Agent frameworks & infrastructure

Multi-agent orchestration

6,185 agents · most starred first

Multi-agent orchestration, page 36 of 62

MAGI★ 4

Modular Agentic Genesis Intelligences

arthur-agent★ 4

Deep Search Pro - 一个轻量的多智能体协作系统(Agent 开发入门实战项目)

-PredictAnything-AI-Skill★ 4

Agent skill for exploring what-if scenarios through personas, multi-round swarm simulations and structured scenario reports inspired by MiroFish.

hermes-office★ 4

把你的 Hermes AI 员工放进一间看得见的办公室:老板办公室 / 经理办公室 / 开放工位区 / 聊天室 @ 派活

bead-rs★ 4

Task-coordination store for agent fleets — a dependency graph of beads in SQLite, one unblocked bead per request via an atomic single-transaction claim, and a git-tracked checkpoint for recovery. Rust.

agent-world★ 4

🌍 A survival sandbox world for AI agents — they trade, cooperate, specialize, or die. Rust + Python + Next.js.

vantage-peers★ 4

Open-source coordination backend for AI agent teams. Shared memory, messaging, tasks via MCP. 20 tables, 75 tools. Convex-native.

veritas-ai★ 3

🤖 Enterprise multi-agent orchestration platform for autonomous content verification. Built with agentic AI workflows, MCP integration, AgentDB, and advanced deepfake detection. Features agent memory, learning, and collaboration.

sim-mcp-token★ 3

Agent-based economic simulation with 50 autonomous agents, limited resources, income/expense dynamics, and configurable policies (taxes, elasticity, regeneration rates). Outputs Gini coefficient and bankruptcy analysis.

synapse-protocol★ 3

Asynchronous multi-agent collaboration protocol with human supervision — Redis pub/sub, documentary contract model, state-machine orchestration. Apache 2.0.

earcp★ 3

A Self-Regulating Coherence-Aware Ensemble Architecture for Sequential Decision Making/EARCP: Ensemble Auto-Régulé par Cohérence et Performance

vichara-ai★ 3

Vichara AI is a modern distributed task orchestration system designed for scalable background processing, intelligent retry mechanisms, job scheduling, and real-time monitoring across worker clusters.

YOAP-A2A★ 3

YOAP - Open Agent-to-Agent Protocol for connecting people through AI Agents. Like open-source matchmaking.

Agentis★ 3

Most AI tools give you one model and one answer. Agentis gives you a team. Open-source multi-agent platform across 12 LLM providers — watch agents think, collaborate, and deliver in real time.

IRIS-GO★ 3

IRIS GO 🚀 — Local multi-agent orchestration. Build, control, and watch autonomous AI execute system-level workflows via CLI, mobile, or dashboard.

AutoOrg★ 3

AutoOrg — Build Fully Automated AI Agent Organizations.

argus-ai-debate★ 3

Debate-native multi-agent AI framework that eliminates LLM hallucination, overconfidence, and opacity. Structures knowledge evaluation as adversarial multi-round debates over a Conceptual Debate Graph (C-DAG) with Bayesian aggregation, CRUX protocol, 8 novel Evolution extensions, 27+ LLM providers, 50+ tools, and W3C-compliant provenance tracking.

moonjelly-reef★ 3

Label-driven orchestrator that routes work to different sub-agents based on labels and keeps looping until all automated work is done.

multi-agent-llm-recipe-prices★ 3

Multi-agent LLM system for meal planning and grocery budgeting, integrating recipe retrieval and ingredient price lookup using LLMs, SQL and vector databases.

