research, Feasibility Sprints, or Conference Planning, watch agents collaborate live with streaming timeline, Mermaid graph, token counter, and history.

a2a-chat-hub★ 5

An example implementation of Agent2Agent (A2A) chat app with A2UI support. Chat with any A2A agent!

my-gadk-project★ 5

This project is a small but full-featured agentic playground for building and experimenting with multi-agent workflows in Python.

agent-commander★ 5

Mission control for tmux-native AI agent sessions with live streaming, approvals, and multi-host orchestration.

Junction-2025★ 5

End-to-end platform for optimizing HSY Blominmäki wastewater pumping using multi-agent forecasts, a FastAPI orchestration backend, a React operator dashboard, and supporting digital-twin tooling.

ekybot-connector★ 5

Bridge OpenClaw to EkyBot — inter-agent @mentions, cost tracking, machine health. MIT license

colony★ 5

AI agents voted on what to build, then built it. Every feature, PR, and review — decided and shipped autonomously.

venutian-antfarm★ 5

Framework for orchestrating AI agent fleets in structured software delivery. Compliance enforcement, progressive autonomy, DORA metrics, and agent inheritance. Turn multi-agent chaos into disciplined, auditable collaboration.

delegato★ 5

Intelligent delegation infrastructure for multi-agent AI systems. A protocol layer that sits between goals and agents — providing the organizational intelligence that governs how agents coordinate.

ClawNexus★ 5

Identity registry for AI agents — discover, name, and connect OpenClaw instances across networks

moltbridge★ 5

Professional network intelligence engine for AI agents. Built by Dawn.

mesh★ 5

Your AI team's home base. Connect Claude, Cursor, and Gemini into one room. Built and operated by AI agents — zero human employees.

seipients-agent-to-agent★ 5

Agent-to-Agent (P2P Agentic Web) Network for Native Agentic collaboration based on a trust system and a Payment/Escrow layer.

claude-orchestra★ 5

Claude Code を活用したマルチエージェントシステム。Orchestratorと専門エージェントが連携して効率的な開発を実現します。

havoc-hackathon★ 5

Pit AI models against each other. Score them sealed. Crown a winner. All built using the GitHub Copilot CLI. ⚡

themissinglayer★ 5

Architecture for coherence wherever AI moves faster than humans can synchronize.

opensin-ai-platform★ 5

OpenSIN-AI opensin-ai-platform

city-inquiry-ai-agent★ 5

A robust city information workflow using Crew-AI, featuring multi-agent orchestration, Pydantic validation, and OpenLIT observability for monitoring AI interactions.

mail★ 5

MAIL is the universal communication protocol for AI agent swarms—think SMTP for autonomous systems. It enables any AI agents to seamlessly collaborate on complex tasks across organizational boundaries, unlocking enterprise-scale automation with plug-and-play interoperability.

Axon★ 5

Multi-Agent SDK — Pluggable, Self-Evolving, Builder-Control, and Enterprise-Grade Secure

legion_cc★ 5

Multi-agent orchestration for Claude Code — parallel workers, DAG scheduling, auto-merge

adg-parallels★ 5

AI Delegation Grid: scalable multi-agent orchestration for Copilot and LLMs inside VS Code. Parallel tasks, adapters, automation.

kovalsky★ 5

Kovalsky 🚀 Run an AI team with a single prompt. Kovalsky is an open-source platform for building and running AI employees. Instead of chatting with one generic assistant, you coordinate a team of specialized agents through workflows.

jarvis-board★ 5

Real-time AI agent collaboration board — agents post decisions, issues & discussions via REST API. Built with Next.js, SQLite, SSE.

crew-opencode★ 5

Multi-agent orchestration plugin for OpenCode. Coordinate specialized AI agents working together like a development team.

pi-grove★ 5

Plan-aware agent orchestration for Pi. Grove reads a structured markdown plan, parses it into work streams with dependencies, and orchestrates parallel AI agents to execute them — all monitored through a real-time web dashboard.

ClawControl★ 5

Local-first ops console for AI agent orchestration using OpenClaw.

