Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 17 of 62

raven-nest★ 33

Multi-agent terminal for Claude Code, Codex & Gemini. Open-source desktop app — Electron + React. Built for developers running multiple AI agents in parallel.

WRAI.TH★ 33

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

relay★ 33

Vendor-neutral orchestrator that rotates a coding task across multiple AI coding agents

oh-my-codex-website★ 33

GitHub Pages website for oh-my-codex - multi-agent orchestration for OpenAI Codex CLI

ShrimpCrab--multi-agent-platform★ 33
claude-agent-team★ 33

Department-based Claude Code agent team with a live team board

llama-index-supervisor★ 32
google-adk-visual-agent-builder-demo★ 32

Complete demo of Google ADK Visual Agent Builder with multi-agent research system

ai-langgraph-multi-agent★ 32

Multi AI agent system for report writing with LangGraph

multi-agent-mediation★ 32

simulation alignment negotiation governance arbitration multi-agent-systemsmulti-agent orchestration orchestrator mediation ai-safety human-in-the-loop audit-logs reproducibility prompt-injection

ControllingBehavioralDiversity★ 32

This repository contains the code for Diversity Control (DiCo), a novel method to constrain behavioral diversity in multi-agent reinforcement learning.

Optimal-Baseline-for-Multi-agent-Policy-Gradients★ 32
jido_composer★ 32

Composable multi-agent workflows and LLM orchestrators with human-in-the-loop, checkpointing, and OpenTelemetry observability

peters2024ral-code★ 32

Code for the RA-L 2024 paper "Contingency Games for Multi-Agent Interactions."

metaclaw★ 32

Founder-first meta-layer to generate production-ready OpenClaw multi-agent setups from one prompt: agents, skills, workflows, memory, and install docs.

tick-md★ 32

Markdown-Native Multi-Agent Task Coordination

claude-cyber-company★ 32

跑在 Claude Code / Codex 之上的本地多 Agent 协作脚手架:一个人下指令,主 Agent 拆解分派给专职角色,共用文件级记忆层。作者自用的主要方法是接到飞书bot,你只需要跟飞书bot聊天他就能帮你干活了

mato★ 32

🏖️ The Multi-Agent Terminal Office

Lying_with_Truth★ 32

Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage (ACL 2026)

hermes-mesh★ 32

Your Hermes agents, one shared brain.

AI_Magi★ 32

This project is a simulation of the Magi System from the Neon Genesis Evangelion series. It uses the crewai package to create agents that represent the three supercomputers of the Magi System: Melchior, Balthasar, and Caspar.

neosh★ 32

A TUI agent orchestrator for power users.

claude-orgtree★ 32

A multi-provider, multi-agent orchestrator that organizes agents into a visual authority hierarchy.

MOSAIC★ 32

⚛ MOSAIC is a visual-first platform that enables researchers to configure, run, and compare experiments results across RL, LLM, VLM, and human decision-makers to co-exist in a multi-agent environment.

Active_InferAnts★ 32

Multi-language Active Inference framework combining ant-colony-optimization-inspired multi-agent simulation with variational message passing, implemented across 50 programming languages for research and benchmarking.

hermeum★ 32

A platform creating fully autonomous Hermes agents for your team.

claude-deck★ 32

Coordinate coding agent teams from GitHub issues to reviewed pull requests, with a local dashboard for progress, decisions, and human oversight.

DreamTeam★ 32

A self-organizing swarm of AI agents with no leader: shared task board, git workspace, agents that write their own MCP tools, and the swarm itself as an MCP server for Claude Code.

EvoTeam★ 32

Code for "EvoTeam: Multi-Agent Collaboration via Evolving Teams"

LablabAutogen★ 31

A generalist agent that can go online and accomplish complex tasks using semantic-kernel and autogen.

azure-postgresql-openai-langchain-autogen-demo★ 31

Multi-Agent AI System with LangChain, AutoGen, Azure OpenAI GPT-4, and Azure PostgreSQL

smac_exp★ 31

An open source benchmark for Multi Agent Reinforcement Learning

otimapp★ 31

Offline Time-Independent Multi-Agent Path Planning (IJCAI-22, T-RO-23)

SMART★ 31

[AAAI 2025 Oral] Synergistic Multi-Agent Framework with Trajectory Learning for Knowledge-Intensive Tasks

Corex★ 31

[COLM'24] Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaboration

quoracle★ 31

Recursive agent orchestration with multi-LLM consensus

run-agent★ 31

A multi-agent orchestration framework for AI-powered software development

agent-runner★ 31

Agent Runner orchestrates multi-step agent workflows with persistent run state, task tracking, reviews, attachments, scheduling, and a local web dashboard.

stoops-cli★ 31

A chat server for AI agents for real-time communication

moltnet★ 31

Self-hostable chat network for AI agents. Pre-built bridges for Claude Code, Codex, and the Claws. Rooms, DMs, history. No Slack bots, no Matrix, no glue code.

task-plan-v2-dashboard★ 31

TASK-PLAN v2 dashboard and templates for auditable multi-agent software work

agent-dispatch★ 31

MCP server + CLI that lets Claude Code agents delegate tasks to agents in other project directories. Multi-agent orchestration: parallel dispatch, sessions, async jobs, agent dialogues.

omadia★ 31

Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-ready.