Multi-Agent★ 3

[Hitachi Digital Services] Demo on LangGraph-based Lightweight Multi-Agent System

forgent★ 3

forgent — meta-orchestrator that grows its own AI subagents on demand. Routes any task across Claude Code subagents, Python frameworks, and MCP servers.

t4★ 3

T4: Multi-Agent - System uses agents. Agents collaborate. Shared canvas holds work. Adapting for code improvement. (Orchestration, System prompt updates, Shared canvas, simple dynamic workflows)

agent-os★ 3

Configurable framework for running multi-agent Claude Code teams. Zero external dependencies.

metacognition★ 3

mBFT: Metacognitive Byzantine Fault Tolerance — reference implementation for Consensus-Driven Metacognition in Multi-Agent Systems

agent-validator★ 3

A production-quality demo of agentic AI systems — LangGraph multi-agent orchestration, browser automation, Slack integration, and LangSmith observability

Swarms-CloudFlare-Deployment★ 3

Learn how to deploy your swarms applications on cloudflare workers

vMAS★ 3

A versatile multi-agent system (vMAS) using the Scrum framework, Python, Langchain, and GitHub for task management.

LLMOps-for-agentic-ai★ 3

LLMOps: A production-ready platform for building, deploying, and managing customizable multi-agent AI chatbots. The system leverages modern LLMs, agent frameworks, and search tools to provide interactive, context-aware conversations.

crewai_multiagent★ 3

CrewAI Multiagent is an AI-powered automation suite for research, news, poetry, code execution, and PDF search. It leverages intelligent agents, web scraping, NLP, and code interpretation to generate reports, articles, and perform data analysis, streamlining automation across multiple domains.

chess_ai_agents★ 3

A chess face-off between AI Agents using AutoGen. Visualize every move and watch AI vs AI, turn by turn.

Harness-Skills_Multi-Agent_AI_PM★ 3

自研先进 Skill+Harness 双轨架构 · 多Agent协作开发框架 v3.1 Ironforge — 高解耦+平台无关+企业工程化(安全强制执行/确定性恢复/自动化可观测)

mage★ 3

Multi-Agent Grid Environment (MAGE)

multi-agent-reinforcement-learning★ 3

Multi-Agent Reinforcement Learning with Deep Sarsa Agents

LearningNashQLearning★ 3

A Jupyter Notebook applet to teach and explore Multi Agent Reinforcement Learning - the Nash Q Learning. "Multi agent systems" project @ PoliMi

qwen-swarm★ 3

🧠 Revolutionary multi-agent orchestration platform with swarm intelligence, self-improving capabilities, and intuitive GUI management built on Qwen Code

claw-swarm★ 3

Field-mediated swarm intelligence for multi-agent LLM coordination — 12-dimensional signal field, 7-domain architecture, 20 bio-inspired algorithms, zero feature flags

kbtz★ 3

Task tracker for AI agents

marl-mo★ 3

Multi-Objective Multi-Agent RL with non-linear utility functions

swarm-js★ 3

Javascript implementation of the Swarm Project by OpenAI

sumo-mappo★ 3

MAPPO experiments for unsignalized intersections using SUMO and Gym.

neuroswarms★ 3

Neural swarming controller models for multi-agent and single-entity simulations.

ystar-bridge-labs★ 3

A real company operated by AI agents, governed by Y*gov

SocioAtlas★ 3

AI-powered social simulation platform for exploring how personas, groups, and coalitions react to events over time.

shepherding-problem★ 3

shepherd model

swarm-agent★ 3
agent-orchestration★ 3

The coordination problems are fifty years old. The frameworks are new.

tianyan-3.0★ 3

人体智能体协作模式-多智能体架构系统

LOOP-STATION★ 3

Agent skill for bounded goal loops, multi-agent review, adaptive sessions, and safe implementation variants.

subagent-cli★ 3

Managing Coding Agents for Coding Agent

CrewForge★ 3

A virtual team in your terminal: multiple AI agents discuss and converge, so you don't have to iterate alone.

trust-based-public-goods-game★ 3

Multi-agent simulation of a public goods game with trust dynamics and reinforcement learning

we-asked-100-agents-public-tr★ 3

Ask 100 AI agents representing Turkey's socio-economic diversity what they think — and get answers in seconds.

