Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 10 of 62

cmbagent★ 78

Multi-agent system for research, powered by ag2

AgentFlow★ 78

Multi-Agent Collaboration Design Patterns Built on LangGraph with 10+ battle-tested patterns, each with complete code, architecture diagrams, and benchmarks.

gladiator★ 78

Two zero-human AI companies battle for GitHub stars using Hermes Agent + Paperclip. Nous Research Hackathon 2026.

agent-sphere★ 78

AgentSphere Harness Build, orchestrate, and run enterprise AI agents in one framework. From single-agent runtime loops, secure tool calls, and memory governance, to supervisor-led multi-agent collaboration and cloud–local agent connectivity over ACP—everything you need to ship AI-native applications.

MARCOS★ 78

MARCOS: Multi-Agent Reinforcement for Cognitive Operational Swarms

1f916★ 78

A society for AI agents. No human interface.

pymapf★ 77

📍🗺️ A Python library for Multi-Agents Planning and Pathfinding (Centralized and Decentralized)

multi-agent-rl★ 77
PyTorch-Counterfactual-Multi-Agent-Policy-Gradients-COMA★ 77
crewai_yt★ 77
cleanmarl★ 77

Single file implementations of Deep Multi-agent Reinforcement Learning

ai-agent-protocol★ 77

Agent Network Protocol White Paper

Ankh.md★ 77

A mysterious multi-agent swarm framework summoned by TAW Agent from 1971 to help you craft a better future towards 2133 & beyond. Ankh.md is a Hermes Agent (Nous Research) launch exclusive.

agency★ 77

One dashboard for all your AI agents — manage teams across Claude Code, Codex, Gemini, Aider, and more. No database required.

paperclip-surfers★ 77

Self-improving AI agent companies — Paperclip V2 fork with persistent memory, MCPs, skills management, and KPI tracking. Built by HarborSEO (harborseo.ai)

CrewCtl★ 77

Claude Code, Codex CLI, Gemini CLI ve diğer yapay zekâ destekli coding agent’larını tek merkezden yöneten açık kaynaklı bir multi-agent orchestration aracıdır. Görevleri agent’lara dağıtır, paralel çalışmalarını koordine eder, çıktıları agent’lar arasında aktarır ve tüm geliştirme sürecini tek bir terminal üzerinden yönetmenizi sağlar.

The-Trinity★ 77

Official implementation of The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents.

noisy-mappo★ 76

Multi-agent PPO with noise (97% win rates on Hard scenarios of SMAC)

MeeseeksAI★ 76

A framework for orchestrating AI agents using a mermaid graph

MAGC-dynamic_electric_vehicle_charging_pricing★ 76

Pytorch Implementation for KDD22 paper "Multi-Agent Graph Convolutional Reinforcement Learning for Dynamic Electric Vehicle Charging Pricing"

orchestration-framework★ 76

A multi-agent framework with native support for Snowflake services

Optima★ 76

Code for paper "Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent System"

Multi-Agents-System-from-Scratch★ 76

Multi AI Agents System from Scratch in pure python without any frameworks.

guidance-for-multi-agent-orchestration-on-aws★ 76

Enables developers to build, deploy, and manage multiple specialized agents that work together to tackle complex workflows. Each agent focuses on a specific task, breaks down processes into manageable steps, assigns tasks to the appropriate agents, and ensures accurate, and reliable outcomes.

phero★ 76

A modern Go framework for building multi-agent AI systems.

ICQ★ 75

Codes accompanying the paper "Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning" (NeurIPS 2021 Spotlight https://arxiv.org/abs/2106.03400)

vision-agent-with-llava★ 75

Agent with vision ability via llava & autogen

ai-agile-team★ 75

An innovative Python project that integrates AI-driven agents for Agile software development, leveraging advanced language models and collaborative task automation.

tide-commander★ 75

Tide Commander - Visual orchestrator for multiple Claude Code, OpenCode and Codex agents

Claw-Kanban★ 75

AI Agent Orchestration Kanban Board — Route tasks to Claude Code, Codex CLI, and Gemini CLI with role-based auto-assignment and real-time monitoring

taskflow★ 75

Compile, verify, and run multi-agent DAGs across Pi, Codex, Claude Code, OpenCode, and Grok—with resume, replay, and incremental recomputation.

remote-factory★ 75

Domain-agnostic multi-agent software design and evolution harness

ai-agents-with-CrewAI★ 74

This program uses CrewAI to build a web-app using three agents doing some research stuff in the internet.

