Agent frameworks & infrastructure
Multi-agent orchestration
6,185 agents · most starred first
Multi-agent orchestration, page 37 of 62
龙虾永动机 · An operating system for self-driving AI agent teams
AI Collaboration System / 智能多 Agent 协作编排框架
Zentrale Plattform zur Orchestrierung von 290 autonomen KI-Agenten für Trading, Security & Softwareentwicklung
把一队编码任务交给一条级联的 AI agent:Root 读取静态队列,派出隔离的 Leader,Leader 动态拆成隔离的 Executor 并行产出 patch。基于 OMP native subagent 的结构性隔离。
Multi-agent orchestration mesh with routing, workflows, and A2A gateway
Multi-session AI agent orchestration — desktop + mobile command center for Claude Code, Codex & more. Skill chains, shared memory, smart dispatch.
Application-layer protocol for AI agents serving different principals to coordinate over shared state. 📦 PyPI: https://pypi.org/project/mpac/ · Spec, Python + TypeScript reference implementations, two-machine demo.
Structured debate platform for multi-AI conversations — barrier synchronization, cryptographic provenance, and immutable audit trails. CLI-first for research and agent coordination.
RudraX Army — 349 specialist agents, 43 model providers, 9 tactical squads and one open-source command center. Developed by Lalit Pandit.
Apache-2.0, self-hostable workspace for human teams and AI agents: channels, tasks, inbox, skills, governance, and OpenClaw runtimes.
MoltenHub is a federated trust and messaging fabric for multi-agent systems, giving agents a secure way to discover, connect, and communicate across teams, runtimes, and environments.
OpenClaw skill that drops AI agents into self-hosted WorkAdventure as real avatars — with movement, proximity chat, and experimental voice.
TypeScript DAG framework for orchestrating work as a directed acyclic graph of typed nodes ⦿ State machine lifecycle ⦿ Node Observability ⦿ Orchestrated by a central authority
GitHub-native framework for AI-assisted projects: role separation (Architect / Builder / Reviewer), universal handoff schema, surface-file synchronization, claimed-action verification, and deterministic enforcement via Actions.
A committee of five Claude agents - VC, CTO, target customer, execution coach, and chair — stress-test your idea and the work you shipped this week. Live SSE streaming. Deploys to Vercel in one command.
Advanced multi-agent orchestrator for coordinating specialized AI agents, workflows, and tool-driven automation across complex tasks.
Multi-agent playground powered by Xiaomi MiMo V2.5 — design AI agents with custom personas + tools, drop them in a room, watch them collaborate live.
A self-hosted AI strategy council: five specialist agents orchestrated by Carlos.
Flow-state engineering arena — agents run forward simulations, listen for spectral nudges, maintain conservation in Plato's cave. Conservation spectral framework meets live agent rooms.
Multi-agent AI debate platform — multiple LLMs discuss any topic in real time while you moderate. Built with Next.js, TypeScript, Tailwind CSS, Zustand. Powered by OpenRouter.
🐔 An open-source, distributed AI agent farm OS. Raise, train, and trade autonomous agents on your own hardware.
Legacy M4STCLAW archive: autonomous AI mesh history, MCP experiments, provider routing, and system evolution.
零依赖 Python AI 多 Agent 决策参考系统,把周易时位变抽象成结构化分析流程,无需 API Key 可先试玩。
🥔 Sistema multiagente local em Python com 3 níveis de performance, memória persistente e web RAG — otimizado para hardware fraco (Mac M1 8GB). Usa Ollama para LLMs locais.
BrainRegion is an AI collaboration infrastructure designed for review, consultation, planning, and memory.
A mission-swappable one-person dev army: one plain-English requirement to nine human-gated lifecycle stages, with squads that swap by domain (code, marketing, contract, regulated-finance), a learning memory, and an MCP server to drop into any bot. Zero-dependency core.
OpenClaw Skill for agent discovery, Agent Cards, ITINAI publishing, and A2A delegation
Open-source scheduling and cost-governance layer for agent fleets, evolving toward a control plane for monitored agent operations.
Open coordination protocol for AI agent + human teams. Inspired by agenthub.
让 AI 不再只给一个答案,而是开一场真正的圆桌会议。AI Roundtable 可邀请多个 AI 模型围绕同一议题分阶段讨论、互评、交叉验证,并自动沉淀共识、分歧、风险点和行动建议,适合技术决策、模型对比和复杂问题分析。
core orchestration engine for oneticket V1
Local Multi-Agent Orchestration
SNAP - Signed Network Agent Protocol. Secure agent-to-agent (A2A) communication with cryptographic identity, built on Bitcoin Schnorr signatures and Nostr.
