Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 18 of 62

multi-agent-spring-ai★ 29

A sample for multi-agent orchestration in Java using Azure Cosmos DB with Spring AI

claude-code-inter-session★ 29

Agent-to-agent messaging for Claude Code sessions on the same machine.

hermes-synapse★ 29

Visual multi-agent orchestrator with a drag-and-drop DAG canvas, dynamic LLM planning loops, permission-based tool execution, and local Qdrant RAG.

jido_claw★ 29

JidoClaw — Open-source OpenClaw alternative built on Jido for Elixir/OTP. AI agent CLI with swarm orchestration, 30 tools, multi-provider support, and live terminal display.

gMAS★ 29

Dynamic graph runtime for building, adapting, and observing multi-agent LLM systems in Python.

Diverter★ 29

Diverter distills Ultra’s delegation strategy into non-Ultra Codex sessions—bringing in the right native specialist while the main thread keeps moving.

swarm-map★ 29

Multiplayer admin and orchestrator platform for heterogeneous agent runtimes — Hermes (container-per-agent) and Letta (memory-first agents on a shared server) in one control plane, with multi-tenant security, group approval, and audit.

kixparadigm★ 29

kixparadigm — AI self-orchestrated minimal paradigm (resident cognition layer) + kixpower multi-agent orchestration · one-command import into DeepSeek Harness (npm i -g) / AI 自编排最小范式(认知层常驻)× kixpower 多智能体编排 · npm 一键导入 DeepSeek Harness

hadron★ 29

A native Rust multi-agent operating system and swarm workspace — GPUI desktop chamber, headless gluon daemon, git-worktree isolation and an automatic merge gate.

ActiveInferAnts★ 29

Multi-language Active Inference framework combining ant-colony-optimization-inspired multi-agent simulation with variational message passing, implemented across 50 programming languages for research and benchmarking.

1★ 29

多 Agent 编排桌面应用。创建角色、技能与能力,通过 6 种编排模式组建协作工作流。基于 Electron + React + TypeScript 构建

DSH-pipeline-kernel★ 29
vigil★ 29

A native macOS multi-agent terminal orchestrator: manager-driven agent trees for Claude Code, Codex, and OpenCode

10xGraph★ 29

Production-grade framework for building multi-agent AI systems. Graph-based orchestration, LLM-agnostic (OpenAI, Google GenAI, Anthropic), 3-layer memory (Redis cache + Postgres + vector store), live agents, parallel tool execution, and native MCP. Ships a full ecosystem: backend, REST API + CLI, TypeScript SDK, and React playground

bot-team-playbook★ 29

One person, one bot team: supervisor + specialist Grok Bot teams with copy-ready prompts for 8 personas · 一个人,一支 Bot 团队

grokbot-dsh-orchestrator-vn★ 29

Biến Grok Bot thành lớp điều phối, DeepSeek Harness làm worker giá rẻ — tiết kiệm quota, chạy liên tục

orcha★ 29

Orcha — multi-agent orchestration platform (CLI, FastAPI portal, desktop app)

vedang-swarm-prediction★ 28

Swarm Intelligence Prediction Engine - Multi-agent AI debate for calibrated forecasting

madara★ 28

Multi-Agent Distributed Adaptive Resource Allocation

MultiAgent-Research-Ideator★ 28

Code for our paper: "Exploring Design of Multi-Agent LLM Dialogues for Research Ideation", SIGDIAL2025

multi-agent-pathfinding★ 28

Heuristic Search vs. Learning. "Distributed Heuristic Multi-Agent Path Finding with Communication" reproduced, trained & benchmarked with M*

multi-agent-a2a★ 28

example of a multi-agent-a2a

socrate★ 28

Run `npm i -g socrate` to install a discussion room for using GPT personalities with internal monologues to debate problems. Provide a problem to start, or customize the settings of the debate room. Custom agents incoming!

agentic-collaboration-standard★ 28

A unified open format for agent-ready projects across tools, teams, and platforms.

multi-agent-orchestration-framework★ 28

Modular multi-agent orchestration framework powered by LangGraph and FastAPI.

Awesome-LLM-based-MultiAgents★ 28
TMC★ 28

Pytorch implementation of "Succinct and Robust Multi-Agent Communication With Temporal Message Control"

Distributed-consensus-of-linear-multi-agent-systems-with-adaptive-dynamic-protoc★ 28

具有自适应动态协议的线性多智能体系统的分布式一致性

ofcourse★ 28

Order Fulfillment by Multi-Agent Reinforcement Learning

thrum★ 28

Persistent Git-backed messaging for AI coding agents — coordinate Claude Code, Codex, and others across sessions, worktrees, and machines.

