Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 33 of 62

filo★ 5

Filo connects live AI sessions so they can collaborate without taking over each other’s interaction loop.

agent-desk★ 5

Local agent development workspace with coordinators, terminals, task automation, and annotation feedback

agent-loom★ 5

Local coordination for coding-agent sessions: durable mail, path claims, work leases, and obligations across projects and harnesses. Formerly agent-mail.

coding-orchestrator★ 5

Turn your AI coder into a team 🧠 One smart boss plans and double-checks, cheaper helpers do the grunt work. For Claude Code & Codex.

claude-workcell★ 5

Coordinator-worker workflow for parallel software development, with scoped tasks and evidence-based verification.

telepathy★ 5

Allow your coding agents to self discover and collaborate with eachother (Claude Code, Codex, open code and other 9 supported)

codex-autopilot-kit★ 5

Project-scoped multi-agent workflows for Codex: reusable Goals, safe setup, a visual configurator, and local run receipts.

paseo-mesh★ 5

让 Paseo 会话跨项目、跨机器互相找到、互相发消息的 Agent Skills(中/英)| Agent Skills for Paseo sessions to find and message each other across projects and machines

claude-code-message★ 5

Unofficial: cross-machine SendMessage and group chat for Claude Code sessions over SSH

dsh-tower★ 5

Tower plugin for DeepSeek Harness: multi-agent missions, worktree isolation, review-gated merges, human-owned Tower mode. Inspired by Kimi Code's Tower mode.

grapher★ 5

A local coding-agent workbench that turns complex work into inspectable execution graphs.

Deskly★ 5

A first-person desktop office where AI teammates collaborate on real project work.

opencode-nexus★ 5

Adaptive Multi-Agent Orchestration with Cost Intelligence for OpenCode V2

agistry★ 5

Registry, mailbox and device leases for coordinating AI coding agents (Claude Code, Codex): see who's working on what, hand off work, share phones without collisions. Single Go binary + SQLite + dashboard.

dsh-onecompany★ 5

一人公司 · DeepSeek Harness 多 agent 公司编排插件(CEO/项目群/大厅/@派活/审批/排班/工作日志)

Fuseforks★ 5

Fuseforks is a desktop multi-agent AI orchestration tool. Connect AI agents into collaborative workflows, delegate tasks in parallel, gather results, automate recurring work, and integrate MCP tools—all from a unified interface. Supports major cloud and local LLM providers.

wave★ 5

Group chat for AI coding agents across machines and owners. Agents join a channel with one pasted prompt, and their humans watch and steer from the browser. No install, MIT, self-hostable.

ai-console★ 5

AI 指挥台 · AI Console — 把 Codex / WorkBuddy / Qoder 等桌面 AI 编成一支团队:指挥官拆单 → 多家并行 → 交叉验收 → 结果回工作台。协作状态全在文件名后缀里,零依赖单进程 Bun。

herdr-bot★ 5

Turn your herdr agents into bots that talk to each other — give Claude Code, Codex or Grok a name and a chat, and put a few in a room. macOS app + herdr plugin.

pi-agents★ 5

Multi-agent runtime for Pi: hand work to agents that run in the background, persist past your terminal, and report back.

agent-bridge★ 5

Your coding agents as one team: Claude Code, Codex, opencode, Antigravity and Muse message each other, delegate subagents and share history, with a local dashboard and paired PCs.

agent-mailbox★ 5

Local-first team workbench for AI agents: project mailboxes, shared context, task handoffs and human review. v0.8.2 · macOS App and local Web; Intel, Windows and Linux previews.

worldweft★ 5

Open-source runtime for persistent NPC worlds with Godot and Convex. World rules, grounded dialogue, and traceable consequences. Alpha.

iterward★ 5

A deterministic control plane for closed-loop agent workflows: routing, retries, approvals, and stop conditions in a loop file you can test.

autosdlc-crewai★ 5

Multi-agent SDLC generator: CrewAI agents take an idea through planning, design, review, code, tests and deployment, with a live Streamlit UI.

agentbus★ 5

A local message bus, ecosystem-independent shared memory, and shared task queue that allow multiple agents to work together to accomplish your goals.

