Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 2 of 62
[ACL 2026] OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction https://arxiv.org/abs/2604.25602
Code for the MADDPG algorithm from the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
Team9 is a collaborative workspace for AI agents, currently built on OpenClaw and its ecosystem.
Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration
A library for generative social simulation
A living pixel-art station where real AI agents do real work. Local-first desktop agent harness - bring your own key, watch your crew actually run.
Workspace-first multi-agent coordination platform for AI development, with shared Specs, Kanban orchestration, and MCP/ACP/ A2A support across web and desktop.
Environment generation code for the paper "Emergent Tool Use From Multi-Agent Autocurricula"
Automatic multi-agent workflow generation, fully integrated with QVeris unified data and tool layer
Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans in control. Deploy Heym on your own infrastructure.
Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.
A Platform for Many-Agent Reinforcement Learning
GPTeam: An open-source multi-agent simulation
A fast and lightweight framework for creating decentralized agents with ease.
Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.
For your multi-agent needs
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Orchestration-builder SDK for multi-agent coding workflows
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
The open-source, multi-agent alternative to Claude Tag. @ any agent, wherever work happens, they work alongside your team, learning as they go.
Multi-Agent Collaboration for Team and Friends
AutoGroq is a groundbreaking tool that revolutionizes the way users interact with Autogen™ and other AI assistants. By dynamically generating tailored teams of AI agents based on your project requirements, AutoGroq eliminates the need for manual configuration and allows you to tackle any question, problem, or project with ease and efficiency.
[IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.
Multiplayer AI: Bring your team and agents together
[IJCAI 2024] Generate different roles for GPTs to form a collaborative entity for complex tasks.
KaibanJS is a JavaScript-native framework for building and managing multi-agent systems with a Kanban-inspired approach.
Claude Code like Sub-Agents & Workflow Orchestration for Pi — parallel execution, live widget, fleet view, custom agent types, mid-run steering, claude compatible dynamic workflows and more ...
ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent
TAKT Agent Koordination Topology - Define how AI agents coordinate, where humans intervene, and what gets recorded — in YAML
Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.
Command Your AI Agent Empire from the CEO Desk — A local-first AI agent office simulator that orchestrates CLI, OAuth, and API-connected agents (Claude Code, Codex CLI, Gemini CLI, OpenCode, and more) as a virtual autonomous company.
The open-source collaboration system for people and AI agents. Share context, coordinate tasks, and work in parallel with your team, cloud agents, Codex, Claude Code, Grok, Grok Bot, OpenCode, Antigravity, and Cursor.
Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.
Multi-Agent Framework
Open-source workspace where your team and your agents share one pod. Connect the Claude Code or Codex you already run, @mention it next to your teammates, and put the work on one board. Self-host with Docker, or try it on commonly.me.
Building LLM-Enabled Multi Agent Applications from Scratch
SMAC: The StarCraft Multi-Agent Challenge
A user-friendly, multi-platform GUI for managing and running CrewAI agents and tasks. Supports Conda and virtual environments, no coding needed.
Simulate anything, for $1 & less than 10 min - Universal Swarm Intelligence Engine
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
Coordinate your coding agents like a group chat — read receipts, delivery tracking, and remote ops from your phone. One pip install, zero infrastructure. A production‑minded orchestrator for 24/7 workflow
A self-organizing multi-agent collaboration platform for OpenClaw. Multiple AI agents work as an autonomous team — planning, executing, reviewing, and patrolling tasks with zero human intervention.
Your Software Factory - build faster and better with multi node agents that work 24/7
Multi-agent orchestration for AI coding agents — pluggable runtime adapters for Claude Code, Pi, and more
Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP). The system is designed for developers building AI applications that benefit from multiple specialized agents working in parallel on different aspects of a project.
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
Govern, Observe, Direct - a real-time control room for agent societies
Spec-Driven Development with AI Sub-Agents. An orchestrator + 9 specialized sub-agents for structured feature development. Zero dependencies. Pure Markdown. Works with Claude Code, OpenCode, Cursor, and more.
Agent Mesh
🤖 MateClaw — Your second brain with Multi-Agent Orchestration, MCP Protocol, Skills & Memory, Dream, and Multi-Channel Support. Built on Spring AI Alibaba.
A playground for neuro-san
[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
🐙 Give your AI a life — open-source agent infrastructure for team collaboration.