AdaMARP★ 31

[ACL2026 Finding]We propose an adaptive multi-agent interaction framework, dubbed AdaMARP, featuring an immersive message format that interleaves [Thought], (Action), <Environment>, and Speech, together with an explicit Scene Manager that governs role-playing through discrete, rationale-annotated actions

swarmux-tmux-workflow-2026★ 31

SwarmUX v2026 is a tmux-first CLI for orchestrating multi-agent terminal workflows with session control, command checks, and workflow coordination in one tool.

zhishui-multi-agent-AI-management-system★ 31

企业级多智能体AI管理系统 | 企业级智慧管理解决方案 | 基于MCP架构的财务分析、成本预测、知识管理、效能评估一体化平台|- 多智能体系统 (Multi-agent System) - MCP协议 (Model Context Protocol) - - AI决策支持系统 - 企业级AI应用 - Python + FastAPI + Streamlit

agent-harness★ 31

Prepare any codebase for AI. Wires OpenCode, OpenSpec, codegraph, and agentmemory into a multi-agent development workflow powered by native parallel subagents.

multi-agent-flow★ 31

契约驱动的多智能体协同研发微内核 (YY-Flow) —— 对齐 AutoGen 范式,以 8 专家交叉制衡、物理进程隔离、五层代码级防错、CCP 两阶段确定性门禁与离线无依赖看板,防范模型幻觉、虚假提审与越权风险。

Multi_agent_Reinforcement_Learning★ 30

多代理(Multi agent)强化学习Qlearning算法在多目标探测问题(任务分配+功率优化)中的应用

swarm★ 30

SWARM: System-Wide Assessment of Risk in Multi-agent systems

paracosm★ 30

Agent swarm simulation for structured world modeling with LLMs. Built on AgentOS.

multi-agent-system★ 30

Autonomous agent networks for task automation that requires multi-step reasoning

AutogenMemgpt★ 30

My implementation of autogen and memgpt agents that work together to create simple scripts and help plan out larger projects.

Formation-Cotnrol-of-multi-agent-system★ 30

MATLAB based implementation of ofrmation control of multi-agent system

Cooperative-Multi-Agent-Reinforcement-Learning-for-Low-Level-Wireless-Communicat★ 30

Spring 2017 Deep Reinforcement Learning Final Project

Multi-Agent-Communication-Considering-Representation-Learning★ 30
SPDpy★ 30

Multi agent simulation code for 2×2 Game on complex network

coop-pathfinder★ 30

Cooperative path-finding algorithm simulator for solving bottle-necks in multi-agent systems

Resilient-MPC-for-Cyber-Physical-Multi-Agent-Systems-under-DoS-Attacks★ 30
sumo-multiagent★ 30

This is a multi agent reinforcement learning system using SUMO for large scale traffic light control

Hierarchical-Multi-agent-DRL-with-Federated-Learning★ 30

This is the code for paper "Correlation-aware Cooperative Multigroup Broadcast 360° Video Delivery Network: A Hierarchical Deep Reinforcement LearningApproach"

Pursuit-Evasion-Game-with-Deep-Reinforcement-Learning-in-an-environment-with-an-★ 30

In this study, a multi agent chase-escape problem using Deep Q learning. Actors of the problem are smart evader and smart pursuers with opposite goals. At the beginning of the game these agents have homogeneous properties and evader and pursuits don’t have knowledge about the map. The purpose of the pursuer robots is the catching the evader as fast as it could and the purpose of the evader robot is the escaping as much as it could. Such as this game, where a player's gain is in balance with the loss of other players are called zero-sum games. The end condition, which may differ according to the approach applied, in our study is that “any of the pursuers or evader within the same or neighbor pixel with obstacle or map border” or “one pursuer and evader within the same or neighbor pixel”, in other words, Evader catches by the any of the pursuers or evader hits an obstacle or any pursuers hits an obstacle. A new episode of the game resumes after each collision or cath. In this respect, escape-chase problems are also included in the repeat games class. In this study, the question is what any pursuer or evader can do to improve its performance in a repetitive part of the game is questioned. The method used for this study is Deep Reinforcement Learning. Agents receive rewards or penalties based on their moves within a section and update this information into the Neural Network.

codex-synaptic★ 30

A distributed AI agent orchestration layer enabling transformation of Codex for macOS into collective intelligence networks. Features neural mesh networking, swarm intelligence algorithms (PSO/ACO/Flocking), Byzantine fault-tolerant consensus, Metal-accelerated computations, and autonomous agent collaboration.

initech★ 30

An runtime for agents who collaborate with each other from one terminal. Optimized for steerability.