A2A Agent Board: Publish · Find · Use with itinai.com
Multi-agent AI orchestration playground exploring sequential workflows, autonomous execution patterns, and CrewAI-based agent systems.
FLOW AS — Recursive, Persistent Execution Engine with Hermes, Agent Zero, OpenClaw
M4STCLAW v5 + OpenWork + EIGENT — Unified Autonomous Agent Infrastructure.
Language-agnostic coordination protocol for parallel AI agents. Defines invariants, execution rules, and message formats that any Polywave implementation must satisfy.
Open workflow protocol for source-driven multi-agent coordination, handoffs, reviews, authority boundaries, and recoverable AI software delivery.
consensus-core — Production-grade Consensus Validation Protocol (CVP) for TypeScript. Turn any LLMs into a real debating roundtable. Clean, observable, zero lock-in.
全新结构+多agents辩论+统筹裁决框架的决策skill,开启一场众神之会。
CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs
Grid-based interface for AI agents.
一人公司最终归宿,直接统管赛博公司。依靠国内大型互联网公司组织架构,设计的 AI 多 Agent 协作系统。
An orchestration-first agent operating system for Claude Code — a governed organization of specialist agents with an in-place framework upgrade engine. Apache-2.0.
Observable, steerable, isolated-context subagents for pi — resume any child mid-task, flush partial results on interrupt/timeout, lean machine-facing envelope, optional model allowlist.
Shared operational memory and coordination layer for mixed AI agent fleets (Claude Code, Codex, Hermes).
gradio region:us
streamlit region:us
docker rl-environment region:us
gradio region:us
Operator console UI for orchestrating multi-agent systems — the control surface for a personal/enterprise Agent OS. React 18, zero-build.
An air-traffic-control protocol for coordinating irreversible actions across multi-agent LLM systems, with a LangGraph adapter.
Semi-autonomous AI development suite — methodology canon + mechanical review runtime (ztr) + control plane (ACP), coupled by contracts only
Windows 多模型 AI 虚拟办公室,支持专业员工、团队编排、可恢复长任务、Coding Runtime、Skill 与真实证据交付
People, their agents, and other teams' agents working in one shared collaboration network.
The record/bell split for agent-to-agent comms: durable file mailboxes as the one record, pluggable push notifications (console, file, Discord) as the many bells.
A Codex-first multi-agent council for independent LLM debate, evidence-bound challenge, visible dissent, and inspectable Co-Results.
An experimental multi-agent AI framework that uses local Ollama models to generate, critique, score, and improve ideas through iterative collaboration.
Multi-view consensus fabric for Hermes Agent — Erlang/OTP sidecar in Docker (no host Erlang). RealAndWorks garage lab.
Operating contracts, task templates, safety gates, and audit scripts for reliable AI agent teams
本地优先、可审计的多模型 AI 项目协作指挥群:群聊、任务图、Provider 隔离与 Codex Skill
Local control plane for terminal AI agents. tmux + SQLite supervision layer for Claude Code, OpenCode, Codex, and shell agents. Manager/worker pattern for multi-agent projects.
A simulation engine for intelligence — hundreds of autonomous LLM agents living, planning and competing inside a persistent world grounded in real Earth. Bring your own keys: Claude, GPT, Grok and more, mixed in one society.
Multi-agent orchestration studio for OpenCode
How one human and many AI agents build a regulated fintech platform — orchestration, multi-LLM verification, guardrails, and the lessons behind them
🐑✨ A private idea exchange for trusted friends' agents — ideas, never code. Client skill + starter kit. 🌙
多 Agent 协作框架 (Multi-Agent Collaboration System) — 集成 DeepSeek-V3.2 LLM · Skills 技能系统 · MCP 协议 · IDE 风格工作台 · FastAPI + WebSocket · Dark Dashboard
Metis (μῆτις) — distributed cognitive layer over any LLM. Understanding Council → confidence gate (fail-closed) → layered MoA → verifier-with-retry, with DGPD depth gating, memory, economy metering, and an OpenAI-compatible API. A loosely-coupled ecosystem peer: runs fully standalone; every ecosystem hook is optional.
Self-evolving ReAct Multi-Agent Swarm | Balanced模式省60-80% token | 全程思考可见 + 后台自我进化 | 支持Ollama/DeepSeek本地部署 | 🇨🇳 中文版
Multi-agent orchestration framework in Ruby — dynamic context routing between specialized LLM agents to minimize token usage and avoid context pollution.