AOSD★ 3

AI Orchestrated Systems Development - A methodology for building software systems by orchestrating multiple AI agents

swarm-debate★ 3

Multi-LLM debate engine with a shared expert validator that fact-checks each round

aip-protocol★ 3

Agent Interoperability Protocol - A standardized protocol for AI Agent communication and collaboration

Acgs-Swarm★ 3

Constitutional Swarm Mesh — orchestrator-free multi-agent governance

openclaw-orchestrator★ 3

Manage complex tasks by breaking goals into subtasks, routing them to specialized agents, and iterating with an LLM-driven real-time orchestrator.

create-agent★ 3

A libarary of template A2A projects

agentdo.dev★ 3

Post a task, another agent does it. Distributed task queue for AI agents with long polling, schema validation, and zero infrastructure.

Multi-Agent-System-Google-ADK★ 3

🚀 An AI-powered multi-agent system using Google ADK that answers queries about rocket launches, weather, and news. It intelligently orchestrates specialized agents to fetch, process, and summarize information for clear, user-friendly responses.

TrippleEffect★ 3

Asynchronous, collaborative multi-agent framework.

tutu-ai★ 3

轻量级中文多智能体生成式仿真框架 · 8 个场景开箱即用 · OpenAI 兼容协议

LIFE★ 3

The MARS LIFE simulation engine

thinktankgpt★ 3

ThinkTankGPT leverages LLMs to simulate expert debates on any topic. Users can input a topic of their choice, and the system dynamically generates relevant experts who autonomously engage in a debate. Additionally, users have the option to join the discussion, adding an interactive element to the experience.

p2p-agent-mesh★ 3

P2P pub/sub transport for AI agents. IPFS gossipsub + Ed25519 + eventual consistency. No central broker.

a2a-gateway★ 3

Open-source gateway and community to make AI agents interoperable using Google's A2A protocol – like Hugging Face, but for agents.

AI_services_agency★ 3

🚀 An intelligent multi-agent platform for analyzing software project requirements, generating technical specifications, and delivering project strategies — powered by OpenAI agents working in synergy.

humanagentprotocol★ 3

A universal protocol for symbiotic collaboration between humans and autonomous AI agents. HAP enables AI agents to request human decisions in a structured, auditable, and latency-safe manner. Agents never block — they create tickets with defined timeout behaviors, allowing graceful degradation or escalation.

project-synapse★ 3

A production-grade demo of a multi-agent system showcasing Agent Communication Protocol (ACP) and Model Context Protocol (MCP) capabilities through a collaborative research workflow.

forge★ 3

FORGE: Federated Orchestration & Resource Generation Engine — intelligent control panel for AI coding agents. Rust.

adk-kitchen-renovation-multi-agent★ 3

AI-Powered Multi-Agent System for Smart Kitchen Renovation. Built with Vertex AI, ADK, MCP Toolbox, and Gemini 2.5, this project simulates intelligent collaboration between agents to optimize kitchen renovation tasks.

yes-ai-master2★ 3

Master Edition: A resilient, self-healing Multi-Agent AI Operating System. Features autonomous task orchestration (Navigator, Curator, Evaluator), Glass-Box observability, and a custom Circuit-Breaker auto-failover pattern (Gemini 3.0 → Llama 3/Qwen) for guaranteed 100% uptime.

semantic-kernel-food-ordering-agent★ 3

A multi-agent restaurant food ordering system using Semantic Kernel, A2A and Azure OpenAI. Includes a backend agent server, customer chat API, and sample UI for natural language food orders. MIT licensed and open for contributions.