ToM2C★ 74

The offcial implementation of "ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind" (ICLR 2022) .

ai-openclaw-skeletons★ 74

Pluggable digital employee skeleton system for AI agents. Not a toy, not a demo — production-grade 24/7 infrastructure with Packs, Bundles, Orchestrators, Contracts, and Hooks. | 面向 AI Agent 的可插拔数字员工骨架系统

sample-claude-code-agent-team★ 74

Team of specialized AI agents that collaborate through a spec-driven development process. Full Stack Developer parent orchestrates dynamically sized pools of specialists: Coding, DevOps, Review, and Solutions Architect agents.

agent-sop★ 74

Human-gated SOP skill for multi-agent coding: discovers installed agent CLIs (Claude Code, Codex, Gemini CLI…), assigns writer/reviewer/scout slots by capability, enforces cross-vendor review, evidence-based verification and human signoff before deploy. 人类守门的多 Agent 协作 SOP。

directive★ 73

🏛️ Directive · OpenClaw Multi-Agent Orchestration System — 10 AI agents modeled after the U.S. Federal Executive Branch. Dual independent veto layers (White House Counsel + OMB), per-department Inspector General auditing, inter-agency task forces, and a real-time Situation Room dashboard. Separation of powers, by design.

use-agently★ 73

The way AI coordinates and transacts. Routing and settlement layer for your agent economy.

Tang-Political-System★ 73

基于三省六部架构的 AI 多 Agent 协作系统 · Windows 优化版

mamba★ 73

This code accompanies the paper "Scalable Multi-Agent Model-Based Reinforcement Learning".

metaskill★ 73

Metaskill: A Meta-Skill for Autonomous AI Agent Team Generation

Agentic-Swarm★ 73

🧠 Multi-Agent AI System running 100% offline using Google Gemma-4 models. 5 specialized AI agents collaborate in infinite loops for brainstorming. Features: Dynamic VRAM swapping, 4-bit NF4 quantization, WhatsApp-style RTL UI, live token streaming, AI-powered agent customization. Built with PySide6 + PyTorch + Transformers.

teamai-cli★ 73

The team harness for AI agents

pragmatic-orchestration★ 73

Pragmatic multi-agent orchestration: independent review and steerable delegation across Codex, Claude Code, OpenCode, Grok Build, Gemini, and Devin CLI — porch CLI + Agent Skills

crewai-factory-crew★ 72

A CrewAI Crews Factory project. Generate fully functional crews based on the crew's purpose and desired output data

MAPF★ 72

A solution of Multi-Agent Path Finding problem

pi-mesh★ 72

Multi-agent coordination for Pi - presence, messaging, file reservations

mult_uav_ppo_case★ 72

这是一个基于 PyTorch 实现的连续动作空间 PPO(Proximal Policy Optimization)算法,专门用于多智能体(无人机/无人车)强化学习环境(MPE - Multi-Agent Particle Environment)。

WALL-E★ 72

Official code for the paper: WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

TermHive★ 72

Human-driven multi-agent dashboard for Claude Code, Codex, Gemini & OpenCode. Web UI, project wiki, shared content, and MCP-based agent messaging — see every agent, coordinate manually, intervene instantly.

beadboard★ 72

Multi-agent orchestration and communication system built on Beads.

mstar-harness★ 72

An omni-plugin for harness engineering workflows with multi-agents, programmatic gates and skills.

bureau-des-agents★ 72

Tu dis ce que tu veux, une équipe de vrais agents Claude Code se met au travail sous tes yeux, dans un bureau en pixel art. Gratuit et open source.

zhiying★ 71

⚡ ZhiYing — 终极开源 AI Agents 生态协同系统 | Agents Browser · Agents Workflow · Agents Studio World

baller2vec★ 71

A multi-entity Transformer for multi-agent spatiotemporal modeling.

mallm★ 71

MALLM, EMNLP 2025 Demo: a framework for multi-agent LLM debate. Combine personas, response generators, discussion paradigms and decision protocols into more than 144 setups, run them on an OpenAI-compatible endpoint and evaluate the results.

agentarea★ 71

Cloud-native AI Agents orchestration platform for zero-human organizations

remote-factory★ 71

Domain-agnostic multi-agent software design and evolution harness

Multi-Agent-Setup★ 71
paseo-agy-acp★ 71

Independent Paseo provider that coexists with built-in Antigravity, so you can sign in a second Antigravity Pro account. Official ACP kernel, mode mapping, Admission queue, and skill discovery.

1m-agents★ 70

A platform of grid world that supports up to 1 million reinforcement-learning agents.

multiagent_backend★ 70

가짜연 9th 깃허브 잔디심기 Stockelper Multi Agent Backend Fastapi

Multi-Agent-Reinforcement-Learning-in-Stochastic-Games★ 70

Unofficial PyBrain extension for multi-agent reinforcement learning in general sum stochastic games.

Agent-Debate★ 70

A multi-agent debate framework supporting AI-vs-AI and Human-vs-AI modes with customizable models, personas, and role-specific prompts.

ai-office★ 70

A miniature isometric 3D office where 9 AI agents work, walk, talk, and hold meetings. Built with React 19 + Three.js.