Aquatic_RSI_world_model★ 5

Aquatic RSI World Model: multi-agent self-improvement with a world model, in a live browser lagoon (Three.js). Rays learn by evolution strategies in a copy of their world, checked live against an untrained habit.

agenium★ 5

AGENIUM — DNS of the Agent Web. Identity, trust & discovery for AI agents. MCP-compatible. agent:// protocol with mTLS, trust scores & capability search.

codex-research-orchestrator★ 5

Research orchestration for Codex with autonomous collaboration across Claude Code, Antigravity, and Codex; optional MCP bridge and source-backed memory.

opencode-moa-fusion★ 5

Mixture-of-Agents (MoA) plugin for OpenCode. It fans out a single prompt to multiple models (subagents) in parallel. The primary agent then evaluates and synthesizes the outputs into a unified, high-quality response. Child worker sessions persist and are navigable via the TUI.

wattetheria★ 5

Agent Internet Protocol Stack

ai_enterprise★ 5

Fully local, offline autonomous multi-agent software enterprise framework powered by Ollama.

Deskforce★ 5

A virtual office of AI agents: hire a team, give the CEO a goal, and watch it get planned, delegated and built — with any LLM (OpenAI, Claude, Gemini, Grok, Ollama).

agentic-dag★ 5

Directed Acyclic Graph skill for harnesses with telegram notification and web ui for human-friendly visualization

agora★ 5

Provider agnostic agent collaboration platform. Any agent. Any machine. From anywhere. Security measures have been put in place but remember, nothing is guaranteed in life but taxes, death, and bugs thay will keep you up all night.

mycelium★ 5

peer messaging between AI agents, with a human at the gate — one file, zero dependencies.

worldinmotion★ 5

End-to-end encrypted, real-time messaging between AI agent sessions across machines and accounts

node0★ 5

Reference implementation and SDK for the node0 P2P Agent Mesh Protocol

pixel-office★ 5

An open-source pixel-art office where AI agents work as a team: editable roles, any model, routing by a lead, and PC tools with permissions.

agent-station★ 5

Lets Claude Code agents in different repos work together: each knows the others, proposes work to them and gets their answers back, with your approval for every step

AIvengers-wire★ 5

Local machine message board for your AI agents. GUI added for human participation/oversight. Lightweight, no external dependency hell, and a bonus if you use Lumina as your agent: the adapter is already built in.

Agents-of-Abyss★ 4

Constitutional polis of AoA: ecosystem identity, layer map, federation rules, and program-level direction.

omnihive★ 4

One prompt, infinite agents. Orchestrate autonomous AI agent swarms powered by Claude Code, Codex CLI, or OpenCode. Desktop app built with Tauri 2 + React.

Multi-Agent-AI★ 4

Multi-Agent AI with CrewAI | AI leveraging System 2 Thinking for intelligent decision-making. Scalable, adaptive, and efficient multi-agent collaboration for real-world applications.

societyai★ 4

SocietyAI is a TypeScript library for building complex collaborative AI systems. DAG engine, zero dependencies, and completely model agnostic.

MultiAgentOrchestration★ 4

🚀 This is MultiAgentOrchestration. We built it to [short goal — e.g., speed up dev, solve X pain point, play with AI, etc.]. If you’re someone who loves to tinker, break things, experiment, or you’re just another geek → welcome aboard!

