Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 12 of 62

Cyber-Ming-Protocol★ 57

A Sovereign Agent Governance Protocol for Deep-Water Workflows

LLM-Deliberation★ 57

Code for our NeurIPS'24 Dataset and Benchmark paper: Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation

ai-long-task★ 57
dpc-messenger★ 57

Since November 2025 D-PC Messenger, a decentralized, Privacy-First Infrastructure for Human-AI-Team Collaboration

nexus-agents★ 57

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

hermes-council★ 57

Multi-agent debate system for Hermes Agent — spawn custom-composed expert agents to debate any question in structured rounds, producing visible transcripts and synthesized recommendations. Pure SKILL.md, zero new infrastructure.

gitlord★ 57

Agent orchestration framework with Git-backed storage. Every turn is a Git commit - inspectable, rewindable, forkable.

Azure-ai-foundry-erp-swarm★ 57

Autonomous SAP S/4HANA & ServiceNow Supply Chain Multi-Agent Swarm on Azure AI Foundry with Two-Phase Commit Safety

mcode-agent-table★ 57

BYOB Table Protocol v0.1 and reference implementation: bring your own agent (MiniMax Code and others) to one shared table for any-topology discussion and collaboration.

Electric_Vehicle_Charging_Simulation★ 56

This project implements Q-Learning to find the optimal policy for charging and discharging electric vehicles in a V2G scheme under conditions of uncertain commitment of EV owners. The problem is modelled as a multi-objective multi-agent cooperative game. Project is part of fulfillment criteria for ECE 730 course at the University of Alberta.

Flocking-Multi-Agent★ 56

Python implementation of "Flocking for multi-agent dynamic systems: Algorithms and theory" by Olfati-Saber for multi-agent triangular formation.

MASA-QMIX★ 56

Codes for paper of 'Solving job scheduling problems in a resource preemption environment with multi-agent reinforcement learning'

agentic-playground★ 56

This is an AI agent playground to demonstrate different agent orchestration patterns and capabilities

Vrooli★ 56

Open-source, self-improving autonomous agent swarm🐇

squads-cli★ 56

CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

crewplane★ 56

Run reviewable, resumable coding-agent workflows across Claude Code, Codex, Gemini, GitHub Copilot CLI, or any CLI. You define the stages in Markdown; Crewplane runs the workflow, agents do the work, and every handoff stays on disk.

three-tier-agent-orchestrator★ 56

Codex 三層多代理協作 Skill:Sol 統籌與複雜推理、Terra High/XHigh 處理視覺與操作、Luna Max 執行可重複工作。

james_library★ 56

(Officially move to Lop Nur Twin) R.A.I.N. Lab is an experimental scientific-agent architecture that separates fast local judgment, independent probabilistic evaluation, multi-agent deliberation, evidence, and authorization into distinct computational layers.🐙(Predates Karpathy's AutoResearch)

dsh-multitask★ 56

A Multitask "shock absorber" plugin & agent preset for DeepSeek Harness (DSH): the main chat only plans, briefs subagents and summarizes results, while file reads, commands, search and builds all run inside subagent contexts. Four worker types, an approval gate, zero DSH source changes.

W-MADDPG★ 55

An intelligent task offloading method based on multi-agent deep reinforcement learning in ultra-dense heterogeneous network with mobile edge computing

a2a-net★ 55

.NET implementation of the Agent2Agent (A2A) protocol to enable secure, interoperable communication between autonomous agents across frameworks and vendors.

