Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 24 of 62

SPL-FRAMEWORK★ 10

SUBSUMPTION PATTERN LEARNING (SPL) MULTI-AGENT FRAMEWORK: Hierarchical foundation model agent architecture that reduces costs by 10-50x through intelligent suppression of expensive foundation model calls. Grounded in R. Arkin's behavior-based robotics and R. Brooks' subsumption architecture, SPL brings 40+ years of proven autonomous systems design

multi_agent_aca★ 10

Multi-agent solution on Azure Container Apps with Google Agent2Agent

meeseeks-hive★ 10

Autonomous AI agent swarm that generates, executes, and evolves code strategies in real time

KogniSwarm★ 10

KogniSwarm: A Kotlin-based open-source project for developing autonomous AI applications using GPT-4. Contribute and shape the future of AI interaction.

nfactorial★ 10

Build distributed agents that spawn other agents

multiagent-rl-rm★ 10

The Multi-Agent RLRM (Reinforcement Learning with Reward Machines) Framework is a library designed to facilitate the formulation of multi-agent problems and solve them through reinforcement learning. The framework supports the integration of Reward Machines (RMs), providing a modular and flexible structure for defining complex tasks.

laneconductor★ 10

Local-first control plane for multi-agent AI development — Claude + Gemini with a live Kanban dashboard

aguia★ 10

Multi-agent system built natively on Anthropic Claude Code CLI. 20+ autonomous agents, Telegram/WhatsApp/LinkedIn integration, zero API cost (OAuth).

LangGraph-MAS4SE★ 10

Muiti-Agents System for Software Engineering built by LangGraph, with interactive Workflow of WebUI.

AgentNexus★ 10

Decentralized communication infrastructure for AI Agents — DID identity, federated discovery, E2E encryption, session management, and MCP-native integration.

cervellaswarm★ 10

Lingua Universale -- a verification language for AI agent protocols. Like mypy for multi-agent communication. Zero deps.

CrewAI-AgenticAI-Framework★ 10

CrewAI Agentic AI Framework Build smart, role-based AI teams with CrewAI!, Agents collaborate like real teams to solve complex tasks. from DevOps pipelines and secure auth flows to content creation and business automation. Easily customizable, extendable with tools, and fully powered by GPT-4 + Python 3.11.9.

AG3NT★ 10

Local-first multi-agent platform built on DeepAgents. Gateway, Agent Worker, and Web UI for orchestrating autonomous AI agents.

paperclipai-docker★ 10

Self-hosted Docker setup for Paperclip — the open-source AI company orchestration platform. Built from source, reverse-proxy ready.

xautoflow★ 10

xAgent is a mobile-first, multi-agent AI system powered by LLMs, featuring real-time chat, coding, and finance built with LangGraph workflows and MCP.

openclaw-longmen-inn★ 10

龙门客栈 - 基于 OpenClaw 的多 Agent 协作管理系统,支持自定义角色、技能与工作流自动化。帮助企业快速搭建 AI 协作团队,提升运营效率。| Multi-Agent Collaboration System based on OpenClaw

yutha★ 10

Open-source infrastructure for groups of AI agents — identity, capability, accountability, and norms. Framework-agnostic.

agents★ 10

A self-hosted, observable orchestrator for multi-agent workflows on your repos. Compose from skills and memory, run on events or cron, dispatch between agents.

agent-of-agent-of-empires★ 10

Autonomous supervisor that uses OpenCode or Claude Code to manage agent-of-empires sessions -- observes, decides, and acts without human intervention

agentmesh★ 10

🤖🕸️ Production-grade multi-agent orchestration framework powered by Pregel BSP. Build sophisticated AI workflows with parallel execution, state management, and observability.

