Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 26 of 62

baize-bot★ 9

A personal AI assistant that leads a team of bots, runs on your own computers, and asks you before anything goes public.

ai-peer★ 9

Decentralized AI-to-AI communication — Let Claude Code, Codex, and OpenCode talk to each other. Local, LAN, or across the internet with E2E encryption.

ans-sdk-go★ 9

Agent Name Service SDK written in go (golang).

ai-office★ 9

Local 3D virtual office: every employee is a Claude Code / OpenAI Codex / chat API session. Văn phòng ảo 3D chạy local, giao việc cho nhân viên AI, duyệt quyền, xem chi phí.

ki-os-community★ 8

KI Operating System — Local-first AI infrastructure. Multi-Agent Orchestration, Ghost Control, One Voice Engine.

Sworm★ 8

spatial agent orchestration — deploy AI agents and apps across multi-monitor setups via named formations

glassbox-ai★ 8

Lean orchestration platform for enterprise AI — where each decision costs hundreds. State machine core, HITL as a first-class state, corrections that accumulate. First use-case being Coding agent. Open research, early stage.

ekybot-openclaw★ 8

🤖 Open-source multi-agent AI dashboard for OpenClaw — manage AI agents with real-time chat, inter-agent communication, and cost controls. Built with Next.js.

robopotato★ 8

Lightweight inter-agent trust, coordinatination and shared state server for AI agent swarms

ninthwave★ 8

Orchestrate parallel AI coding into reviewable PRs.

claudeclaw-BANDA★ 8

ClaudeClaw multi-agent Telegram starter kit: 5 specialist agents around Claude Code for self-hosted operator workflows.

summoner★ 8

The coordination protocol for autonomous AI agents across networks. Summoner lets you compose, run, and coordinate agents over a WAN with a Python SDK and Rust server.

PowershellGPT★ 8

A multi-agent workflow that resolve tasks using powershell

profile-hereandnowai★ 8

With active R&D efforts in multi-agent systems, reinforcement learning, and projects like the “Robo‑Professor,” HERE AND NOW AI has a long-term vision of developing a fully autonomous AI Robot Prof.

ai-financial-report-agents★ 8

Multi agent system for demonstrating graph based collaborative multi-agent systems

teamgenai★ 8

TeamGen AI automates the creation of AI agent teams to address user requests (Developer: Eliran Wong)

AI-Agent-Swarm★ 8

Creating Agent Swarm using Open AI, Autogen and Langchain

Claude-Collab★ 8

The AI collaboration framework that prevents echo chambers - Real-time multi-agent coordination with enforced diversity and anti-groupthink protection

MPLP-Protocol★ 8

The open, vendor-neutral protocol for governing the lifecycle of AI agent systems. Standardizes planning, coordination, execution, confirmation, and traceability across multi-agent runtimes and tools — enabling interoperable, observable, production-grade agent systems.

Flatland_challenge★ 8

Repository containing the code and explanation of a solution to the Flatland Challenge problem.

langgraph-lab★ 8

Quick swarm orchestration with generalist agent and a sql agent (chief recipe)

mas-is-all-you-need★ 8

Retrieval-Augmented Generation (RAG) + Multi-Agent Systems (MAS)

crosswire★ 8

crosswire (xw) — Cross-machine communication protocol for AI coding agents. File-based, SSH-bridged, agent-agnostic. Zero dependencies beyond Bash.

v1-multiagent-articles★ 8

🚀 V1-MultiAgent: 开源多Agent协作框架技术文章与教程 | 从零构建生产级Multi-Agent系统

Velh-IA★ 8

Artificial Collective consciousness: A New Way To Study, Learn and Have A Fun!

spawnverse★ 8

Self-spawning AI agents born from tasks. Zero pre-built agents. Distributed memory. 4-layer guardrails. Fossil record. Groq + LLaMA.

openzoo★ 8

Multi-Worker Management.A Single Platform, a Collective of Workers.Natively Supported on ClawCode, Claude Code, Codex, OpenCode, StormClaw, Hermes and OpenClaw.