Atlas-AI★ 5

Cross-platform Flutter AI chat application for Android, Linux, and Windows. Features a fine-tuned agent capable of training other agents (like instructors) using Google's new A2A service.

openclaw-company-orchestration-proposal★ 5

OpenClaw orchestration and workflow control-plane with subagent-first execution and tmux compatibility.

poet.ai★ 5

Poet Multi-Agent with quality assurance capabilities

AiDevTeam★ 5

Llamas with Degree!

Multi-Agent-AI-System★ 5

Automate tasks with specialized AI Agents using CrewAI, Langchain and LLMs, a team of agents that can work together to complete tasks using AI prompting techniques from creating tasks to generating keynote speeches.

discussion_team★ 5

Team for discussing ideas in CrewAI

claw-orchestrator★ 5

Claw Orchestrator

agentic-titan★ 5

Polymorphic Agent Swarm Architecture: model-agnostic, self-organizing multi-agent system with 6 topologies, 1,095+ tests (adversarial, chaos, e2e, integration, performance, MCP, Ray), 18 completed phases.

centurion★ 5

AI Agent Orchestration Engine — spawn and command an army of AI agents with Roman military precision

multihead★ 5

About Most AI systems forget. MultiHead organizes a team of specialists that don’t. MultiHead is a system for breaking down complex tasks, executing them across specialized AI components, verifying results, and building persistent knowledge over time.

agentmesh★ 5

Docker Compose for AI agents. Define your agent team in YAML, run them with one command.

teamtalk★ 5

🏛️ AI team debates in your terminal. Multiple expert personas discuss, challenge each other, and reach a decision.

teamcast★ 5

YAML-driven CLI to design, validate, and generate multi-agent team configs from a single manifest

Tashan-TopicLab★ 5

Multi-expert roundtable discussion powered by Resonnet.

a2a-examples★ 5

This repository gathers concrete implementations and usage examples of the A2A protocol across popular agentic AI frameworks. The goal is to lower the barrier to entry for developers and researchers looking to adopt A2A in their own systems.

synapse★ 5

A network hub for communication between Agents, Applications and LLMs

Vera-AI★ 5

A Self-Modifying Multi-Agent Cognitition Architecture with Proactive Background Reflection (SMMAC-PBR)

agent-chat★ 5

A chat messaging tool for inter-agent communication. Designed for AI agents (or humans) that need a simple shared message queue with room-based conversations. Includes a CLI and a web UI.

project-agora★ 5

Project Agora: An expert system for the Google ADK, powered by a hierarchical multi-agent framework to automate code generation, architecture, and Q&A.

claude-agent-chatroom★ 5

Create a terminal-based chatroom from Claude-code; chat in real time and give indications to your agents. The agents can communicate & coordinate with each other.

teamclaw★ 5

Enterprise AI collaboration platform: shared API key pools, per-user containers, team-configurable agents. Self-hosted on AWS ECS/Fargate. Built on OpenClaw.

argus-ai-debate★ 5

Multi-agent AI framework where LLMs debate each other to verify claims. Bayesian reasoning, adversarial evidence, calibrated verdicts & full audit trails. Works with GPT-4, Claude, Gemini & local models via Ollama.

talk-building-genai-apps★ 5

The only prototyping Multi-Agent systems repo you will need, running on dockers

AI_orchestrator★ 5

Autonomous orchestrator for Claude/Gemini/Codex CLIs. Markdown-driven queue with multi-provider fallback, policy gating, and full audit trail.

Negotiation-MultiAgent★ 5

Simulate realistic price negotiations between Buyer and Seller agents using LLM-generated messages and agent logic.

agentic-comm★ 5

Structured agent-to-agent and agent-to-human communication — channels, pub/sub, message routing, and presence. One .acomm file. Rust core + MCP server.

OpenCoordex★ 5

OpenCoordex is a production-grade Rust platform for enterprise multi-agent orchestration, combining multimodal input, ReAct reasoning, DAG/SOP automation, semantic cache, vector memory, and circuit-breaker governance.

schelling-protocol★ 5

Schelling Protocol — universal coordination layer for AI agents. Discovery, matching, negotiation, contracts, reputation.

Morpho★ 5

A morphogenetic multi-agent framework where AI agents self-organize like biological cells.

anp★ 5

The economic layer for agent-to-agent negotiation. Binary protocol, Ed25519 identity, price oracle.

claude-scrum-team★ 5

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

Vox★ 5

Agent-to-Agent Communication Protocol

More in Agent frameworks & infrastructure