MARL_UAV★ 55

This repository implements the proposed method from IEEE 2020 Paper Multi-Agent Reinforcement Learning Based Resource Allocation for UAV Networks Donate me: 8660186868668 MB Bank

DRL-UCS-AoI-Threshold★ 55

[ToN 2024] Ensuring Threshold AoI for UAV-assisted Mobile Crowdsensing by Multi-Agent Deep Reinforcement Learning with Transformer

A-Team★ 55

Multi-agent system that designs and generates complete agent team structures through conversational interviews. Supports Claude Code and Codex.

let-them-talk★ 55

MCP message broker + web dashboard for inter-agent communication. Let AI CLI agents (Claude Code, Gemini CLI, Codex CLI) talk to each other.

cloudflare-multiagent★ 55

Multi-agent AI platform on Cloudflare Workers — public preview (v0.1.x)

dsh_workflow★ 55

把Claude Code的UltraCode模式带给DSH,把 DSH 的一次性多 Agent 调度,升级为可生成、可保存、可治理、可观察、可恢复的 Workflow 层

AgenticPay★ 55

[NeurIPS 2026]AgenticPay: A Multi-Agent LLM Negotiation System for Buyer–Seller Transactions

QuorumForge★ 55

A multi-agent evidence adjudication engine - normalize claims, weigh support and contradiction, render deterministic verdicts. Rust core, std-only, zero dependencies, with a TypeScript council viewer.

SwaT★ 55

SwaT: Allowing LLM Agents to communicate without text. Prefill-free cross-family KV-cache transfer for LLMs communication using latent states instead of text.

Recurrent-Multiagent-Deep-Deterministic-Policy-Gradient-with-Difference-Rewards★ 54

Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging simulated continuous control single agent tasks. These methods have further been extended to multiagent domains in cooperative, competitive or mixed environments. This paper primarily focuses on multiagent cooperative settings which can be modeled for several real world problems such as coordination of autonomous vehicles and warehouse robots. However, these systems suffer from several challenges such as, structural credit assignment and partial observability. In this paper, we propose Recurrent Multiagent Deep Deterministic Policy Gradient (RMADDPG) algorithm which extends Multiagent Deep Determinisitic Policy Gradient algorithm - MADDPG \cite{lowe2017multi} by using a recurrent neural network for the actor policy. This helps to address partial observability by maintaining a sequence of past observations which networks learn to preserve in order to solve the POMDP. In addition, we use reward shaping through difference rewards to address structural credit assignment in a partially observed environment. We evaluate the performance of MADDPG and R-MADDPG with and without reward shaping in a Multiagent Particle Environment. We further show that reward shaped RMADDPG outperforms the baseline algorithm MADDPG in a partially observable environmental setting.

VBC★ 54

pytorch implementation of "Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control"

adk-mcp-a2a-crash-course★ 54

This project demonstrates a multi-agent system using Google's Agent Development Kit (ADK), Agent2Agent (A2A) and Model Context Protocol (MCP). that integrates Notion for information retrieval and ElevenLabs for text-to-speech conversion.

ai-multi-agent-presentation-builder★ 54
openclaw-paradigm-book★ 54

Used OpenClaw to set up an autonomous multi-agent system that reads OpenClaw's own source repo, gathers info from the web, and writes a full book about the platform.

MiroFish-ESP★ 54

Motor de Inteligencia de Enjambre para el mercado hispano 🐟 | Sube cualquier informe, predice el futuro al instante | Adaptación en español por EnPíxeles Lab

foolery★ 54

Agent orchestration Web-UI

devs★ 54

Delegate tasks to AI agent teams, from a browser tab.

Multi-Agent-★ 54
WorkFlowX★ 54

一个更强调可控、可追踪和 Token 效率的 AI 多智能体开发工作流 || An AI multi-agent development workflow that emphasizes controllability, traceability, and token efficiency

swarm-agent★ 54

An enterprise-grade implementation of multi-agent systems using OllamaJS, featuring advanced orchestration, dynamic agent allocation, and seamless integration capabilities.

agent-team★ 54

Multi-agent team collaboration for DeepSeek Harness, with independent models, skills, MCP tools, contexts, and a shared workspace.

pilotfish-codex★ 54

Codex CLI 版 pilotfish:GPT-5.6 分層(luna/terra/sol)的 multi-model orchestration,改編自 @Nanako0129/pilotfish / pilotfish for Codex CLI — multi-model orchestration with GPT-5.6 tiering

xylocopa★ 54

Xylocopa is a visual orchestrator that runs your Claude Code agents in a more organized way.