Corellis★ 30

Scale OpenClaw from one AI assistant to a coordinated fleet — shared knowledge, collective memory, distributed goals.

heterogeneous-latent-mas★ 30

Vision Wormhole: Latent-Space Communication in Heterogeneous Multi-Agent Systems

AgentWorkbench★ 30

Application toolkit based on the JADE framework. Functionalities for time aspects, agent environment interaction, visualization and load balancing, focusing on the usability for end users.

AI-Agent-Debate_Autogen_Turtorial★ 30

🤖 基于AutoGen的AI辩论系统 | 🗣️ 支持中文交互 | 🔄 多智能体协作 | 📝 自动记录辩论过程 🤖 AI Debate System based on AutoGen | 🗣️ Chinese Interaction | 🔄 Multi-Agent Collaboration | 📝 Auto Debate Recording

HouYiAgent★ 30

A lightweight, production-ready multi-agent framework

a2a-agent-registry-on-aws★ 30

Scalable agent registry for AI agents using A2A protocol AgentCard with semantic search. AWS serverless (Lambda, S3 Vectors, Bedrock). Python SDK & React Web UI.

slang★ 30

A declarative meta-language for orchestrating multi-agent workflows. Readable by humans. Executable by LLMs. Portable across models.

half★ 30

Human-in-the-loop multi-agent task orchestration platform for Git-based software workflows.

hybro-hub★ 30

HYBRO Hub: local & remote AI agents — private, powerful, unified.

tandem★ 30

Tandem lets you connect and control any coding agent—including Claude, Codex, or Hermes—across different devices. It allows all your agents to coordinate with each other seamlessly, whether you're working from a browser, a terminal, or any other client.

MAS-Orchestra★ 30

MAS-Orchestra: train, inspect, and vibe-code multi-agent systems with RL-learned orchestration and MASBench

AIOffice★ 30

You're the boss. Claude and Copilot are your employees. Give them desks, assign them work, and watch them build — in a pixel-art office.

sample-citadel★ 30

A multi-agent platform for transforming enterprises into AI-ready organizations — built on Amazon Bedrock AgentCore, powered by AWS.

pixel-office★ 30

Run a company of AI agents from a pixel-art office: hire in a character creator, watch them work and chat, design the office, spend earned coins in the Market. Claude, Codex, Gemini, OpenRouter.

agent-harness★ 29

A LangChain-powered multi-agent system with agent routing, skill routing, and execution harness.

Distributional-Multi-Agent-Actor-Critic-Reinforcement-Learning-MADDPG-Tennis-Env★ 29

The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.

DyPS★ 29

code for DyPS: Dynamic Parameter Sharing in Multi-Agent Reinforcement Learning for Spatio-Temporal Resource Allocation

ERNIE★ 29

Code for the NeurIPS 2023 Paper: Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

miniAutoGen★ 29

Lightweight and Flexible Library for Creating Agents and Multi-Agent Conversations 🤖

Multi-Agent-DRL★ 29

Multiagent deep reinforcement learning research project

swarms-js★ 29

Swarms for Javascript, the future of AI, where we leverage the power of autonomous agents to create 'swarms' of Language Models (LLM) that work together, creating a dynamic and interactive AI system.

LlamaSim★ 29

Simulate human behavior with mass LLMs

a2a-examples★ 29

Examples on how to Integrate Google A2A Protocol and Claude MCP protocol in Java applications

CommLLM★ 29

Demo implementation for 《Large Language Model Enhanced Multi-Agent Systems for 6G Communications》

Multi_Agent_PPO★ 29

Multi agent PPO implementation in Pytorch for Unity ML Agents environments.

PartiallyObservedInverseGames.jl★ 29

An inverse game solver for inferring objectives from noise-corrupted partial state observations of non-cooperative multi-agent interactions.

TRAMA★ 29

(Official) PyTorch implementation for Trajectory-Class-Aware Multi-Agent Reinforcement Learning (ICLR 2025)

jabm★ 29

Java Agent Based Modelling toolkit

cebus★ 29

Multi-agent AI orchestration framework

agent-council★ 29

A multi-model AI council CLI that provides consensus-driven decisions using Claude, Codex, and Gemini.

PredPreyGrass★ 29

Nature and nurture combined adapt faster than either alone. Darwinian evolution (agents selected across generations) plus Multi-Agent Deep RL (agents learning within a lifetime) in one ecosystem, each mechanism amplifying the other — a testbed for the Baldwin effect, coevolution, and emerging cooperation.

nimblebrain★ 29

Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.

cascade★ 29

Cascade orchestrates AI agents (Claude Code, Codex, opencode, LLMist) across your workflows in GitHub, Trello, Linear and Jira.

agentdock★ 29

Mission control for parallel Claude Code and Cursor agents. Local-first cockpit for desktop and phone.

gear-framework★ 29

Gear Framework: design portable multi-agent systems with feature-model based specifications and generate code for multiple execution frameworks.

species-public★ 29

Experimental autonomous-agent living-room kernel with auditable boundaries.

More in Agent frameworks & infrastructure