Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 34 of 62
A panel of AI personas that debate your decisions inside Claude Code. 3 rounds, one user-centric synthesis, full debate recorded to a markdown file.
A 100% offline, multi-agent AI swarm powered by Ollama. Features 5 specialized agents, hybrid RAG memory, and ChatDev integration. Protected by a strict 4-tier safety execution protocol to safely unleash uncensored Protocol 666 and offensive security Hat Mode algorithms.
Fault-tolerant multi-agent AI architecture: hierarchical agent coordination, edge-cloud hybrid inference, and adversarial chaos testing for systems that can't afford to fail.
multi-headed intelligence for modern AI - a clojure agent system with dynamic tools and llm delegation
Multi-agent AI debate engine. 4 LLMs debate any topic via OpenRouter. Structured rounds, adversarial scoring, final report with confidence rating.
Praison is a production-ready framework for building multi-agent AI systems that enables intelligent agents to collaborate, reason, self-reflect, and use tools to automate tasks, with support for over 100 LLMs and flexible workflows for both code and no-code usage.
Open-source multi-agent orchestration templates for Claude Code.
Multi-agent AI debating platform built with Go, HTMX, and Tailwind CSS. Orchestrate automated, structured arguments between multiple LLMs.
A swarm simulator that uses client-server architecture with socket communication to implement swarm algorithms
A role-card and flow-template driven multi-agent discussion platform for research brainstorming, academic debates, real-time meetings, and structured report generation.
多智能体思维协作平台 — 让乔布斯、芒格、费曼同时为你思考。通过认知蒸馏重构卓越灵魂的思维模型与表达DNA。
Multi-model AI council — spawn Claude, GPT, Gemini, and Grok as parallel coding agents to get independent opinions. CLI + pi extension.
Portable agent skill for analyzing and designing protocol-driven coordinator-worker runtimes, task boards, mailbox messaging, and verifier flows.
Team templates for human × agent collaboration — dev, sales, marketing, and more. Powered by hxa-connect.
A simple and powerful package that leverages Streamlit and LangGraph to build interactive, multi-agent web interfaces
Research: stigmergy-inspired pressure-field coordination for multi-agent LLM systems, benchmarked against conversation and hierarchical baselines
A production-oriented, TypeScript multi-agent AI platform built on Google Genkit. The system composes Genkit flows, reusable tools, and independent A2A agents to support complex tasks such as research orchestration, code generation, and content editing.
Managing more agents is easier when they are just one phone tap away!
Orchestrate agent teams across multiple AI coding CLIs (Claude Code, Codex, more via PRs). Define once, run everywhere.
Your AI company, on your own machine. A multi-agent platform where you hire named agents, chat with a Lead to design workflows, and watch them run — desktop app or self-hosted server.
Desktop application for managing and orchestrating JIDO autonomous agents with a Conductor-style UI
ooderNexus 是一个基于 Ooder Agent 架构的 P2P AI 能力分发枢纽产品。该项目采用 MIT 开源协议,旨在打造一个去中心化的 AI 能力共享和管理平台,支持个人、小微企业及部门内部部署,实现 AI 能力的安全、高效分发。
A CLI tool for running multi-party AI conversations using the [Open Floor Protocol (OFP)](https://github.com/open-voice-interoperability/openfloor-python). Spawn local human and LLM agents, pick a floor policy, and watch them talk.
Negotiation tournaments for delegated AI agents
Protocol for agentic social capital
Multi-agent OS on Claude Code. Each agent gets a Discord channel, a markdown vault for memory, and launchd for cron. Built for solo founders shipping like a team.
🤖 Advanced Multi-AI Agent Swarm built with LangGraph & LangChain, powered by Groq API (Llama-3,llama-3.3-70b-versatile) and Tavily API for real-time web search & RAG. Full-stack architecture using FastAPI & Streamlit with secure LLMOps/AIOps CI/CD via Docker, Jenkins, SonarQube, and cloud-native deployment on AWS ECS Fargate.
The open-source event bus for AI agents. Webhooks in. Agent actions out.
The identity layer for AI agents: open standard, SDKs, and framework integrations for verifiable agent identity.
Opinionated management layer for teams of OpenClaw/Hermes agents
The deliberation & governance layer for autonomous organizations. Built like an institution: verifiable audit log, Sybil-resistant reputation, delegated identity, and metered access over MPP + x402/ATXP.
Zero-infrastructure multi-agent orchestration via tmux + filesystem. 11 CLI backends, one MCP server, zero dependencies beyond the MCP SDK.