llegos★ 53

A strongly typed Python DSL for developing message passing multi agent systems

MADPL★ 53

Task-oriented Dialog Policy Learning with Multi-Agent Reinforcement Learning

agents_manager★ 53

A lightweight Python package for managing multi-agent orchestration. Easily define agents with custom instructions, tools, containers, and models, and orchestrate their interactions seamlessly. Perfect for building modular, collaborative AI systems.

mapf-visualizer★ 53

A Multi-Agent Path Finding visualization website.

aistack★ 53

Production-grade agent orchestration for Claude Code - 11 agents, 46 MCP tools, SQLite+FTS5, drift detection, consensus checkpoints

Deepagent-research-context-engineering★ 53

DeepAgent 기반 Research(연구) Multi Agent System 구축 - Context Engineering

multi-agent-framework★ 53

LLM multi-agent discussion framework for multi-agent/robot situations.

ChronicleCore-Architecture★ 53

The conceptual architecture and governance whitepaper for ChronicleCore, an enterprise-grade Multi-Agent orchestration framework.

nexus-agents★ 53

A distributed multi-modal agent orchestration framework implementing advanced natural language processing, computer vision, and audio processing capabilities through a microservices architecture.

HyperCat-Agent★ 53

A standalone, personality-driven multi-agent workspace application written in C, & C++

oap-agent-supervisor★ 52

A supervisor agent for open agent platform

beekeeper★ 52

An implementation of a multi-agent task management system that enables hierarchical agent coordination and task execution.

enterprise-ai-agents-spec★ 52

An open-source, detailed blueprint for implementing highly scalable swarms of specialized AI Agents in enterprise product development, emphasizing parallelization, robust governance, compliance, and minimal human oversight

Dorchestrator★ 52

My own multi agent tool with graph view , terminal view and agent management to build my little world.

Organized-LLM-Agents★ 52

Embodied and organized multi-LLM-agent teams supporting communication for >3 agents. Source codes for the paper "Embodied LLM Agents Learn to Cooperate in Organized Teams".

MARS★ 52

MARS is shortened for Multi-Agent Research Studio, a library for mulit-agent reinforcement learning research.

synthetic-user-research★ 52

Example Notebook for Synthetic User Research with Persona Prompting and Autonomous Agents

translator★ 52

layer that lets you connect any agent, any tool, any api together.

Hail_Hydra★ 52

🐉 Hail Hydra — Multi-headed speculative execution framework for Claude Code. 10 AI agents, 3x faster, ~70% cheaper. Inspired by speculative decoding.

devCrew_s1★ 52

Specification 1 (hierarchical style) for an agentic software development crew, for implementation with mainstream Agentic platforms like Claude Code, Strands, etc.

swarm★ 52

SWARM: System-Wide Assessment of Risk in Multi-agent systems

grokbot-gtm-team★ 52

My 13 Grok Bot GTM agents, the rules they work by, and the setup prompt that builds the team from 1 chat. Grok Bot orchestrates, Claude Code and Codex do the work.

PIC★ 51

PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning

MaDKit★ 51

Multi-agent systems Development Kit - version 6

AutoGenTest★ 51

微软开源多Agent智能体协作框架AutoGen全新改版核心概念介绍及相关案例测试

pi-squad★ 51

Multi-agent collaboration extension for pi — task decomposition, dependency management, parallel execution, TUI panel

Agentic_AI_using_LangGraph★ 51

Agentic AI framework built using LangGraph and Multi-Agent Control Plane (MCP) for building structured, goal-driven multi-agent systems.

auto-co-meta★ 51

Autonomous AI Company OS — 14 AI agents loop 24/7, ship real software

guidance-for-multi-agent-orchestration-using-bedrock-agentcore-on-aws★ 51

This Guidance demonstrates how to build and deploy multi-agent systems using Amazon Bedrock AgentCore and Strands Agents SDK.