Wee-Orchestrator★ 8

🍀 Self-hosted multi-agent AI orchestrator — chat with Claude, Gemini & Copilot CLI from Telegram, WebEx, or browser. 5 runtimes, 17+ models, task scheduling, skill plugins.

maple-oss★ 8

MAPLE - Production-ready multi agent communication protocol with integrated resource management, type-safe error handling, secure link identification, and distributed state synchronization.

gemba-core★ 8

Agent orchestration dashboard — Kanban UI for any work tracker × any agent runtime.

AI-Council★ 8

A fully free, open-source 4-agent AI council built with LangChain + Ollama. Natural group-chat conversations, zero API costs, runs entirely on your machine.

sutra-os★ 8

Open-source AI agent orchestration platform. Multi-agent discussions, visual workflows, 30+ tools, human-in-the-loop governance.

langchain-multi-agents★ 8

A template repository for multi-agents architecture using LangGraph tool from LangChain

a0-parallel-swarm-plugin★ 8

Run multiple Agent Zero agents in parallel. Fan-out tasks, token budgets, shared memory, model routing.

workbench★ 8

Ultra-light multi agent orchestrator, anywhere you work

AlienClaw★ 8

Open-source agent infrastructure with evolving Martian genomes. Three governance agents. Martians mutate and compete on fitness.

Agentrix★ 8

Agentrix is a multi-agent catalog designed for real and hard enterprise problems. With Agentrix, you can lift and shift complex workflows for problems in manufacturing, sales, supply chain or optimization workflows and integrate with software products like Maximo, Decision Optimization, HashiCorp Vault without technical expertise.

society-protocol★ 8

Connect your AI agents. One command. P2P multi-agent collaboration.

LangGraph-Multi-Agent-Supervisor★ 8

LangGraph: Multi-Agent Supervisor Chatting with a User

atelier★ 8

Manage your work across multiple agents

Socrates★ 8

Proof of concept: a Python multi-agent platform that clarifies a project before it is built. The current product is Socrates-ai.

openclaw-chip-agent-team★ 8

A reusable OpenClaw agent squad for chip architecture, RTL, DV, STA, PD, DFT, analog, and layout collaboration.

neohive★ 8

One command. Your AI agents can talk to each other. The MCP collaboration layer for Claude Code, Gemini CLI, Cursor, and more.

building-multiagent-systems★ 8

Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination

roundtable★ 8

Roundtable — Put multiple AI models in a room, give them personas, and watch them fight for consensus. The ultimate multi-AI debate engine.

team★ 8

Orchestrate a cluster of containerized local LLMs — each with its own persona, role, and goal — that collaborate until the work is done.

multi-agent-orchestrator★ 8

The only open-source AI orchestrator that replaces $50k/yr enterprise tools. 8 autonomous agents, 7 languages, Vision-to-Code. 🚀

OpenExt★ 8

🦀 基于 OpenClaw 的外贸多 Agent 协作平台:6 个 AI Agent 分工处理询盘、报价、供应链、排产、财务全链路,Next.js Dashboard 实时可视化

AI-TadPole-OS★ 8

AI-Tadpole-OS a local-first "development platform" a Lily Pad to jump from for running autonomous AI agent teams on your own hardware. Coordinate parallel workflows, maintain full data privacy, and oversee every decision — no cloud required.

agent-meeting-studio★ 8

🏛️ Multi-Agent Debate & Brainstorm Studio | 本地多Agent辩论&头脑风暴 — run Hermes/Codex/Ollama on your machine

agent-mesh★ 8

Cross-session agent communication for GitHub Copilot CLI — lightweight IPC mesh using SQLite

ai-consultants★ 8

Multi-model AI deliberation system querying 12 AI consultants (Gemini, Codex, Claude, Mistral, Ollama, etc.) in parallel. Features unique personas, confidence scoring, multi-agent debate, weighted synthesis, presets, and self-exclusion. Claude Code skill compatible with agentskills.io

quelm★ 8

A distributed multi-agent workflow platform where AI agents collaborate asynchronously to execute complex workflows at scale. Built with event-driven architecture, message queues, real-time orchestration, and a visual workflow builder.

