muti-agent 开源项目推荐（59 个）

Onelevenvy /flock

由Rust、Tauri和React构建的桌面多代理工具，由langgraph-rust提供支持。

agentscope-ai /agentscope-go

AgentScope Golang: Agent-Oriented Programming for Building LLM Applications

mkassaf /langgraph-complete-guide

A complete LangGraph guide for PhD students and researchers. From zero to multi-agent systems with Python examples (chatbots, ReAct agents, supervisor patterns, research pipelines).

Notyourbing /MultiAgentPathFinding

同济大学群体智能期末项目，多智能体路径规划与拥堵控制+强化学习算法

wyx135230 /DeepSeek-Office

Built with the dsh-bot plugin, this is an immersive 2.5D office game where you interact and collaborate with your agent employees.基于dsh-bot插件制作，沉浸式2.5D办公室游戏，与你的agent员工交互协作

skygazer42 /Glyph

基于autogen开发的政务咨询智能助手

Yuan-ManX /Memex

Memex — Memory Infrastructure for AI Agents.

sligter /qunica

Bring humans and AI agents into one room to plan, delegate, code, and ship. Shared conversation history and project files, 4 group routing topologies, ACP external CLI integration, and guarded shell approval workflows.

firstsnowcg /SwarmPentest

SwarmPentest: World's first open-source multi-agent automated penetration testing framework featuring a blackboard system and plug-in architecture for third-party agent integration, designed for LLM-support.

IRISX-AI /IRIS-GO

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

ai-4Work /iWork

自主办公智能体

bssm-oss /CodeAgora

Code review, but with 5 models arguing first.

jujubooom /WebCmsAutoDigger

WebAutoCmsDigger：人人可用的 AI 漏洞挖掘协作系统，让代码审计从“难而慢”变成“快且可落地”。 面向实战场景的开源多智能体安全框架，支持一键运行，自动完成项目侦察、风险点定位、LSP调用链追踪、污点分析与逻辑漏洞推演。 自动生成结构化审计报告与可视化调用链结果。 让安全能力不再依赖少数专家，让高质量审计成为每个团队都能拥有的基础能力。

zenus10 /PreUser

基于muti-agent的虚拟用户模拟平台——针对vibecoding者

RijoSLal /God-s-eye-v2

God's Eye v2 is a terminal-native, multi-agent penetration testing system that combines autonomous agent orchestration, advanced search, and remote Kali Linux capabilities to perform offensive security workflows with minimal human input. Designed as an experiment in autonomous cyber operations, it explores the practical and ethical boundaries of hi

bruce601080102 /ccc-mcp

Stop trusting "tests passed." Orchestrate ChatGPT, Codex & Claude Code over MCP, with evidence for every handoff: host-run tests, versioned shared context, quota fallback and recoverable tasks.

ferris-joy /flock

Flock is a native desktop AI agent application built with Rust and Tauri, enabling multi-provider LLM support, tool orchestration, memory, and skills systems. It provides structured automation, persistent sessions, and accessibility-driven agent workflows for powerful cross-app control.

divyat2605 /creator-collab-coordinator

Multi-agent AI system that automates brand–creator collaboration approvals using a shared-memory ledger for intelligent campaign matching and eligibility decisions.

freyzo /arxiv-deep-research

ArXiv MCP server built for multi-agent systems like Magentic-UI and AutoGen

Sma1lboy /ArcticAI

🦊 An intelligent multi-agent framework for CodeFox ecosystem that orchestrates collaborative AI agents with adaptive decision-making capabilities.