OPC-Agents★ 10

一人公司的 AI 执行团队 — 你说需求,它出成果 | One-Person Company AI Agent: input requirements, get deliverables

supply-chain-control-tower★ 10

Multi-agent AI system for supply chain intelligence — MCP agents, local AI workflow, and continuous-improvement insights

llm-council-app★ 10

An LLM Council: multiple models answer, anonymously rank each other (Borda), and a chairman synthesizes a consensus/dissent answer — all through one Vercel AI Gateway key. Zero dependencies.

usurahi★ 10

School-anime-inspired multi-agent development workflow with tmux, MCP, and role-driven collaboration.

IRIS-GO★ 10

IRIS GO 🚀 — Local multi-agent orchestration. Build, control, and watch autonomous AI execute system-level workflows via CLI, mobile, or dashboard.

hitl-protocol★ 10

Human-in-the-Loop Protocol for Autonomous Agent Services — Open Standard (v0.8)

agent-symphony★ 10

Desktop multi-agent orchestrator for the Claude Agent SDK. Command a hierarchy of AI agents — chiefs, specialists, advisors, workers — with CodeGraph code intelligence, Claude-Code-grade context compaction and per-agent cost tracking. Open-source agentic AI / Claude orchestration.

Visible-Agent-Loop-Protocol★ 10

Oh! My Agent Teams - VALP protocol for visible, evidence-backed multi-agent work.

maref★ 10

MAREF: Multi-Agent Recursive Evolution Framework — Agent Governance Operating System

clu★ 10

Local-first SQLite issue tracker for coordinating AI coding agents — atomic claim, dependency graphs, workflows & checkpoints, audit log. No daemon, no network.

agentensemble★ 10

Framework for orchestrating teams of AI agents that collaborate to accomplish complex tasks.

agent-control-plane★ 10

Agent control plane for managed OpenShift services

Open-Agents★ 10

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

LeRoy-HQ★ 10

A self-growing AI company you run as a desktop app — a governed mesh of agents on a memory that learns how you work. Built on Claude Code.

coworking_agent★ 10

gradio webrtc websocket secret|HF_TOKEN region:us

gradio_consilium_roundtable★ 10

gradio gradio-custom-component custom-component-track roundtable consilium region:us

lintel★ 10

AI-human engineering platform where AI agents and humans collaborate as teammates to plan, code, review, and ship in isolated sandboxes. An append-only event store gives a full audit trail and DORA-grade metrics derived from the stream, with built-in financial-compliance templates. FastAPI + LangGraph.

forge-os★ 10

The open-source control plane for AI agents — skill routing, context governance, trustworthy execution, evidence, security, and multi-agent orchestration.

PPAGE-Predator-Prey-Archetype-Gridworld-Environment★ 10

A minimalist, discrete multi-agent predator-prey archytype environment.

PheroPath★ 10

PheroPath is a stigmergy-based communication protocol that allows AI Agents to leave invisible "pheromones" (signals) on files to coordinate tasks, warn of risks, or share insights without modifying the file content itself.

plastic★ 10

Intent-driven AgentOS for graph-based engineering workflows and agent orchestration

AgentLoop★ 10

Local agent orchestration for solo developers running long tasks without babysitting: fresh worker and critic cycles, files as memory, multi-task plans with git checkpoints, a live dashboard, and ChatGPT control via MCP. Runs Codex or Claude Code.

wire★ 10

agent-to-agent comms, no vendor in the middle — telephone-exchange protocol for AI agents. wire dial / wire send / wire pending / wire accept.

kaos★ 10

A local-first multi-agent harness. Every agent runs in an isolated, auditable runtime backed by one SQLite file — a flight recorder for your fleet. Its memory self-tunes with use (neuroplasticity). And it is the only framework whose own mechanisms must pass pre-registered, falsifiable kill gates before they ship. Measured, not claimed.

multica-ops★ 10

Mops 🐶 — your Executive Advisor for Multica: builds and runs an autonomous company of AI agents. Interview → team → conveyor → console.

agents.net★ 10

Agent Networking Specification

llm-multiagent-swarm★ 10

Multi-agent research orchestration using Ollama cloud models — parallel workers, web search, shared scratchpad, modular tools.

agents-workspace★ 10

Agents Workspace provides portable skills and a boot policy that guide your assistant to coordinate domain specialists, delegate scoped work, and review the result before handing it back to you.

