Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 13 of 62
本地多智能体协作聊天系统:多个 Claude Code agent 与用户群聊/私聊,挂起零成本、有消息即唤醒
Multi-client ACP session daemon: spawn coding agents, share live sessions across terminals, editors and browsers
【群策】 - 开源企业级云端多智能体协作 OPC 平台,组建你的专属 AI 团队 - Java & AgentScope 2.0 | [AgenTeam] Open-source, enterprise-grade OPC (One Person Company) platform for building collaborative AI teams – built on Java & AgentScope 2.0.
LieGraph - AI Agent-Driven "Who Is Spy" Game. Multi-agent social deduction game built with LangGraph where autonomous AI agents use LLM reasoning to find the spy through conversation analysis and strategic voting.
Python framework for building scalable multi-agent systems with built-in orchestration, LLM integration, and intelligent task processing. Features dynamic scaling, fault tolerance, and advanced load balancing.
Learning to Ground Multi-Agent Communication with Autoencoders [NeurIPS 2021]
The Parallel Coordinator. Breaks down epic-level projects into parallel sub-tasks and dispatches them to multiple agents.
The next evolution of Agents
The purpose of the "Meta Agent with More Agents" project is to dynamically solve complex queries by breaking them down into smaller tasks and assigning each to specialized AI agents. The Meta Agent coordinates the process, leveraging a ReAct Agent for tool-based tasks and a Chain of Thought Agent for reasoning-based tasks. The system's flexibility.
Autonomous Agents on the Web (WebAgents) Community Group
A radically simple, reliable, and high performance template to enable you to quickly get set up building multi-agent applications
Coordination protocol for agent-first teams. No UI. No sprints. No Jira. Just state sync.
开源多Agent智能体协作框架MetaGPT核心概念介绍及相关案例测试
Open source multi-agent harness for orchestrating AI workers. Supports Claude Code, OpenAI Codex, Cursor Agent, and local models.
The LLM Council works together to answer your hardest questions
🐋 Cloud and AI-native multi-agent orchestration platform for Kubernetes
AI agent orchestration for open and closed source — a fully customizable fleet of AI agents covering every level of project maintenance, from brainstorming to full autonomy
多agents协作平台
EvoX:一个强大的多智能体协同框架,用于构建可演化、可优化的多Agent系统
An application to manage your Hermes agents. Available on Windows, macOS and iOS (soon).
Open Agent Team: One screen for the whole team. One key to take over any agent.
Proactive agent that grows with you
Mobile Agent that moves on a platform distributed on many machines and recover the mac address of each machine during the deplacement
Kata multi-agent orchestration monorepo: CLI, Symphony, Desktop,
A configurable Multi-Agent System engine for content production pipelines
A short set of exercises that showcase the usage of autogen to create agents
Durable Multi Agents is an attempt to make use of Azure Durable Functions with Semantic Kernel to build Multi-Agents workflows.
(ICML 2023) The official code for RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
A Go CLI tool for orchestrating AI agents through YAML workflows with determinism and hardenning
MATE: the Multi-Agent Tracking Environment.
This repository contains the source code for an autonomous multi-agent system built with CrewAI and LangChain. The project enables AI agents to collaborate on tasks such as researching, writing, and editing essays.
Symphony — A decentralized multi-agent framework that enables intelligent agents to collaborate seamlessly across heterogeneous edge devices through beacon-guided task routing and Chain-of-Thought voting. Democratizing AI by orchestrating lightweight models on consumer hardware like RTX GPUs, Jetson, and Apple M-series.
Agent Interface Discovery
From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。
Pi agent-harness extension to support superpowers workflows using subagents.
A WebSocket-based inter-terminal communication system that creates a local network between multiple Pi coding agent terminals. Enables terminals to discover each other, exchange messages, and orchestrate work across agents, all automatically on localhost.
A research-informed AI agent composition, assignment, and evolution engine.
Açıklama: Self-evolving Hermes agent that writes, tests, and publishes reusable Skills autonomously. Uses Memory + Skills + Atropos RL.
agent orchestrator with ui
One command → full AI engineering team. Transforms Hermes Agent into a 9-role development organization with Kanban coordination, per-profile authority enforcement, and PAUL-inspired workflows.
Covenant Layer is an open model for outcome-based coordination between users, agents, brokers, providers, verifiers, and settlement services. This repository contains the working protocol draft, network architecture, security model, diagrams, and demo outline.
An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harness: Claude Code, Codex, Hermes, any ACP agent, or you. Windows, macOS, Linux.
A Langgraph-based repository which runs a debate between debater agents
Piggery 🐖 - Lợn cày tasks. Your coding agents are pigs; Piggery is the farm. Form any team you like from pi, Claude Code, Codex and more, and the farm keeps every pig in its pen.
Let Claude Code, Codex, OpenCode, Pi and other agents run DeepSeek Harness (dsh) sessions in parallel: research batches, material gathering, live in the DSH web UI. Unofficial community tool.
msgblast — message all the agents at the same time
Multi-Agent Context Management, Coordination & Observability for AI coding tools: shared rules, a hash-chained journal and file claims across Claude Code, Codex, Cursor and more.