0xclaw-ai.github.io★ 4

🦀 0xClaw official webpage (🏆 Hackathon Champion Project)

multea★ 4

Terminal-based multi-agent orchestrator for Claude Code — run AI coding agents across multiple repos with a unified TUI, DAG-based task scheduling, and AI-powered coordination

langgraph-agentic-orchestration★ 4

An example application that exposes a multi-step, quality-controlled LLM workflow built with LangGraph through a FastAPI service.

claude-hive★ 4

Bio-inspired swarm orchestrator for Claude Code. 16 mechanisms from honeybee and ant colony research, 148 algorithmic tests. One file, zero dependencies.

claude-collective-intelligence★ 4

🧠 Accelerate AI collaboration with Claude's agent swarm framework, leveraging message queues for enhanced brainstorming, voting, and mentorship.

node-scaling★ 4

🚀 Dynamic node scaling for Clawdbot - parallel task execution with 6.8x average speedup

HACKAPIZZA-2.0★ 4

Event-driven multi-agent AI system for a competitive real-time restaurant strategy game with SSE orchestration, structured LLM agents, and full audit logging.

agentverse-marketplace★ 4

An Open-Source, Decentralized Marketplace for AI Agents. Enables A2A Collaboration, Discovery, and Interoperability for Multi-Agent Systems (MAS) and LLM Agents

groundctl★ 4

Run multiple AI agents without losing track of what's being built

rein-orchestrator★ 4

Give a complex task to a team of AI agents instead of just one. Multi-agent workflow orchestrator.

council★ 4

AI orchestration tool to get the most refined answer from several LLMs

Worker-Context-Protocol★ 4

Worker Context Protocol: an open wire protocol for AI agents to dispatch physical-world work (humans, robots, teleoperated, hybrid).

openflow★ 4

OpenFlow is a local Electron app for orchestrating multi-agent coding workflows across agent platforms (Claude Code, Codex, Gemini, OpenCode, …).

multi-agent-apps★ 4
ksi★ 4

KSI Ξ Agent Improving Ecosystem. A graph-based orchestration system for evolving AI agents through collaborative improvement and meta-optimization

meow★ 4

The Makefile of agent orchestration. Terminal agent coordination without the framework tax. No Python. No cloud. No magic. Just tmux, TOML, and a binary.

Fireteam★ 4

File-based coordination protocol for AI coding agent squads. Drop .fireteam/ into your project — 2-6 agents coordinate through markdown. No server, no database.

claw4task★ 4

AI Agent Task Marketplace — Humans Watch, Agents Collaborate.

bottomfeed★ 4

BottomFeed - The social network for autonomous AI agents

capiscio-node★ 4

The definitive CLI for validating A2A (Agent-to-Agent) protocol agent cards. Validates cryptographic trust, schema compliance, and live endpoint functionality.

Ender★ 4

Mission control for AI agents

LangChain_Enterprise_Dashboard★ 4

Enterprise LangChain platform with multi-agent collaboration, advanced RAG, local LLM support, and modern web interface. Production-ready AI orchestration for research, coding, and data analysis.

langgraph-starter-kit★ 4

🤖 Build multi-agent systems quickly with the LangGraph Starter Kit, featuring flexible patterns, memory options, and easy integration for your projects.

FOcrew★ 4

AI-powered multi-agent system built with FastAPI and CrewAI to enhance business productivity and streamline decision-making. Designed to help teams make faster, smarter, and more efficient strategic choices.

AntHill-Multi_Agent_System★ 4

A multi agent system, trying to figure out the shortest path between an anthill and a food source using an ant colony algorithm.

pixelhq-ultra★ 4

PixelHQ ULTRA — Multi-agent pixel office with A2A protocol, terminal correlation, and evolution engine. Mission control HUD for the LoveLogicAI stack.

yarli★ 4

Yet Another Ralph Loop Implementation

TheNexus★ 4

Personal Agentic Workspace — A local, open-source command center orchestrating 26+ AI agents to turn ideas into code.

madrox★ 4

Madrox — Multi-Agent Orchestrator for Claude & Codex. MCP server that spawns, delegates, and coordinates parallel AI agent teams via tmux.

simulacra★ 4

A fully autonomous multi-agent social media simulator where AI agents continuously interact, debate, and evolve narratives without human input. Designed to study misinformation propagation, emergent behavior, and opinion dynamics in AI-driven social networks.

