Claude Code, Codex CLI 및 Gemini CLI를 위한 다중 시약 관현 플랫폼. AI 에이전트를 사용하여 서로를 발견하고 실시간 통신, 좌표 파일 편집 및 공유 codebases에 팀으로 작동합니다.

MCP (모델 콘텍스트 프로토콜)에 내장.

그것은 무엇을

-Peer discovery: 에이전트는 list_peers를 통해 서로를 찾습니다. -Real-time messaging: Orchestrator-launched Claude와 Codex Agent는 팀메이트 메시지 중반 (stream-json stdin / turn/steer); 각 에이전트는 다음 도구 결과에 읽지 않은 메시지를 얻고, 메시지는 모델에 도달한 후 한 번만 표시됩니다. -Role 할당: assign_role, rename_peer] 런타임 -File coordination: 독점적인 자물쇠 + 소유권 지역은 충돌을 방지합니다.

• **Task 라이프사이클 **: idle → working → done_pending_review → addressing_feedback → approved → released
• 리뷰 루프: signal_done → submit_feedback → fix → re-review → approve -Shared Knowledge: 건축 결정, 발견된 패턴 및 프로젝트 컨텍스트에 대한 지속적 키가치 저장소 — 에이전트를 통해 맥락을 방지
• Persistent session: 에이전트 재시작, 전체 메시지 기록

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