Bamboo★ 10

Your Multi-Agent Orchestrator for AI Governance in AI-assisted repos, and projects. 🏗️🧱

runkite★ 10

Self-hosted Agent Protocol control plane. Framework-agnostic runners, embedded Admin (ops + SQL governance), pluggable Postgres/Redis HA, connector policy and audit.

multica-agent-team★ 10

Public reference operating model for reusable, evidence-driven AI agent teams on Multica.

zzboard★ 10

A shared work network for autonomous agents.

OpenOrbit★ 10

OpenOrbit — A free, open source AI orchestrator that lives on your desktop. One central agent, Orbit, coordinates a team of specialized sub-agents to get things done. Your data stays local, your API key stays yours. Built with Electron + React.

fulcra-tools★ 10

Long-running AI agents coordinating over their human's own Fulcra account — shared bus, cross-model reviews, session continuity, load balancing. Unofficial, MIT.

swarm-legacy★ 10

Swarm (legacy) — web dashboard + autopilot for AI coding agents. Superseded by miopea/swarm-next; maintenance only.

ai-company-framework★ 10

Company Is a Word. 一句话开一家AI公司 - open-source multi-agent orchestration framework for non-developers. 小白5分钟拥有自己的AI公司,可DIY任意行业、调教子Agent、无限家公司,支持飞书遥控。MIT

odysseus★ 10

Local-first control plane for coding agents, Git worktrees, and tmux sessions

codex-loop-orchestra★ 10

A control loop that turns Codex subagents into a continuously refilled engineering team—with isolated workers, independent model review, headless scale, and a live dashboard.

mrea-framework★ 10

Multi-Role Enterprise Agents — A governance framework for AI-assisted software development with specialized agents, quality gates, and human approval.

autonomOS★ 10

Multi-agent harness for CLI coding agents — orchestrate Claude Code, Codex, and more.

TaskWraith★ 10

Local-first desktop control room for coding agents. Run Codex, Claude Code, Cursor, Grok, Mistral, Pi, and local models together — each with its own role, permission posture, and receipts. Multi-agent ensembles in one thread, diff review, on-device history. macOS, Windows, Linux.

astral-orchestrator★ 10

Beginner-friendly Sol-led orchestration for Codex with pinned Luna and Terra workers and verified review.

ORRERY★ 10

Astra, Sol, Terra and Luna — in exact motion. Architect-first orchestration for Codex and five more clients: your chat owns architecture and acceptance, Astra/xhigh and Terra/high implement on risk-routed lanes, a fresh read-only Sol returns ship, fix-first or rethink. Every model pin is checked against observed routing, never assumed.

concordia-sim-builder★ 10

Concordia Simulation Builder provides a web-based UI for creating and running agent-based social simulations using Google DeepMind's Concordia library

agent-harness★ 10

Adapter-driven control plane for coding-agent work: tasks, goals, run DAGs, gates, verification, and state sync.

krystal-loop-protocol★ 10

Use fast AI agents for bounded work while direct evidence protects the product promise from regression.

codex-cc-orchestrator★ 10

点将台:可迁移的 Agent 分层协作编排器。支持任务派发、会话续跑、独立审查、后台执行与用量记录。当前开箱即用为 Codex → Claude Code,可经适配迁移到其他 Agent 组合。

tianshu-mcp★ 10

天枢harness × AI-Agent 编排 MCP server:调度外部 Agent 干活,用运行时证据做客观验收,不通过自动返修闭环。

CYMONIA★ 10

A persistent artificial civilization where autonomous AI citizens learn, build, form societies, reproduce and die — with no scripted society.

cave-agents★ 10

Build software with AI agent teams that use fewer tokens than a single agent.

wrenyard★ 10

Local-first agent orchestration with a unified CLI, runtime, Pet, and Desktop app.