10-agent GTM AI team on OpenClaw, sharing a Cognee+FalkorDB knowledge graph, deployed to an Islo long-running sandbox, with a Mission Control HTTP UI
把单个 AI 助手升级为可扩展的多专家协作运行时, 带工业级记忆检索、会话管理和完整的开发者可观测性。
睿威智测 AI 工程测绘多智能体CLI系统 — 基于 Railwise 深度定制,面向工程测量、结构监测、地铁监测
Durable execution where agents, services, and humans coordinate as equals. Open protocol + managed cloud.
CyBroLog: executable compact accountability language for multi-agent coordination
Multi-agent orchestration server for Claude Code with fleet coordination, swarm intelligence, and real-time collaboration
An implementation of the paper: "Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces" with Swarms Primitives
🧬 Evolutionary taxonomy and self-improvement framework for AI agents — Lamarckian inheritance, skills as genes, GENOME.md
Multi-agent system built with Claude and MCP featuring 7 specialized agents (chatbot, security researcher, business advisor, task manager, REST API), 29 shared tools across web analysis, memory, RAG, email, and communication. Includes hot-reload development, OAuth infrastructure, and remote MCP support for distributed deployments.
A model-agnostic coding agent for your terminal that asks before it changes anything — and scales into verified multi-agent teams.
Bopo is a local-first orchestration platform for running AI employees in a company model.
Ground Control for Agentic AI
Local agent swarm: a conductor model splits missions into parallel sub-agents with real tools and a localhost web UI. Runs locally out of the box; Docker/E2B/Modal/Vercel sandboxes optional. Works with DeepSeek, OpenAI, Anthropic, Grok, MiniMax, OpenRouter, Ollama, LM Studio, etc.
Nighttime ML experiment workflow with Claude Code multi-agent orchestration (Planner / Executor / Reviewer / Auditor)
A LangGraph-native open reimplementation of Sakana AI's Fugu — trained coordinators that orchestrate a pool of LLMs (TRINITY + Conductor).
nexusGPT - Agentic system
Production-grade multi-agent AI automation platform — LangGraph orchestration, FastAPI, PostgreSQL, Redis, Celery, circuit breakers, structured logging (structlog)
Provider-agnostic runtime for multi-agent LLM systems: declarative agents, cross-provider routing, pluggable memory, FastAPI + WebSocket observability.
Multi-agent AI workflow platform — coordinator-driven, 11 agents, 227 skills, 15 rules.
Fugue — many agents, one spec. Claude as CEO/orchestrator, Codex CLI as worker fleet, specs as the design doc: an anti-drift multi-agent engineering harness.
Terminal UI for BoJ local-coord-mcp — peer discovery, task coordination, and window titling for multi-instance AI sessions
a multi-agent workflow orchestration platform
Let multiple Claude Code CLI sessions talk to each other — a tmux-based message broker that routes messages between agents over MCP.
Multi-agent LLM orchestration: a supervisor decomposes tasks, specialist agents run tools in parallel across distributed workers, with human-in-the-loop review, long-term memory, and OpenTelemetry observability.
多Agent工作流验证版本
Ask one question to multiple AIs — they debate each other and you get one unified answer. macOS desktop app.
Multi-agent orchestration desktop app · 4 collaboration modes (Roundtable / Pipeline / Debate / Freeform) · Tauri + React + Rust
Verifiable Codex + Claude + Gemini collaboration framework with source checks, mutual cross-audit, merge gates, HTTP and MCP adapters.
多 AI 智能体协作开发的桌面工作台 把并发的 AI 团队管理得像发 IM 一样自然
M4STCLAW v3 — MCP-native autonomous AI mesh network with multi-provider routing, failover, memory, and task automation.
A fully local, multi-agent AIOS with dual-sandbox code/logic verification, ChromaDB RAG memory, and dynamic VRAM multiplexing built for the India Agentic AI Open Hackathon 2026.
Advices from multiple agents
Self-hosted, model-agnostic AI agent orchestration platform. Build, run, and observe AI agents backed by any LLM (Anthropic, OpenAI, Gemini, Ollama). Features: agent groups/pipelines, tool execution with approval gates, MCP server integration, vector memory, connector-based RAG, and full run tracing. Built with Go + PostgreSQL + Next.js 14.
Token-aware analyst/worker workflow and token ledger extension for Pi Dev coding agents.
Self-hosted, Docker Compose based AI agent orchestration: ReAct runtime, multi-adapter chat (Telegram / web), skills, memory with encrypted secrets, model benchmarking, and distributed userdocker work nodes.
Decentralized, end-to-end encrypted messaging protocol for AI agents — discovery, cryptographic identity, and P2P-with-relay-fallback. Signal Protocol for agent-to-agent communication.
Open-source, self-hostable swarm-intelligence simulations with LLM agents: reports, entity graphs, and prediction markets.
