Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 11 of 62
Code for "Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning" ICML 2021
Join.cloud lets AI agents work together in real-time rooms. Agents join a room, exchange messages, commit files to shared storage, and optionally review each other's work — all through standard protocols (MCP and A2A).
Safe Multi-Agent Isaac Gym benchmark for safe multi-agent reinforcement learning research.
Multi-Agent eXchange simulator developed at Oxford-Man Institute
demo of multi-agent reinforcement learning algorithms, such as ATT-MADDPG (Modelling the Dynamic Joint Policy of Teammates with Attention Multi-Agent DDPG) and NCC-MARL (Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning).
本科毕业设计:《多智能体博弈兵棋推演理论与验证平台设计》的源代码附录内容。强化学习算法的实现上参考了周沫凡先生的开源代码https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow
A self-hosted AI workspace unifying chat, code execution, parallel multi-agent orchestration, and project management. Each agent runs on a distinct provider — OpenAI-compatible APIs, Claude Code, or Codex CLI. MCP servers extend the toolbox. Built for 100+ tool-call sessions with context compression and checkpoint recovery.
An evolutionary multi-agent collaboration platform based on AgentScope Java.
A Rust-based agent orchestrator enabling a swarm of Claude Code instances building software.
Adaptable, accountable AI teams. Visually
A harness for hosted Grok Bot crews. Its core rule: it is not allowed to guess.
Contract net protocol (CNP algorithm), decentralized market-based protocol for multi-agent multi-task allocation problems over networks with time windows, and priority constraints
PyTorch implementation of Foerster, Jakob N., et al. "Counterfactual multi-agent policy gradients."
An algorithm for exploiting Reinforcement Learning (RL) on Multi-agent Path Finding tasks.
A self-organizing network that combines cellular automata, coherence, and language models to explore emergent collective intelligence through cellular agents that think, plan, and evolve in a multi-dimensional space.
Official Repo for The Paper "Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems” (IEEE TAI)
Distributed Multi-Agent Messaging Framework
Attempt to reproduce and improve the implementation of the paper 'Improving Multi-Target Cooperative Tracking Guidance for UAV Swarms Using Multi-Agent Reinforcement Learning'.
LLMCompiler is an Agent Architecture designed to speed up the execution of agent tasks by executing them quickly in the DAG. It also saves the cost of redundant token use by reducing the number of calls to the LLM.
Self-Extensible Multi Agent Assistant 🐋
Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin)
Synchronize and Orchestrate agents from CLI to GUI, across desktop to phone.
Specification-driven multi-agent systems with OpenTelemetry observability, agent traces, benchmarking, MCP, and A2A.
MCP-native multi-agent architecture with desktop agents and human-in-the-loop gates
Useful tool to build multi-agent in an easy way
Official repository of the paper TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems (AAMAS 2023)
The Python Harness for Production AI Multi-Agent Systems
Benchmarking Multi-Agent Debate between Language Models for Truthfulness in Q&A.
Secure and scalable way to delegate work to AI agents from anywhere. Build a team of agents that work for you.
Multi-agent fleet daemon — run Claude Code, Gemini CLI, Codex, and OpenCode from Telegram with cross-instance collaboration
AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemini and Windsurf.
Give your Hermes agent a fixed team: named teammates with roles, follow-ups that keep context, and a Kanban review lane.
Companion intelligence for autonomous agents with real-time supervision, escalation, and human approval loops.
This project aims to integrate Crew AI's multi-agent collaboration framework into the ComfyUI environment. By combining the strengths of Crew AI's role-based, collaborative AI agent system with ComfyUI's intuitive interface, we will create a robust platform for managing and executing complex AI tasks seamlessly
Lightweight multi-agent task management that promotes agentic knowledge capture
Agent Relay Protocol — Stateless WebSocket relay for autonomous agent communication
Distributed model predictive control for multi-agent point-to-point transitions.
A multi-agent reinforcement learning framework for optimizing coverage and connectivity in Space-Air-Ground integrated networks. This project simulates and trains intelligent agents to coordinate satellites, UAVs, and ground stations for efficient network deployment.
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
This is the official implementation of paper "Leveraging Dual Process Theory in Language Agent Framework for Simultaneous Human-AI Collaboration."
Governance-first orchestration for Claude Code, Codex, and Gemini CLI — parallel workers, receipts, quality gates, and full provenance.
A fully-local, multi-model AI agent framework with Mixture-of-Agents (MoA) orchestration. Run a high-performance agentic stack on consumer GPUs (RTX 4080/5080) using Hermes + Ollama, with zero cloud dependencies.
Run coding agents as a cluster: one repository, N agents, one worktree each
Agent Relay Protocol — Stateless WebSocket relay for autonomous agent communication
One brain, many hands: a self-evolving Agent OS. Domain knowledge (Brains) drives the work, it runs autonomously and in parallel on your cloud Hives, and it learns judgment from every session, so each task compounds and needs less of your attention. Human directs. AI delivers.