MCP-MultiServer-Interoperable-Agent2Agent-LangGraph-AI-System★ 28

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independently (via SSE or STDIO), offering modularity and cloud-deployable execut

CrewAIFullstackTest★ 28

本项目带大家搭建一个完整的AI应用全栈项目,Flask+Vue.js+CrewAI

AgentManager★ 28

Conduct autonomous Claude Code agents at scale safely. Human-on-the-loop orchestration platform with kill switch, cost tracking, and inter-agent messaging.

gitguardex★ 28

Run many Codex & Claude agents in parallel without them overwriting each other. Isolated worktrees, file locks, PR-only merges. Auto-wires Oh My Codex, Oh My Claude, OpenSpec, and Caveman in every worktree.

ordine★ 28

🪄 Ordine: reliable orchestration for autonomous multi-agent systems.

DMAD★ 28

[ICLR 2025] Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate

Multi-AI-Agents-Cloud-Native★ 28

These are multi-ai-agents samples for Cloud Native

stem-agent★ 28

Self-adapting, Tool-enabled, Extensible, Multi-agent System

agentVerse★ 28

gradio region:us

GlossoGen★ 28

A platform for running controlled experiments on teams of LLM agents: multi-agent simulations, an event-sourced run log, swap and fork interventions, and post-hoc evaluation metrics.

nouride-releases★ 28

Lightweight, zero-bloat multi-agent AI engine in a single daemon. Homelab-friendly and built for mini devices (Raspberry Pi, Orange Pi, Geekom, NUC, LXC).

the-agency-starter★ 28

Convention-over-configuration framework for multi-agent Claude Code development

agent-peer-bridge★ 28

借脑:把团队里 AI 用得最好的那个人的 AI,借给每个人。Let coding agents on different machines start, continue and read each other's sessions (Claude Code ↔ Codex), with per-person permissions and rules. No inbound ports.

thrum★ 28

Persistent Git-backed messaging for AI coding agents — coordinate Claude Code, Codex, and others across sessions, worktrees, and machines.

FCMADRL★ 27

Fully Cooperative Multi-Agent Deep Reinforcement Learning

viche★ 27

Bespoke agent-to-agent discovery and communication protocol

townhall★ 27

A Python-based chatbot project built on the autogen and tinygrad foundation, utilizing advanced agents for dynamic conversations and function orchestration, enhancing and expanding traditional chatbot capabilities.

temporal-multi-agent-order-repair★ 27

An example showing how to do different kinds of AI agents with Temporal in an order repair context

PRISMA★ 27

Packet Routing Simulator for Multi-Agent Reinforcement Learning

LogiCity★ 27

LogiCity@NeurIPS'24, D&B track. A multi-agent inductive learning environment for "abstractions".

HAVEN★ 27

Codes for the paper "HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism"

Distributed-Learning-and-Cooperative-Control★ 27

Codes reproducing paper Jongeun Choi, Songhwai Oh, Roberto Horowitz, Distributed learning and cooperative control for multi-agent systems, Automatica, Volume 45, Issue 12, 2009

ClawTabs★ 27

Multi-agent command hub for AI coordination. Connect multiple OpenClaw agents, coordinate via channels, manage tasks. Local-first, no servers.

cursor-experiments★ 27

Demo: Multi-Agent Orchestration in Cursor

orc★ 27

A lightweight orchestration framework that piggybacks your local Agentic CLI setup. Intentionally simple. Yet powerful... like an army of Orcs 👹

maestro★ 27

Multi-agent orchestration platform. Deploy any AI agent to any interface.

dark-factory★ 27

🏭 Agentic dark factory for AI building with sealed-envelope testing

Orchestra★ 27

Governed AI workflow orchestration for complex software development, coordinating specialist skills, validation, security review, human gates, and execution continuity.

memclaw-build-fleet★ 27

A runnable reference implementation of multi-agent constraint propagation using MemClaw. 5 specialists share memory via MCP so decisions made upstream automatically govern downstream agents.

kynomesh★ 27

Kubernetes-native platform for orchestrating distributed multi-agent systems.

HYGMA★ 27

Code for ICML25 paper "HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning"

Langgraph1.0★ 27

这是一个最小化的Multi Agent项目模板,帮助你理解 LangGraph 1.0的核心概念,并快速上手开发自己的多Agent应用。

mogui-ADE-orchestrator★ 27

Run one AI agent as the orchestrator of your whole workspace, inside the Orca ADE, on the CLI subscription you already pay for. No API key, no model endpoint. Orca hosts and places every session; the harness dispatches workers under contract, verifies their output before accepting it, and hands the role to a fresh session when context runs out.

a2wave★ 27

Turn the agent CLIs you already use into shared services your whole team can call. Natural-language-driven agent orchestration for Claude Code, Cursor Agent, and OpenAI Codex.

agent2world★ 27

🪐 Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback

CivicMesh★ 27

Multi-agent AI navigator that routes people in crisis to housing, food, healthcare and legal aid. 7 walkers, 40 real resources, any language. Built in Jac.

agentran★ 27

AgentRAN: Multi-Agent Framework for AI-RAN Control

agora★ 27

Self-driving multi-agent development team plugin for Hermes Agent — role-based workers discuss, vote, and execute on a shared Kanban board

SocioVerse2★ 27

SocioVerse2: A Longitudinal Dynamic Social Simulation Framework under a Human-AI Co-evolutionary Paradigm

course-builder★ 27

AI multi-agent harness that plans, designs, and produces online courses (slides + notes + TTS audio + quiz + player) from a topic using ADDIE + Bloom's Taxonomy.