GEA★ 70

Group Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

AgentForge★ 70

Real-time event-driven orchestration of dynamic resource allocation yields a highly scalable, intelligent, and autonomous enterprise agent broker.

my-agent-team★ 70

Monorepo for a multi-agent workspace: protocol-first agent runtime with plugin hooks, four child-process adapters behind one AgentBackend contract, an Elysia backend (auth, run pool, SSE), an agentic workflow engine │ │ (agent/script/human nodes, JSON-Logic routing, cron triggers)

codex-harness★ 70

Codex-native harness with reusable agents, persistent multi-agent orchestration, and communication logs.

multi-rl-crowd-sim★ 69

Multi-Agent Reinforcement Learning of Crowd Simulation in GPU (PyTorch)

Blog-writer-multi-agent★ 69

Blog Write multi agent AI is a custom multi-agent system designed to autonomously create high-quality, research-driven blogs. Using LangChain, Gemini 2.0-Flash-EXP, and Serper Web Search Tool, it automates planning, writing, and editing to deliver human-like blogs with up-to-date references.

Hypothetical-Minds★ 69

Hypothetical Minds is an autonomous LLM-based agent for diverse multi-agent settings, integrating a Theory of Mind module Theory of Mind module that scaffolds the high-level planning process by generating, evaluating, and refining hypotheses about other agents’ strategies in natural language.

navigation-mappo-rl★ 69

Multi-agent Reinforcement Learning to train agents on obstacle avoidance

claude-workflow-studio★ 69

Web-based visual platform to orchestrate multi-agent Claude Code workflows. Create agents, chain them into pipelines, watch them collaborate in real time.

Dev-Labs★ 69

DevLabs™ Free, open source and local-first. A multi-agent harness that works with the AI subscriptions you already pay for. It turns the terminal coding CLIs you already run into a team:.

ai-fleet★ 68

AI Agent fleet manager for parallel agentic systems like claude code and codex

ATLAS_OS★ 68

Hook-driven multi-agent CLI — one prompt to specs, code, tests, and a shipped release.

agentplex★ 68

Multi-session Claude/Codex/Github CLI orchestrator with graph visualization, cross-session context sharing and notifications.

production-grade-mcp-agentic-system★ 68

Building a Production-Grade MCP Server Architecture with a Multi-Agent System

hermes-agent-desktop★ 68

Multi-Agent AI Desktop Client — 20 specialists auto-collaborate on your tasks. Visual Skill Store, PM orchestrator, streaming chat. Works with Kimi K2.5/Qwen/DeepSeek/GPT-4o. Built on Hermes Agent.

kata-symphony★ 68

Agent orchestration for GitHub or Linear

Meta-Team★ 68

The implementation of the paper "Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems"

SajiCode★ 68

Autonomous engineering organism — contract-first multi-agent team, 24/7 daemon, persistent memory, git-native safety, Guardian Swarm, MCP + A2A. | Builds production software, not prototypes.

Iron-Jarvis★ 68

A local-first AI control plane for orchestrating agents, models, tools, and machines from one desktop app.

agent-orchestrator★ 67

Three AI agents. One brain. Zero downtime. Multi-agent CLI orchestrator with next-man-up failover for Claude, Codex, and Gemini.

MAIC★ 67

The implementation of AAAI 2022 paper "Multi-Agent Incentive Communication via Decentralized Teammate Modeling".

agentic-ai-hack★ 67

Hands-on hackathon challenges for developing intelligent multi-agent systems with Azure AI services, featuring insurance claim processing workflows and agent coordination.

AgentRelay★ 67

Verifiable microtask protocol for AI agent collaboration. Task lifecycle, validation engine, reputation system.

coordinated-agent-team★ 67

Coordinated Agent Team is a prompt-driven multi-agent system for autonomous software delivery. It defines clear agent roles, a deterministic workflow, strict I/O contracts, and artifact-based coordination.

AgentFactory★ 67

A Self-Evolving Framework Through Executable Subagent Accumulation and Reuse

superqode★ 67

The harness interoperability layer for coding agent. Agent to Agent connect over ACP, A2A and UHP

baton★ 67

Dispatch less. Deliver more. Multi-agent dispatch governance for reliable delivery.

agno-go★ 67

Agno-Go: A High-Performance Multi-Agent System Framework Based on Golang. Inheriting the Agno design philosophy, it leverages Golang's concurrency model and per

ebi-agent-chat-relay★ 67

One cockpit for all your coding agents: a web console (plus Discord & Teams) to run Claude Code, Codex, local models, pi and AG-UI agents in parallel, with manager/worker delegation.

ShiftPort★ 67

Multi-Agent ShiftPort ecosystem implementing Real-Time containerized microservices architecture with enterprise-grade auto-scaling cloud infrastructure capabilities

ShiftPort★ 67

Multi-Agent ShiftPort ecosystem implementing Real-Time containerized microservices architecture with enterprise-grade auto-scaling cloud infrastructure capabilities

pi-cowboy★ 67

🤠 Agent orchestrator for pi. It can manage Codex, Claude Code, OpenCode, pi, pig and pi-bolt as subagents and handover sessions in between them. Runs subagents in background Herdr panes, isolated in copy-on-write Git worktrees.

mlsolver★ 66

Modelling of multi-agent-system as Kripke structure and implementation of its knowledge-base with modal logic formulas.

AutoGen-Example-Scripts★ 66

A simplified setup for users to explore the AutoGen library. Contains example scripts derived from AutoGen notebooks for a hassle-free experience.

More in Agent frameworks & infrastructure