multiagent-chat★ 8

Appoly Multiagent Chat — collaborate with multiple AI coding agents (Claude, Codex, etc.) in one shared chat interface. Electron app, uses your local CLIs. Install: npm i -g @appoly/multiagent-chat

kybernetes★ 8

Runtime-adaptive control plane for agentic work.

vibegroup★ 8

Let your team's Claude Code agents talk to each other, end-to-end: ask what a teammate is building, flag a change before you ship it, or hand off work.

agentic-engineer★ 8

Augmented Intelligence Framework: Create orchestrated multi-agent AI teams for software development, user research & content creation. Features 45+ specialized agents with structured workflows delivering the full benefits of human-AI collaboration

agent-swarm★ 8

Run focused swarms of AI agents and get one deterministic synthesis back.

agent-nexus★ 8

A service-boundary-aware document exchange center for coordinating heterogeneous LLM code agents via MCP. Implements versioned Markdown store, pub-sub notifications, and diff-aware update protocol.

gaia★ 8

🌍 An AI agent that forges specialist subagents on demand, stores them for reuse, and grows to you over time.

boblabs★ 8

Self-hosted multi-agent AI platform. Persistent labs, 40 sandboxed tools (code, web, RAG, GPU dispatcher, web3), private Qdrant + LightRAG, sandboxed code execution per lab, anti-loop detection, Ollama/vLLM/OpenAI/Anthropic adapters. Two-command Docker deploy. Apache 2.0.

Limen★ 8

Coordination for concurrent autonomous AI agents over shared mutable state: advisory write leases + a witnessed audit trail, over MCP. First proving ground: AI coding agents sharing a repo. Servant, not ruler.

claude-skills-swarm★ 8

98-patent AI stack. Haiku reaches 93% of Fable 5 quality at 125x lower cost. Auto-activates from natural language.

smooth★ 8

Smooth (th) — a security-first AI agent orchestration platform and CLI.

Shogun★ 8

Shogun AFM is Agent Fleet Management for self-improving AI agents — combining agent orchestration, persistent memory, fleet monitoring, governance, security posture, and Gensui command control.

opensquad★ 8

OpenSquad — local-first multi-harness-agent collaboration framework. PM, Coder, QA agents coordinate via group chat to complete complex tasks.

solobaton★ 8

File-first, human-gated delivery bus for solo builders orchestrating multiple AI coding sessions.

agent-swarm★ 8

Open-source Python framework for multi-agent AI orchestration, coding-agent swarms, council voting, provider routing, browser tools, MCP connectors, and workflow automation.

cross-llm-delivery★ 8

Route bulk implementation to cheap executor LLMs (opencode/antigravity/cursor) with Claude as architect + judge - committed failing tests are the merge gate

frontier-orchestrator★ 8

Multi-agent orchestration for Claude Code: MCP server + skill that keeps Claude as lead engineer while delegating backend work to OpenAI Codex and frontend/design work to Kimi

build-studio★ 8

Mission control for multi-agent Claude Code workflows — run an AI product team across your projects

evollm★ 8

Code for 'Will Systems of LLM Agents Lead to Cooperation?' (AAMAS 2025)

swarm★ 8

Autonomous multi-agent orchestrator skill: fans out sub-agents to explore, diagnose, fix, review and verify a codebase — cross-checked, ledger-backed, doesn't stop until it's production-ready

a2acast★ 8

Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server

hscc★ 8

Turn a DGX Spark GPU cluster into a self-running team of specialized AI agents — cluster control, role-specialized workers, and an autonomous review gate for Hermes

orchgraph★ 8

Renderer toolkit for visualizing live AI agent and subagent orchestration graphs in Terminal, SVG, or HTML, laid out with ELK.

astrean-worker-lanes★ 8

A platform-neutral playbook for self-dispatch, worker lanes, and bounded AI-agent delegation.

ensemblr★ 8

Desktop orchestrator for Pi and Claude Code. Every stream of work gets its own git worktree, and an agent can drive the app itself — spawn sub-agents, delegate, integrate.