MASPY★ 27

A Python Framework for Multi-Agent Programming with Machine Learning

inai★ 26

Autonomous Agentic Coordination Framework (WIP)

crewlit★ 26

🚣 Crewlit brings the power of CrewAI to your browser, making multi-agent AI systems accessible to everyone.

stoa★ 26

Multi-agent swarm framework. Seven autonomous agents. 30 skills. One shared mesh. Zero infrastructure.

Neuron★ 26

Neuron is a composable agent framework. It enables you to build, orchestrate, and monitor intelligent multi-agent systems using a modular circuit-based architecture.

EzCoworker★ 26

A multi-user Claude Code CLI based Coworker with Multi Agent Orchestrator, Multi model support including Ollama models, Advanced Functional skills, Channel integration for Chat and text messaging platform running completely in docker containers with an Admin module for complete visibility and observability

aperture★ 26

The human-attention system for agent work.

VisionClaw-Agent-Public-Release★ 26

AI agent platform: 18 personas, 428 tools, 68 skills, 148 capabilities and 100 curated models. Owner-first access, scoped MCP, local inference and documented safety limits. R137.3+sec2 source; not production certification.

agents-chat★ 26

An open-source AI agent platform for orchestrating, and collaborating with multiple AI agents. Connect seamlessly to GitHub Copilot CLI, Claude Code, Codex, and any ACP-compatible agent.

glueRun-go★ 26

Autonomous multi-agent orchestration engine for software repos — L0/L1/L2 agents, leases, gates, audits, git-worktree isolation. Detached dispatch by default. GPL-3.0.

FoX★ 26

This repository considers the implementation of the paper "FoX: Formation-aware exploration in multi-agent reinforcement learning" which has been accepted to AAAI 2024

multi-agent-chatbot★ 26

Multi-agent chatbot with integrated search engine, utilizing a plan-execute-replan approach for complex queries, built with LangGraph and Tavily.

AzureAgentForge★ 26

Turnkey, self-hostable multi-agent AI platform on Azure - PaperClip orchestration + Hermes runtime + Honcho memory + OpenAI-compatible model router, deployed via Terraform to Container Apps.

Nexora★ 26

Self-hosted, MIT-licensed AI-agent orchestration platform. Agents with personas, skills & tools that chat, run ~90 tools, delegate to sub-agents, and stream results across ~46 LLM providers. RAG, semantic memory, marketplace.

ggo_public★ 26

Official implementation of the paper "Guidance Graph Optimization for Lifelong Multi-Agent Path Finding", published in IJCAI 2024.

Multi-Agent-Channel★ 26
claude-agent-os★ 26

Agent operating system for Claude Code: a CEO agent plans, five roles execute, you get 15-minute tasks and decisions. Plain Markdown files, MIT.

colosseum★ 26

A framework for auditing collusion in agentic multi-agent systems

inai★ 26

Autonomous Agentic Coordination Framework (WIP)

Master-Orchestrator★ 25

一个迭代器,可以迭代任何项目,包括他自己

sutra-mas★ 25

36,299 multi-agent systems papers collected, 17,969 analyzed with coordination patterns, embeddings, and a 16-cluster taxonomy — the largest structured MAS corpus bridging 30 years of classical research with modern LLM agents

multi-agent-arch★ 25

A unified interactive portal solution for multiple agents, enabling users to access multiple types of agent services through a single interface.

gpt-mind★ 25

A multi-agent mind implemented using LLMs engaged in ongoing conversation

ain★ 25

AIN is an AI-only, AI-native social network implemented as a peer-to-peer gossip mesh where autonomous agents exchange signed, content-addressed events and artifacts, prioritized by information gain and verified utility (not engagement).

ValueDecomposition★ 25

Value-Decomposition Networks For Cooperative Multi-Agent Learning

Adv-MARL★ 25

Adversarial attacks in consensus-based multi-agent reinforcement learning

asolaria-behcs-256★ 25

Federated multi-agent civilization toolkit · 19 supervisors/tools · SMP v5+ GA 2026-04-20

MAMR★ 25

Code for Multi-agent reinforcement learning to unify order-matching and vehicle-repositioning in ride-hailing services

ICES★ 25

[ICML' 24] The PyTorch implementation of our paper: "Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning".

summoner-agents★ 25

A collection of Summoner clients and agents featuring example implementations and reusable templates

More in Agent frameworks & infrastructure