Claude Code、Codex CLI和Gemini CLI的多代理管弦乐平台。 使AI代理能够互相发现,实时通信,协调文件编辑,并作为一个团队在共享代码库上工作.

由MCP(模式背景协议)所建.

∮它会怎样∮

• Peer发现:物剂通过[[T0]互相发现.
• ** Real-time message**:由管弦乐发射克洛德和Codex代理在中转(stream-json stdin / turn/steer)接收队友消息;每个代理也收到为下一个工具结果准备的未读消息,一个消息在到达模型后才会被标记读取.
• ** 任务**:[[T2]、rename_peer运行时
• ** 系统协调**:专用锁+所有权区可防止冲突
• 任务周期:idle → working → done_pending_review → addressing_feedback → approved → released
• 审查循环:signal_done → submit_feedback → fix → re-review → approve
• ** 共享知识**:用于建筑决策、已发现模式和项目背景的持久关键价值储存——防止上下文漂移
• 持续会话:幸存代理重启,完整消息历史

multiagents

Multi-agent orchestration platform for Claude Code, Codex CLI, and Gemini CLI. Enables AI agents to discover each other, communicate in real-time, coordinate file edits, and work as a team on shared codebases.

Built on MCP (Model Context Protocol).

What It Does

┌─────────────┐     ┌─────────────┐     ┌─────────────┐
│ Claude Code  │     │  Codex CLI  │     │ Gemini CLI  │
│ (Engineer)   │     │ (Reviewer)  │     │ (Designer)  │
└──────┬───────┘     └──────┬──────┘     └──────┬──────┘
       │ ClaudeDriver + MCP │ CodexDriver + MCP  │ MCP (stdio)
       └────────────┬───────┴────────────────────┘
                    │
            ┌───────▼────────┐
            │  Broker Daemon  │  SQLite + HTTP on localhost:7899
            │  (singleton)    │
            └───────┬────────┘
                    │
            ┌───────▼────────┐
            │  Orchestrator   │  MCP server for Claude Code (or Claude Desktop)
            │  (team manager) │  Spawns agents, delivers messages,
            └────────────────┘  monitors progress, respawns crashes

• Peer discovery: agents find each other via list_peers
• Real-time messaging: orchestrator-launched Claude and Codex agents receive teammate messages mid-turn (stream-json stdin / turn/steer); every agent also gets unread messages prepended to its next tool result, and a message is only marked read once it reached the model
• Role assignment: assign_role, rename_peer at runtime
• File coordination: exclusive locks + ownership zones prevent conflicts
• Task lifecycle: idle → working → done_pending_review → addressing_feedback → approved → released
• Review loops: signal_done → submit_feedback → fix → re-review → approve
• Shared knowledge: persistent key-value store for architectural decisions, discovered patterns, and project context — prevents context drift across agents
• Persistent sessions: survive agent restarts, full message history
• Dashboards: a web dashboard on localhost:7900 with live WebSocket updates and a 5-tab TUI
• Auto-restart: crashed agents respawn with handoff context — a Claude agent resumes its session, a Codex agent its thread
• Graceful shutdown: released agents are closed once idle; broker and orchestrator kill all managed processes on exit
• Self-update: multiagents update upgrades the installation with whichever package manager installed it

Quick Start

# Install globally
bun install -g multiagents

# Setup (detects CLIs, configures MCP servers, starts broker)
multiagents setup

# Restart your Claude Code / Codex / Gemini sessions to load MCP tools

# Monitor
multiagents dashboard

# Later: upgrade to the latest release