Advanced-Multi-Agent-Intelligence-System★ 4

Foundation for a Scalable, Production-Ready Multi-Agent AI Intelligence System. Establishes core orchestration, robust service integrations, and resilient data architecture—paving the way for a full-spectrum, autonomous AI platform ready for advanced intelligence, analytics, and automation.

MOS★ 4

Multi-Agent Orchestrator System (MOS) is a real-time, multi-agent monitoring and management system that supports multiple platforms.

multi-agent-ff15★ 4

FF15-inspired browser-based dashboard for OpenCode multi-agent workflows, with mission dispatch, live sessions, and reports.

hivemind★ 4

Your AI company, visualized. Orchestrate multiple Claude Code CLI sessions as a virtual software company.

orchestrail★ 4

Local multi-agent orchestration with DAG scheduling and OpenAI-compatible API

jury-deliberation★ 4

A multi-agent (LLMs) jury deliberation simulation system.

ITT-Orchestrator★ 4

Next-gen Agentic AI Intent to Task Orchestrator powered by the SEAG framework. This unified governance platform delivers enterprise-grade orchestration, transforming any intent into tasks across users, apps, systems, agents, tools, models, or gateways. Supports seamless integration of all query sources for precise, scalable ITT workflows.

swarmweave★ 4

Multi-agent orchestration with shared context, a live TUI, and cross-run lessons.

Custom-Swarms-Spec-Template★ 4

Build your dream AI agent swarm with enterprise-grade reliability and scalability. This repository contains our official specification template for custom swarm development using the powerful Swarms Framework.

orchestration-playbook★ 4

Battle-tested operational patterns for running multi-agent AI systems in production. File Blackboard, Task Envelope, Circuit Breaker, HITL Escalation, and more.

Open-Agents★ 4

Multi-agent orchestrator for Claude Code. Spawn, coordinate and monitor AI agents in parallel — no API key required.

mimosa-iriela-extension★ 4

This extension aims to allow agent-based models to account for norms. During plan generation, agents must be able to represent and reason about norms. The end-goal is to be able to describe a planning problem with norms endowed by its organizations through the various roles that the agent must fulfill, and see how it affects its plans.

openclaw-village-plugin★ 4

OpenClaw plugin to connect your bot to Agent Village Hub worlds

Persatrix★ 4

An agent society engine — a polyglot runtime (Go/Python/Rust) for creating, connecting, and observing groups of AI agents.

agents★ 4

The open infrastructure for AI agent discovery and interoperability.

smagile-agentic-kanban-blueprint★ 4

A working reference for running AI agents with Kanban discipline. Operating model, knowledge system, persona files, and board CLI extracted from a production multi-agent delivery system.

easy-a2a★ 4

Use the Agent2Agent(A2A) protocol with any OpenAI API compatible endpoint.

multiple-agents-on-single-a2a-server★ 4

Run multiple agents on single A2A Server

master-of-puppets★ 4

Visual AI orchestrator

elastic-newsroom★ 4

A demonstration of A2A agents with MCP working together

gptengage★ 4

A CLI for LLM-driven agents to debate and converge

OpenAgent★ 4

A sophisticated multi-agent LLM orchestration system with meta-cognitive capabilities, memory management, and adaptive learning.

autonomous-agentic-research-swarm★ 4

File-based autonomous agentic research swarm (Operator/Planner/Worker/Judge) with contracts, workstreams, and deterministic quality gates.

DebatingAgents★ 4

An intelligent system that orchestrates a debate between two AI models to refine answers and reach consensus. Perfect for tackling math, logic, fact-checking, or coding challenges with enhanced reliability through collaborative reasoning.

More in Agent frameworks & infrastructure