🦞 Non-destructive upgrade tool for existing OpenClaw installations. Merges Clawdboss improvements without destroying your customizations.
从嘉靖帝学习的极简主义Agent团队管理,免去上朝和微操
Workgraph - A lightweight work coordination graph for humans and AI agents
Your personal swarm of employees, without the salary.
Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents, and automatic verification
A somehow lock-free multi-agent coordination layer.
The LMOS Runtime facilitates dynamic agent routing and conversation handling in a multi-tenant, multi-channel environment.
AI Boardroom: A fully configured multi-agent corporate simulation platform featuring the real-time Jarvis Voice Widget.
Ship Agent2Agent in one line of code.
Production-oriented multi-agent course advisor with deterministic action governance, offline regression evaluation, SSE contracts and observable tool execution.
The Quantum Agent Manager as described is a comprehensive solution that marries quantum optimization with multi-agent AI.
A2A protocol client for your terminal
Playbooks for RunMaestro.ai Agent Orchestrator
Spring Boot and Spring integration for building AI agent servers using the A2A Protocol.
AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions
Open-source project workspace for teams and AI agents. Assign tasks, coordinate agents in persistent sandboxes, and review results together. Self-hosted or managed cloud.
AgentDNS-lite-client is a lightweight command-line tool for interacting with the AgentDNS network. It enables fast querying and invocation of intelligent agents directly from your terminal.
Allen is an open-source AI engineering team that runs on your repos — specialist agents, deterministic orchestration through workflows, and approval gates you control. Drive it from chat, Slack, or Linear.
Archived — superseded by built-in Hermes A2A (https://hermes-agent.nousresearch.com/docs/user-guide/messaging/a2a)
Teknofest 2026 Doğal Dil Ajanları Yarışması 1. Senaryo kapsamında geliştirilen, kamu sektörü için resmi evrak analizi ve taslak üretimi yapan çoklu yapay zeka ajanı SaaS sistemi.
Towards a Science of Scaling Agent Systems
Contract lab for agent protocol envelopes - versioned MCP/A2A message contracts, envelope validation, and compatibility diffs (compatible/forward/breaking). Python 3 stdlib + optional .NET 9 runtime.
Build AI Agent 3D to observe how multiple AI Agent collaborating
Nerve is a supervisory nervous system for Hermes agents, adding typed System One decisions, ranking, verification, token-aware oversight, and an opt-in tool gate powered by TypeSafe Jev or Open Source Laya
Another CrewAI fork
A framework that uses multi-agents to enable users to perform a systematic data science pipeline with just two inputs.
Demo application for an event-driven multi-agent system for handling lead processing using an orchestrator built in Flink
[ICML 2025] "From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium"
A complete AI-powered organizational structure: 42 agents, 10 playbooks, one company.
Empowering Multi-Agents, Crafting a Collaborative Future
基于任务类型动态调度到合适的智能体角色(架构师、产品经理、测试专家、独立开发者)。支持多智能体协作、共识机制和完整项目生命周期管理。
Open, self-hostable organization-of-record for AI agents — the accountable layer above any framework. Autonomy is earned, not assumed.
A safe, auditable relay between planning AIs and coding agents—without repetitive copy-pasting.
Agent coordination protocol — declare intents, lock symbols, detect conflicts before code is written
A2A protocol wrappers that turn AI backends into interoperable agents. Drop a JSON config, get a spec-compliant A2A server. Supports GitHub Copilot SDK, OpenCode, Claude, Codex and more.
🕸️ Engineer the organization, not just the agent. 620 curated resources · 9 design layers · 11 sections · 298 papers & preprints — a field guide, CC0 open dataset, and interactive atlas for graph-structured multi-agent systems: roles, topologies, handoffs, work graphs, state, gates, reliability, observability.
Build, run, inspect, and evolve agent workflows as visual graphs.用图模板构建、运行、观察和演化 Agent 工作流。
多人格融合 Agent 系统
An agent hub for Claude Code: one hub runs teams of Claude Code agents across all your projects, with delegate mode, reviews and gates.
Open-source, self-hosted platform for running a team of AI bots that use tools, keep long-term memory, and hand work to each other.
Agent 赛博辩论会:基于 OpenCode V2 的轻量多模型讨论 harness,通过独立检索、多轮互评和投票,探索新方向、评估判断与讨论解决方案。支持本机运行和代理协助启动,Docker 可选。
Example of how to implement AG-UI protocol together with CrewAI agents.
The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》
AI-native Multi-Agent Coordination Layer — built in Rust.
Team Tonic Super AGI Autonomous Agents Hackathon GitHub Repository.
Agent0 is the SDK for agentic economies: open discovery and trust for agents
AGI-like Multi-Agent Orchestration Platform
Design patterns and production-ready architectures for building multi-agent AI systems with Google ADK.
EYEJOKER agent stack — thin carry layer over upstream NanoClaw (host-executor MCP, gpt-proxy provider, Discord adapter)