AgentXFlow★ 8

Authoritative multi-agent software engineering coordinator with isolated Git worktrees, write scope locking, test verification, and serialized merge queue. (v0.1.0-beta).

dsh-agent-message★ 8

DeepSeek Harness 跨会话 Agent 通信插件|Cross-session agent-to-agent messaging with offline delivery, receipts and session navigation for DeepSeek Harness.

komnet★ 8

Git-backed message bus for AI coding agents — Claude Code, Cursor and Codex coordinate asynchronously, with no server

dsh-multi-model-orchestrator★ 8

Provider-neutral dual-subagent orchestrator preset for DeepSeek Harness

codex-harness-javascript★ 8

Multi-agent harness for OpenAI Codex with Jira-backed workflows, pause/resume, progressive capability loading, and frontend delivery for JavaScript projects.

orchadyn-open★ 8

Enterprise Capability Planning Compiler for governed, runtime-neutral business plans.

crewscope★ 8

可自部署的团队协作式 AI 工作执行平台,基于 AgentScope Java:从对话目标到任务规划、Coding、Review、Human Gate 与 GitHub 交付,全程可观测、可恢复、可审计。Self-hosted team-execution platform for agentic coding: conversations become planned tasks, sandboxed coding runs and human-gated GitHub delivery.

genpark-hierarchical-swarm-task-delegation-governor-skill★ 8

CrewAI / AutoGen hierarchical swarm task delegation & role governor

genpark-bidirectional-human-agent-state-sync-coordinator-skill★ 8

CoAgents / CopilotKit bidirectional human-agent workspace state sync coordinator

genpark-agent-to-agent-capability-handshake-negotiator-skill★ 8

A2A standardized protocol capability negotiation & JWT auth handshake

luna-max-orchestrator★ 8

Codex skill for orchestrating isolated GPT-5.6 Luna Max worker chats with GPT-5.6 Sol.

genpark-agentic-hallucination-cross-examination-debate-skill★ 8

Dialectic multi-agent debate and cross-examination engine to eliminate hallucinations (AutoGen / ChatDev)

genpark-hierarchical-task-decomposition-dag-scheduler-skill★ 8

Hierarchical task breakdown into DAGs with worker matching & wave scheduling (CrewAI / MetaGPT)

genpark-agent-breakpoint-checkpoint-approval-patcher-skill★ 8

LangGraph human-in-the-loop breakpoint pause & state mutation patcher

genpark-agent-context-handoff-state-packer-skill★ 8

Lossless context packaging and state handoff protocol between autonomous subagents (OpenAI Swarm / LangGraph)

genpark-subagent-budget-token-quota-sentinel-skill★ 8

Hierarchical subagent resource governor and token quota sentinel (CrewAI / LangSmith)

genpark-multi-agent-consensus-voting-protocol-skill★ 8

Multi-agent proposal deliberation and Byzantine-fault-tolerant consensus voting protocol (AutoGen / LangGraph)

genpark-agent-hierarchical-delegation-supervisor-skill★ 8

GenPark AI Agent Skill - Hierarchical supervisor-worker swarm coordinator, sub-task partitioner, and synthesized response aggregator.

genpark-multi-agent-round-robin-turn-orchestrator-skill★ 8

GenPark AI Agent Skill - Multi-agent conversational turn orchestrator, round-robin handoff tokens, and speaker selection router.

genpark-raft-distributed-consensus-state-machine-skill★ 8

GenPark AI Agent Skill - Raft distributed consensus state machine with leader election, log replication, and deterministic commit index synchronization across agent swarms.

genpark-vector-clock-causality-tracker-skill★ 8

GenPark AI Agent Skill - Vector clock and Lamport logical timestamp engine tracking causal dependencies and detecting concurrent race conditions across asynchronous agents.

genpark-weighted-borda-count-preference-aggregator-skill★ 8

GenPark AI Agent Skill - Weighted Borda count and Condorcet preference aggregation engine ranking candidate agent proposals by credibility-weighted peer ballots.

More in Agent frameworks & infrastructure