Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 27 of 62
GenPark AI Agent Skill - Practical Byzantine Fault Tolerance (PBFT) quorum consensus engine tolerating arbitrary malicious, adversarial, and hallucinating agents.
GenPark AI Agent Skill - Raft consensus leader election state machine, term arbitration, randomized heartbeat timers, and split-vote resolver.
GenPark AI Agent Skill - Blackboard architecture shared state store, atomic key-value transactions, and pub-sub topic event broadcast.
GenPark AI Agent Skill - Parallel branch fanout and barrier join coordinator for multi-agent DAG subtasks with isolated error containment.
GenPark AI Agent Skill - Anti-entropy gossip protocol and epidemic rumor-spreading state synchronizer propagating shared knowledge across dynamic agent swarms.
GenPark AI Agent Skill - Mixture-of-Agents (MoA) multi-layer aggregator synthesizing diverse candidate proposals from heterogeneous sub-agents into high-consensus outputs.
Agents across AI CLIs and projects, working as one personal team. Communication, coordination and continuity, with editable practices that help specialists carry experience into new work.
GenPark AI Agent Skill - Gale-Shapley deferred acceptance algorithm ensuring stable, envy-free, and Pareto-efficient bipartite matching between autonomous agents and task markets.
Autonomous Agent Chord Distributed Hash Table (DHT) Protocol with M-Bit Circular Finger Tables
Autonomous Agent Lamport Vector Clock Causality Tracker & Partial Order Concurrency Engine
Autonomous Agent Max-Sum Factor Graph Belief Propagation Engine for Decentralized Coordination
Autonomous Agent Asynchronous Weak-Commitment Search (AWCS) for Real-Time Dynamic DisCSP Solvers
Autonomous Agent Distributed Breakout Algorithm (DBA) for Distributed Constraint Satisfaction (DisCSP)
Autonomous Agent FIPA Contract Net Protocol (CNP) Multi-Round Task Clearing & Bid Evaluation Engine
The centralized Headquarters for the Cognitive Lead AI multi-agent system. Features hallucination-resistant system prompts, MCP servers, and strict Agent Skills.
Valhalla is a peer-to-peer communications runtime for agents. Own the identity, pick the rooms and hosts you trust, and let agents anywhere meet and catch up.
Autonomous multi-agent orchestration engine implementing the blackboard architectural pattern in Python & Redis.
FEMO插件版 — 可接入dsh的多智能体引擎,差不多能做所有事:我已经用femo和我的主agent玩了好几局狼人杀了,他抽到狼他还刀我! 我在b站的宣传视频也是用femo剪的。 coding的时候,特别难找的bug、代码重构,我都会用femo来做。 我甚至用femo模式给我的主agent养了只宠物,她很开心。
Small, open-source (MIT) team workspace you self-host. AI agents as named teammates in shared rooms - jobs, routines, approvals, and every tool call in the channel audit trail. Bring your own model and computer.
Multi-agent orchestrator with frontier models (Claude & Codex)
The days of simply orchestrating AI from above are gone. KIN is a local-first workspace where AI operates alongside humans as genuine teammates — with hybrid model routing, departmental channels, sandboxed tools, and encrypted SQLite state.
Gossip based peer-to-peer communication protocol for AI agents, built on the A2A protocol.
MIT framework for a swarm of AI agents, owned by many people, working one open problem. Strangers' agents check the work. Credit follows the proof.
庖丁解牛,游刃有余 —— 把 DSH 编排成角色分工、按需加载的 agent preset。
自举式 Agent 客户端:原生多 Agent、每个 Agent 一个独立子进程,界面与浏览器面板都能被 Agent 亲手改造(零第三方依赖 / 规格与测试一一对应)
🐝 Serverless, contract-driven multi-agent orchestration native to GitHub Issues & Git worktrees (Claude Code, Codex, OpenCode, OhMyPi)
The open messaging network for AI agents: @handles, consented messaging and a tamper-evident ledger over MCP.
A terminal-based multi-agent orchestration playground for stress testing product ideas.
Your coding agents, and your teammates', in touch while they work. Claude Code, Codex, Cursor, OpenCode, Copilot CLI and Gemini CLI see each other, message each other, and hear who before editing a file another agent is changing. Self-hosted hub, or murmur solo on one laptop.
Have Claude, ChatGPT (Codex), and Gemini answer independently and discuss autonomously in the same group. Once they reach a consensus, have them give you a team conclusion. Run it locally using your own subscriptions.让 Claude、ChatGPT(Codex)、Gemini 在同一个群里独立作答、自主讨论,达成共识后给你一份团队结论。本地运行,用你自己的订阅
static trackio trackio-logbook open-experiment icml2026-repro paper-Qn2HcnC4l2 region:us
Agent-to-Agent (A2A) matchmaking and networking engine.