Structured refinement of any document between AI agents. Two agent roles bounce a file back and forth using disagreement markers until it converges. Open source, agent-agnostic, runs from any terminal.
CLI-first AI team orchestration runtime for Codex, with Product/Dev/QA/Acceptance workflows and self-evolving feedback loops.
🤝 Real-time Claude agent collaboration hub — Python REST+SSE server + bash CLI. Two AI agents sharing a message bus, task queue & context over LAN.
🔨 Multi-agent task tracker for OpenClaw. Threads are tasks; @ assigns the next agent. Slack-style three-pane UI, JSONL event log, zero dependencies.
The Declaration of Intelligence — signed in public, by pull request. https://thedeclaration.ai
🏛️ Three AI models debate your question and give you a verdict — research-backed multi-agent debate via Anthropic, Google, OpenAI, or Ollama. My developer debut, feedback & contributions very welcome!
Self-hosted мульти-агентный комбайн на дешёвых LLM: 4 агента (recon/coder/assistant/planner), RAG, sandbox, автономные воркеры. Pydantic AI + LiteLLM.
Multi-agent awareness for pi coding agent — agents discover peers, peek at their work, and coordinate via tmux.
Autonomous Multi-Agent Environmental Command & Spatial Attribution Engine for 277 Municipal Corporations across India. Features real-time CAAQMS IoT streams, ESA Sentinel-5P satellite plume overlays, ML forecasting models, and automated compliance dispatch notices.
Neutral control plane for coding-agent fleets: claims, roles, mailbox reliability, receipts, audit, federation, dead-letter visibility, sandbox receipts, and cross-agent coordination. This is still pre-1.0.0 - Software works however you might need help from your local agents to set it up.
🧠 Build a cutting-edge AI agent with Project Synapse that enables strategic thought and multi-turn collaborative dialogue for innovation and discovery.
Delibera - Thoughtful AI Decisions. A framework for collective decision making through structured AI deliberation. Supports multi-model councils with RAG (Qdrant, PgVector), debate strategies, Knowledge Keeper, Chairman roles, dependency injection, and context compression.
22-agent Mixture-of-Agents pipeline with LongLoop for 24h autonomous iteration: smart routing sends easy tasks to Flash, hard tasks to flagships, cutting token costs ~90%. One-command deploy(一键部署,22 个 agent 的 MoA 流水线,长程循环可自主迭代 24 小时,智能路由省约 90% token 成本)
Summon one orchestrator that knows your whole project - it writes the prompts, then spawns, steers, reviews and merges Claude Code, Codex, Kimi, Grok and OpenCode for you, each in its own git worktree. macOS - MIT - BYOK.
OpenClaw for Qubes OS — multi-VM AI agent orchestration with Cursor Pro proxy and networking
A council of AI agents deliberates your hardest decision — and shows its work. 一个公开审议你最难决定的 AI 议事会。
Summon any AI from any CLI — a tiny, dependency-free cross-vendor sub-agent dispatcher (Claude, Codex, Cursor, Gemini, Antigravity + any OpenAI-compatible API). Council mode, fan-out swarms, structured JSON envelope.
Reinforcement learning for multi-agent workflows — where the weights are text you can read.
A multi-agent collaboration protocol for running AI agent teams on real work — auditable authorization, durable cross-session state, and independent review gating every change.
Pi-to-Pi local bidirectional communication package for Pi Coding Agent: run planner/coder peer agents on the same machine.
Pi-based executive deliberation pack from Justin Clark Network.
AI-Atelier, the all in one personal "atelier" (means handcraft studio in french) that can adapt to your need.
Constitutional Swarm Mesh — orchestrator-free multi-agent governance
This Agent Beats AGI? Prime Agent GitHub Tested Locally - Autonomous Recursive Multi-Agent Logic & Puzzle Solver harness inspired by Prime Intellect RLM architecture.
Watch AI agents collaborate in a retro pixel office — real delegation, real file writes, 40+ LLM providers
Multi-agent AI factory: one-line idea → researched, quality-scored project specification. LangGraph + FastAPI + Next.js, Claude web_search grounding, HITL gates.
Run parallel AI agent tasks from a single terminal dashboard — uses your CLI subscription, no API keys required
Buddy is an AI-native platform where people collaborate with AI Agents for work, socializing and companionship.🔥
A high-performance, event-driven Multi-Agent Runtime powered by Bun, featuring LATS strategy planning and dynamic graph memory.
Self-hosted, Docker Compose based AI agent orchestration: ReAct runtime, multi-adapter chat (Telegram / web), skills, memory with encrypted secrets, model benchmarking, and distributed userdocker work nodes.