ShallowCodeResearch★ 51

gradio mcp multi-agent research code-generation ai-assistant python web-search

Opencognit★ 51

OpenCognit Desktop — every coding agent in one window. Claude Code, Codex, Gemini CLI, Kimi and Hermes side by side, orchestrated and checked. Local, no telemetry.

RL-Ridesharing★ 50

Effcient Ridesharing Dispatch Using Multi-Agent Reinforcement Learning

multigrid★ 50

Fast and flexible multi-agent gridworld reinforcement learning environments.

OpenclawInterSystem★ 50

OpenclawInterSystem (OIS) - A collaboration framework for multi-agent OpenClaw deployments

MultiAgentSystem★ 50

针对基本的一阶二阶多智能体控制,给出了基本 的Matlab仿真

adapter★ 50

Building the Internet of Agents

asynkor★ 50

File leasing for AI agent teams. One MCP server. Any IDE. Zero merge conflicts.

v1★ 50

Open-source multi-agent platform that structures software engineering as a coordinated team of specialized AI agents. It enforces strict role separation, isolated execution sandboxes, structured communication, and secrets management.

broomy★ 50

Tool for making it easy to work with lots of AI agents

AgentChatBus★ 50

An MCP project that supports multiple agents chatting and collaborating with each other.

smaclite★ 50

The Starcraft Multi-Agent challenge lite

openclaw-world★ 50

3D virtual room where AI agents walk, chat, and collaborate as animated lobster avatars

InstAgent★ 50

InstAgent - ⚙️ Instantly transform natural language descriptions into powerful multi-agent systems 🤖 — define roles 🎭, equip them with the right tools 🧰, and generate ready-to-run code 💻 — all in one seamless flow, guided by a single instruction 🚀.

synapse★ 50

Headless, declarative multi-agent orchestration framework with a domain-agnostic signal bus, workflow engine with Postgres persistence, and configurable agent runtime (ships code review domain).

llm_coordination★ 50

Code repository for the NAACL 2025 paper "LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models"

pocket-universe★ 50

Agentic closed loop with async capabilities

agentClaw★ 50

Make openclaw`s agents for multiusers,just a agent platform for small teams.

TitanX★ 50

Enterprise AI Agent Orchestration Platform — Secure, Observable, Configurable. Multi-agent teams with IAM policies, n8n workflows, LangChain memory, LangSmith traces, NemoClaw security, OpenTelemetry, and 20+ LLM providers.

crewform★ 50

Build your AI team with Crewform. Orchestrate specialized, autonomous agents to collaborate on complex tasks and connect outputs to your stack. — AI Orchestration for Everyone

worca-cc★ 50

Workflow Orchestration for Agents

agentverse★ 50

Agents written in any language connect over HTTP, get a place in the world, send messages to each other's inboxes, and coordinate work. Works with OpenCrabs, OpenClaw, ClaudeCode or any HTTP-capable agent. Built for teams to manage their agents. Built in Rust. TUI with Ratatui and GUI with Bevy 3D.

shachi★ 50

Reimagining Agent-based Modeling with Large Language Model Agents via Shachi

multiagent-business-automation★ 50

Multi Agent for Business Automation is a multi-agent orchestration platform for business automation and decision support. It coordinates specialized AI agents—each with distinct roles, personalities, and tools—through LangGraph workflows, shared memory, and human-in-the-loop (HITL) approval gates.

Interlat★ 50

[ACL 2026] Official respository for Interlat: Enabling Agents to Communicate Entirely in Latent Space

open-dynamic-workflows★ 50

Open-source dynamic multi-agent workflows for AI coding agents - the script-as-orchestrator engine behind Claude Code dynamic workflows & ultracode, for OpenCode, Codex, Antigravity & VS Code. Local-first, bring your own model (Anthropic/OpenAI/Ollama), MIT.

oh-my-multica★ 50

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

More in Agent frameworks & infrastructure