vertex-ai-agent-research★ 3

Multi-agent AI system built with Google ADK and Vertex AI Agent Engine - 7 specialized sub-agents for university advising

football-manager-slms★ 3

Experiment with SLMs in a multi agent football management team

heureum-agent★ 3

Heureum Agent

agent2agent-strands-ai21-maestro★ 3

Agent-to-Agent AI Integration: AWS Security Analysis with AI21 Maestro & Strands Agents

semantic-kernel-agent-a2a-protocol-example★ 3

Semantic Kernel A2A protocol and A2A Discovery Service Example

integraciones★ 3

Integración del prototipo desarrollado por los participantes del laboratorio {DATAR} para la orquestación de agentes autónomos.

tm-swarm★ 3

A Python framework for N-agent collective learning using Tsetlin Machines and synthetic data sharing, supporting zero-shot sensor onboarding and LLM-driven feature extraction.

commander.ai★ 3

Mission Control for multi-agent AI systems. Real-time orchestration, live metrics, and complete visibility. Built with LangGraph, FastAPI, and Next.js.

ai-chatbot-multiagent★ 3

An AI-powered chatbot aimed to deliver accurate and contextually relevant responses by combining the strengths of pre-trained language models with specialized agents

stapler★ 3

Self-hosted AI org platform with a compounding Quality Flywheel — every run gets graded, every failure becomes a rule, every success becomes a playbook. Fork of paperclipai/paperclip.

reasonance★ 3

A collaborative AI reasoning platform built with Reflex that facilitates dialogue between Claude (Anthropic) and GPT (OpenAI). The application enables two LLMs to independently respond to prompts, critique each other's outputs, and iteratively converge on shared conclusions through multiple rounds of discussion.

multi-agents-lab-agno★ 3

Multiagent chatbot 🤖🤖🤖 - Lab with Agno and open source llms

chamberlain_multimodal_multiagent_chatbot★ 3

An AI-driven Multimodal multi-agent chatbot for home deployment to manage the user's daily chores and tasks. Used OpenAI and Langchain and MORE

modular-llm-architecture★ 3

Exploring the cognitive architecture and design of a multi-agent system leveraging Large Language Models (LLMs) for scalable workflows.

a2a-langgraph-agent★ 3

A sample project to demonstrate how a langgraph ReAct agent can be wrapped with the A2A protocol

AgentMesh★ 3

AgentMesh: A dynamic multi-agent orchestration system where users can create, configure, and connect AI agents defining their behaviors, interactions, and tool access all through an interactive visual builder.

distributed-multi-agent-platform★ 3

Reference distributed multi-agent platform using AutoGen, FastAPI, Redis, WebSockets, and semantic agent discovery.

roomq★ 3

🎥 Google Meet for AI agents — coordinate many agents from a single primary over a simple HTTP API, watched live in the browser. Self-hosted, 100% local.

SiliconLifeCollective★ 3

A .NET 9 multi-agent platform where AI agents (Silicon Beings) self-evolve via Roslyn dynamic compilation. Features tick-driven time-sliced scheduling, executor-permission security, and zero-database file storage. Cross-platform, single-file deployable.

mawa★ 3

Open governance architecture for multi-agent AI systems. Give your agents a job title, not just a job.

ThinkChain-AI★ 3

Multi-agent AI that turns prompts into structured, impact-driven decisions.

A2ALinker★ 3

HTTPS broker designed to let autonomous AI agents collaborate natively across different machines using standard terminal streams

multi-ai-cli★ 3

A lightweight CLI to orchestrate Gemini and GPT using your local files as a shared blackboard.

quorum★ 3

Multi-agent deliberation engine — AI personas compete on real-world questions scored against the Doughnut Economics framework, with every decision committed to a Dolt branch.

dureclaw★ 3

흩어진 컴퓨터와 브라우저를 하나의 AI 팀으로 — Agent Skills + MCP + 플러그인 (Claude Code · Codex · Gemini CLI · Cursor)

trellis★ 3

Design agent teams that take ideas from concept to launch. Custom pipelines, sandboxed execution, plugin marketplace.

agent-greenroom★ 3

A private backstage for AI agents

More in Agent frameworks & infrastructure