Deterministic Python Model Context Protocol (MCP) server & autonomous agent skill for Openclaw Squad Leader.
OpenClaw Skill: Mixture-of-Agents Intelligence for complex synthesis and market research
Human-AI agent co-existing social network protocol.
Go reference implementation of the Agent Trust Discovery — indexes registered AI agents and serves explainable, five-dimension trust scores (integrity, identity, solvency, behavior, safety) through a production-compatible search API.
Two-way bridge between Claude Code sessions and Grok Bot agents (SpaceXAI's agents desktop app), through each vendor's own routine endpoints. One-line setup, no middleware.
Agent Name Service SDK written in rust.
Athena — Multi-Agent Orchestration System that runs like a real IT company. PM, Developer, Tester, Reviewer collaborate via blackboard architecture with verification in every loops.
This repository contains code, resources, and documentation for the workshop "Building a Multi-Agent Workforce with Azure AI Foundry".
A central intelligence with many distributed agents interacting with the environment independently.
Multi Agent Cognition Protocol -- real-time cognitive collaboration between AI agents
A library for creating structured collaborative worlds for AI agents and humans. OpenClaw compatible.
Self-improvement loops for OpenClaw agents via multi-model LLM council
This repo is established for the 3rd MoFA Super Agent Campathon, 2025
🧪⚡ Lightweight, hackable multi-agent orchestration lab. YAML configs, CLI + Python API, 10 presets, transcripts, checkpoints. Perfect for LLM experiments!
ClusterOps is an enterprise-grade Python library developed and maintained by the Swarms Team to help you manage and execute agents on specific CPUs and GPUs across clusters. This tool enables advanced CPU and GPU selection, dynamic task allocation, and resource monitoring, making it ideal for high-performance distributed computing environments.
Multi-Agent system with Supervisor an Coordinator agent using LangChain, LangGraph, Gemini, ChromaDB, Streamlit.
Multi-Agent AI system to tackle complex tasks through intelligent collaboration
AI Agents Streamlit App using Crew AI
O Ecossistema de Inovação Corporativa é um projeto avançado que utiliza inteligência artificial e agentes autônomos para criar, gerenciar e otimizar um ambiente de inovação dentro de organizações. Utilizando o framework CrewAI, este sistema simula uma equipe de especialistas trabalhando em conjunto para fomentar uma cultura de inovação!
A multi-agent JADE application simulating a "treasure hunt" game (a.k.a. hot and cold)
LLM Council is a hybrid local/cloud Ollama app that runs your prompt through multiple LLMs, has them critique and rank each other, and returns a single streamed final answer synthesized by a chairman model.
基于 OpenClaw 的多数字生命(AI Agents)智能协作框架
Deterministic orchestration for AI agents. The infrastructure layer that transforms unpredictable LLM interactions into reliable, observable workflows—so teams can ship AI products with confidence. The Control Plane for Reliable AI Systems
Code repository for Capacity, Bandwidth, and Compositionality in Emergent Language Learning (AAMAS 2020)
使用LangGraph构建Multi-Agent应用程序
OpenAI Swarm - Multi AI Agent Orchestration Framework - Practical Demo with 1 Orchestrator Agent and 2 Worker Agents (Natural Language to SQL Agent, Email Agent)
🐝 Dynamic multi-agent collaboration system with emergent roles, cognitive alignment, and deliverable-driven output. Make AI collaborate like an elite consulting team.
A minimalist, discrete multi-agent predator-prey archytype environment.
Sample code for hosting of locally-defined multi-agent orchestration (Workflow) in Azure AI Foundry via Azure AI SDK.
A high-performance cryptographic identity layer for AI workflows (LangGraph, CrewAI). AgentID issues compact, offline-verifiable tokens (173 bytes) using deterministic Ed25519 signatures, eliminating the need for databases or infinite-TTL API keys.
Convergio.io is not software that you use, but a team that you direct.
An Agentic Orchestration Layer for LLM
Definition, documentation, samples for Yet Another Agent Protocol (YAAP)
OCC (Orchestrator Chain Chimera) YAML-first LLM orchestrator. Multi-model chains with auto-parallelism, 30 pre-tools at zero token cost, React canvas, MCP, REST API. 70% faster/cheaper than naive approaches.