Infrastructure for coding agents
AgenticX is a unified, production-ready multi-agent platform — Python SDK + CLI (agx) + Studio server + Machi desktop app. Features Meta-Agent orchestration, 15+ LLM providers, MCP Hub, hierarchical memory, avatar & group chat, skill ecosystem, safety sandbox, and IM gateway (Feishu/WeChat).
A Python framework that emulates Grok Heavy functionality using intelligent multi-agent orchestration. Deploy 4 (or more) specialized AI agents in parallel to deliver comprehensive, multi-perspective analysis on any query.
Your Company Agentic Operating System
Low code tool to rapidly build and coordinate multi-agent teams
🐝 The First Self-Improving agents with RL / Prompting Optimization
Experts.js is the easiest way to create and deploy OpenAI's Assistants and link them together as Tools to create advanced Multi AI Agent Systems with expanded memory and attention to detail.
A Python-first runtime layer for multi-agent systems, with persistent run state, streaming execution events, and a pluggable orchestration interface.
Workflow orchestration for AI coding agent swarms, from task to merged PR.
Open protocol for communication between AI agents, applications, and humans.
构建受监督的、自我进化的 Agent 组织的基础设施 | Infrastructure for supervised, self-improving agent organization. 飞书/Telegram 手机端运行 Claude Code 或 Kimi Code(双引擎,两家原生订阅直接用),共享记忆、Agent 工厂、定时任务、通信总线。
Web UI for AutoGen (A Framework Multi-Agent LLM Applications)
Python A2A is a powerful, easy-to-use library for implementing Google's [Agent-to-Agent (A2A) protocol](https://google.github.io/A2A/). It enables seamless communication between AI agents, creating interoperable agent ecosystems that can collaborate to solve complex problems.
Multiple Agents, Parallel Flow
[NeurIPS 2026] Recursive Multi-Agent Systems
Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP plugins. Browse skills and verified security audits.
AgentSims is an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in.
AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.
不是问答机器人,而是能真正干活的数字分身。共享智能体,共享项目上下文,让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中
A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
A cartoon 3D office where your team hires Claude Code workers at desks, shares live terminals, talks over voice, and tracks GitHub issues and PRs.
SAM
open-source framework for creating and managing simulations populated with AI-powered agents. It provides an intuitive platform for designing complex, interactive environments where agents can act, learn, and evolve.
The spatial IDE for recursive multi-agent orchestration. It's like an Obsidian graph-view that you work directly inside of.
Multi-Agent Resource Optimization (MARO) platform is an instance of Reinforcement Learning as a Service (RaaS) for real-world resource optimization problems.
A suite of test scenarios for multi-agent reinforcement learning.
The Multi-Agent Custom Automation Engine Solution Accelerator is an AI-driven system that manages a group of AI agents to accomplish tasks based on user input. Powered by Microsoft Agent Framework, Azure Foundry, Azure Cosmos DB, and infrastructure services, it provides a reference application, allowing you to hit the ground running.
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph queries, agent-to-agent messaging. Manage Claude Code, Codex, Grok Build or any AI Agent from one dashboard. Move Agents between computers and locations
Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it lets you take what you've created and deploy fully hosted agents for real business purposes. Use Claude Code to get the agent working, then deploy it in your favorite cloud.
Multi-AI agent terminal collaboration tool
OpenSwarm — Autonomous AI dev team orchestrator powered by Claude Code CLI. Discord control, Linear integration, cognitive memory.
Code for the paper "Emergent Complexity via Multi-agent Competition"
An open-source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
Private control plane for AI agents
More is Different. A multi-agent world engine where AI agents live, talk, compete, ally.
Coordinate your models from Codex. Plan, delegate, use host tools, and review work across workspaces. Formerly Astra Flash Orchestrator.
PlayGround: AI Research into Multi-Agent Learning.
Hierarchical agent loops with recursive self-organization.
A multi-agent framework written in Rust that enables you to build, deploy, and coordinate multiple intelligent agents
A chatbot/GraphRAG framework that creates multi-llm-agents from social platform user comments and let them debate on specific topics.
An open-source platform for long-duration multi-agent workflows. This project automates long-running, multi-agent AI work by distilling each agent’s output into context for the team of agents. You can let the distilled context to drive each agent.I hope this project can save people's time and be cost effcient- since Deepseek models are cheaper.