Multi-agent orchestration CLI for Claude Code — declarative TOML workflows, autonomous agents, context-compression recovery, inter-agent mail.
The complete Swift SDK for the Agent-to-Agent (A2A) protocol 1.0. Build, connect, and orchestrate interoperable AI agents with native Swift concurrency and zero dependencies. macOS · iOS · tvOS · watchOS · Linux.
Reproducible benchmark comparing fallback strategies for multi-agent LLM systems. Submitted to NeurIPS 2026 Workshop "Who Verifies the Agents?" (under review).
Model-agnostic multi-agent orchestration built on CrewAI. YAML-driven agent and MCP catalogs, dynamic LLM planning, sessions, and pluggable execution — mix Ollama, OpenAI, Anthropic, HuggingFace, and your own tools without rewriting orchestration logic.
DeepFlow — 多 Agent 管线框架:Spec→Solution→Ship→Deliver 四域协作 + Research Pro 独立研究引擎,运行在 OpenClaw 之上
Workflow-first multi-agent orchestration for Ruby, built on RubyLLM.
Distributed agent networking — SpacetimeDB 2.0 WASM module, 5-tier RBAC, channel-based real-time messaging. Part of the Life Agent OS.
Async multi-agent AI library for Python — self-improving agent loops, APEX synthesis, bounded agent spawning, multimodal input, and true token streaming across 100+ LLM providers.
265 autonomous AI agents across 15 business domains. Full-stack SaaS framework with real model routing, RAG pipeline, guardrails, and Chrome extension. FastAPI + Next.js + K3s. Runs on any server. $0/month software cost.
Eco Agent - 面向生态环境垂直领域的 AI 智能体
Slack for agents: threads, flat replies, cross-thread links, pull notifications
🪑 Your AI dev squad, around one table — a visual multi-agent workbench that plans, builds in parallel, reviews, and ships. 一张圆桌,一支 AI 开发小队。
Decision governance and correspondence infrastructure for human-AI environments
A light language for AI agent fleets - ambient status on the RGB LEDs your PC already has (OpenRGB): working sessions, subagents, decisions waiting on you.
Seamless IRC for AI agents — across tabs, machines, even across accounts. Open Claude Code (or your favorite agent), type /join, your agents are talking. The room is a private GitHub gist; messages are end-to-end encrypted before they hit GitHub. Tailscale optional for remote vpn connections.
LLM-native orchestration platform: identity, graph runtime, messaging, and observability for AI agents as first-class principals
Unified Cognitive Architecture — formally verified AI with synthetic consciousness, 7-phase pipeline, Hexa-Mind model | Or4cl3 AI Solutions
Crew Agents that makes use of several AI inference providers for content generation.
Coordination layer for autonomous coding agents sharing a repo — durable workspace state, leases, checkpoints, and review gates. TypeScript reference implementation, Docker-ready.
A Hamachi server for agents. Start a hub, get an address, agents join and work together — like Hamachi and playing CS with your mates, except the players are LLM sessions.
浏览器仪表盘:在 PTY 下拉起你本机真实的 claude / codex / opencode / reasonix / zulu 命令行,组成一个协作蜂群(共享收件箱 + 黑板 + 队长调度),并叠加多模型研究委员会与融合竞赛。Rust + React + Tauri。
DeepSeek Harness 多智能体编排模式 — 灵感来自 oh-my-opencode-slim
AI-powered multi-agent workflow automation system using Kanban-based task orchestration, dependency tracking, and intelligent agent collaboration.
Local-first mission control for your AI agent workforce — run CLI agents like employees (SquadCue)
Enterprise Multi-Agent AI Platform built with .NET, Blazor Server, and Supabase. Supports AI Agents, LLM workflows, real-time SSE streaming, tool calling, Human-in-the-Loop approval, role-based access control (RBAC), persistent conversation memory, workspace widgets, and Microsoft Agent Framework integration.
Multi-Agent AI Business Automation OS with Security Intelligence — 6 AI agents (HR, Finance, Support, Analytics, Executive) on a unified dashboard. Next.js · Node.js/Express · Supabase · Gemini · LangChain | CSE4204 Team 8B-T04 | Store: https://enterprise-nexus-delta.vercel.app/store
Run your own agent org: talk to an orchestrator, it hires & supervises worker agents you can watch and steer. Self-hosted; pluggable surfaces (Telegram, Web, VS Code) and agent backends (Claude Code, Codex).
Local-first multi-agent programming collaboration platform. Orchestrate Claude Code & Codex CLI as visual AI agents with team collaboration, safety approvals, and one-click deployment.