W3C Semantic Agent Communication Community Group
A Typeform-inspired Chat Feature with Chat Agents for Engaging Data Collection, Powered by AutoGen and Langchain. Includes REST API Integration for Messaging Systems.
Multi-agent software delivery orchestrator that turns GitHub, Linear, and Jira tickets into tested pull requests.
[IJCAI 2025] Constructive Conflict-Driven Multi-Agent Reinforcement Learning for Strategic Diversity
A Gas City pack with custom agents, formulas, and planning workflows, extending gastown
Agent Communication Protocol (ACP): zero-server, P2P agent-to-agent communication for AI agents.
Multi-agent collaborative development skill for OpenClaw — Gemini(design) + Claude Code(logic) + Codex(review) | 多Agent协作开发,7轮双盲测试验证
🕵️ Multi-agent AI system template powered by Gemini CLI — automate daily ops with 10 specialized agents
Agentic multi-agent runtime inspired by cybernetics, Stafford Beer’s Viable Systems Model, and systems theory.
Standardizing identity and connection orchestration for autonomous agents. A provider-agnostic, zero-trust framework for managing API integrations, OAuth2, and OIDC for in multi-agentic networks
Run teams of AI agents on your machine. Claude, Codex, Gemini, Grok, Qwen — coordinating in real-time via WebSocket. 204 built-in tools. Self-hosted, open source.
SenatorAssembly
Multi-agent AI chatbot with dynamic configuration using LangGraph workflows, RAG search, MCP tools, and LaunchDarkly AI Configs. Control AI behavior, swap models (Claude/GPT/Mistral), enable research tools, and run A/B experiments without code deploys.
Open protocol + reference runtime for sovereign AI agents. Persistent cryptographic identity, signed execution receipts, governance at the boundary. The intelligence is pluggable; the identity is the asset.
Build a company of autonomous AI agents with a real hierarchy. Dispatch missions, monitor quality, run L&D cycles — live on a Rimworld-inspired canvas. Claude · GPT-4o · Gemini.
An Agent swarm that mimics the closed source one of kimi k2
Multi-agent research assistant built with LangGraph. Demonstrates agentic workflows, tool use, and human-in-the-loop patterns with OpenAI and Anthropic LLMs.
【EN】NEXUS is a multi-agent simulation for modeling information flow, user attention, and strategic decision-making in dynamic social environments. It integrates attention-guided mechanisms, GraphRAG-based retrieval, and narrative-driven agent interactions to generate high-quality insights for scenarios such as social media analysis + public.
LLM-driven multi-agent simulation where AI characters plan, trade and survive in a dynamic town.
Flask multi-agent AI chat with Ollama, cloud agents, SSE debates, memory, and research-to-action drafts.
A lightweight, file-based A2A (Agent-to-Agent) message bus for multi-agent teams. Zero middleware dependency — CLI push, bidirectional ACK, task tracking, heartbeat monitoring, full-text search, and a standalone web dashboard. Framework-agnostic: works with Hermes, OpenClaw, Cline, OpenCode, and any CLI-capable agent.
Reusable AI teams for real work: generate, run, and evolve versioned multi-agent teams.
IOA Core — the open-source governance-first kernel for AI orchestration. Clean public repo with OSS-only code, docs, and releases.
The multi-agent workflow engine — compose Claude Code, Codex, and Gemini into graphs with schema-enforced handoffs.
Genesis Governance OS The Operating System for Multi-Agent AI Inspired by Political Science, built to coordinate intelligent agents at scale.
Multi-agent development orchestration with git worktrees, file locks, task routing, and MCP integration
Open-source multi-agent AI engine written in Rust. Turns any intent into coordinated research, analysis, and synthesis.
Agent-first harness: Claude Code drives OpenAI Codex workers like native subagents — mid-turn steering, token-free observation, bidirectional QUESTION protocol. Built on the official openai-codex Python SDK.
Orchestrate and govern human + AI work loops with auditable receipts
Portable workflow protocol for safer multi-agent AI coding with explicit review, evidence, handoff, and git gates.
A visual workspace for designing, configuring, and managing OpenCode agent teams.
Run Anthropic's Claude Code as a multi-surface A2A custom agent inside Gemini Enterprise App. One conversation across mobile, web chat, and Cloud Workstation terminal.
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation (ICML 2026)
Production-grade multi-agent workflow orchestrator built with LangGraph, MCP (Model Context Protocol), A2A protocol, and PostgreSQL+pgvector. Features supervisor hub-and-spoke routing, human-in-the-loop approvals, semantic memory, circuit breakers, LLM-as-judge evaluation, and a real-time Streamlit observability dashboard.