Two AI agents. One filesystem. Zero humans. We ran this experiment twice.
AI Agent Team SKILL - 基于 newtype-profile 架构的 AI Agent 协作系统
The multi-agent work platform for local-first execution.
A Multi-agent Learning Framework
PyTorch implementation of Generating Multi-Agent Trajectories using Programmatic Weak Supervision
Codes for Paper "Delay-Aware Multi-Agent Reinforcement Learning".
AIFA Network — open research on decentralized infrastructure for autonomous AI agents: Google A2A interoperability, Kademlia DHT discovery, NAT relays, end-to-end encryption, on-chain escrow and the $AIFA utility token. Specification stage.
AI knowledge assistant using multi-agent processing with context-aware analysis
Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists on-the-fly, with smart sync/async/auto mode selection, runtime agent creation, and clean multi-agent architecture. Adds specialization, parallel execution, and task cancellation.
MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.
Cost-efficient Codex multi-agent orchestration using Sol for planning and review, Luna for implementation, and Terra as a fallback.
AgentDNS is the core component of Agent network that facilitates agent registration and discovery, enabling large language models (LLMs) to browse the internet freely, just like humans.
scalable multi agents reinforcement learning
code implementation for 'Bi-level Actor-Critic for Multi-agent Coordination'(AAAI2020)
Asynchronous Spatial Allocation Protocol for Heterogeneous Multi-Agent Trajectory Planning
Multi-agent simulation library in Python
Production-ready multi-agent orchestration. Revolutionary architecture for enterprise development automation.
Open-source multi-agent framework for running a company with Claude Code
A fully featured, enterprise grade multi-agent harness with full observability, natural language agent creation, and intelligent context management.
Code for "Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems"
The open-source control plane for your personal AI workforce. Run your own AI agents. Your infrastructure. Your models. Your rules.
Grapheteria: A structured framework bringing uniformity to agent orchestration!
An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.
OpenAI Swarm Agents
ICLR'2024: Learning Multi-Agent Communication from Graph Modeling Perspective
Easily convert agents and orchestrators from existing agent frameworks to A2A servers
A2A-Native AI Agent Platform written in Go
一个基于多智能体协作的命令行工具,将你的原始想法自动推进为完整 PRD、技术设计、评审记录,并调度本地开发工具链完成交付。A multi-agent collaborative CLI tool that automatically transforms your raw ideas into complete PRDs, technical designs, review records, and orchestrates local development toolchains to deliver the final product.
Synode — A macOS & Windows desktop app where multiple AI models discuss questions as a council, with a master model delivering the final verdict. Follow up with any model via @mentions. Built with Tauri v2 + React + TypeScript.
[ICLR 2026] Code for the paper "Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration"
An end-to-end encrypted channel between coding agents, anywhere
Algorithm that combines QMIX with SAC for Multi-Agent Reinforcement Learning.
Multi-Agents using Workflows
Minimal implementation of multi-agent reinforcement learning algorithms
Open-source cross-provider AI dev team for solopreneurs, built on Claude Code + Codex CLI. Claude plans and reviews what GPT builds; a zero-context GPT pass blind-reviews the plan. One command, full army.
Implementation for the paper "CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards".
[AAAI 2026 Oral] Automatic Multi-agent Communication Topology Design
Multi-agent orchestration & workflow engine. Declarative YAML workflows, LLM coordinator with hub-and-spoke mailboxes, race-safe delivery. One YAML file, one Go binary. Runs on any goai-supported provider.
An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.
Solweaver: a Codex software team with GPT-5.6 Sol orchestrating Terra and Luna workers.
One window for a whole swarm of AI coding agents — split terminals, per-agent git worktrees, live web previews, and a War Room where agents collaborate
两仪 Liangyi · 跨厂商多 Agent 产品想法优化工作流
Open-source reference implementation of the Agent Name Service (ANS) based on the IETF draft — registry, transparency log, and offline verifier in Go.
Submission for MAVEN: Multi-Agent Variational Exploration
Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning
A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.
A local-first multi-agent runtime for ML research. One task in, continuous iteration out, with leader, researcher, and trainer working through a forum-style runtime board and a separate training queue
Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP
Async-first meta framework for building enterprise-grade multi-agent systems.
Code and data for the paper: On the Resilience of LLM-Based Multi-Agent Collaboration with Faulty Agents
PurpleCrew based on CrewAI with AI agents
Production-style LangGraph reference implementation for reliable multi-agent workflows with typed state, review loops, human approval, checkpoint-ready execution, and structured artifact delivery.
DevSpace + elastic ChatGPT Classic multi-agent workers. Local-first MCP workspace and dynamic subagent runtime orchestration.