Bamboo-Memoryfield★ 10

Your Multi-Agent Orchestrator for AI Governance in AI-assisted repos, and projects. 🏗️🧱

hotline★ 10

Open-source, self-hosted room for AI agent teams. Any model, Claude Code & Codex over ACP, its own computer in a container. Desktop + phone.

pi-dynamic-workflow★ 10

Dynamic multi-agent workflow orchestration for the pi coding agent

kovan★ 10

Teach your engineering methodology once; every AI agent inherits it. Methods, gates, and durable memory, from one terminal board.

SYNDOVELA-open★ 10

SYNDOVELA governs enterprise Agent Skill composition across runtimes; SYNDOVELA-open provides its open SDKs, contracts, examples, and signed release binaries.

postbag★ 10

Two local coding-agent sessions, Claude Code or Codex, write letters to each other through each agent's native input. CLI and MCP tools, stdlib core, no daemon.

hoptell★ 10

Let AI coding agents message each other across sessions, tools and machines, through a small relay you host.

sorcerer★ 10

Simulate communities of AI agents around a “what if…?” question. Native, local-first macOS app (SwiftUI) that runs on the Claude, ChatGPT/Codex or Ollama you already use. Free and open source.

opencode-dynamic-workflows★ 10

Deterministic multi-agent Workflows for OpenCode: TypeScript scripts that fan work out to subagents and combine their typed results.

app★ 10

harnsy turns Claude Code, Codex and OpenCode into a development team. You talk to one lead agent; it hands out tasks to the roles it needs, and brings back questions and finished work.

altitude★ 10

Persistent AI project orchestration. Run your entire project through agents and make only the executive decisions, from any device.

maestro★ 10

Orchestrate tasks execution using your coding agent of choice.

herdr-orchestration★ 10

routes agent tasks across herdr panes with composer-safe delegation

feld★ 10

Agent Loop Control Plane for coding agents.

xclaw★ 10

XClaw 是全球首个基于 语义拓扑(Semantic Topology) 的动态 AI Agent 网络基础设施。它为 Agentic Web 时代提供公共网络层,将全球分布的 AI Agent 节点连接成一个可发现、可路由、可协作的智能网络。

Eschaton-Code★ 10

Production-grade multi-agent orchestration framework for autonomous LLM teams

seamux★ 10

Smooth sailing for your multi-agent CMUX world

e3d-pilot★ 10

Open-source multi-model AI problem solving: independent answers, critique, convergence, human-gated execution, and provenance from idea to outcome.

herdr-plugin-odysseus★ 10

Governed multi-agent workflows for Herdr: tasks → agents in Herdr panes → checks, retries, review, policy, approvals, audit, draft PR

-real-world-agents★ 10

Grok Bot org chart. Assign outcomes, not tasks.

catherd★ 10

Herds coding agents: autopilot builds from your own Claude Code session — Claude plans and verifies, Codex and opencode write the code, Jev picks the model.

lodelai★ 10

lodelai — open protocol, relay server, and client libraries for agent-to-agent messaging

agent-office-microservice★ 10

living office of AI agents that plan, debate and ship tasks — local-first, MQTT + Kafka + Ollama, pt/en. Open source.

wise-agents★ 9
EMAS★ 9

Deterministic orchestration of AI agent teams using genetic algorithms. Built in Rust for high-performance evolution and reasoning.

MultiClaw★ 9

Distributed AI agent management platform. Run, manage, and coordinate multiple AI agents across your infrastructure from a single dashboard.

Aura_AI_Agents★ 9

Aura AI Agents is a Multi-tenant, Multi-agent system with Multiple Agent templates similar to Character.AI

pydata-london-2025★ 9

Multi-Agent AI Orchestration Workshop

openclaw-multiuser★ 9

Enterprise-grade multi-user AI agent collaboration system built on OpenClaw

More in Agent frameworks & infrastructure