cj-vana/claude-swarm

MCP server for Orchestrating Parallel Claude Code worker swarms with protocol-based behavioralGovernance. 지속적인 국가, 병렬 노동자 및 행동 제약의 실행을 가진 다시간 자율 코딩 세션을 가능하게 합니다.

설치 • 빠른 시작 • 대시보드 • 프로토콜 • 제품정보

---

특징

노동자 관현

• Persistent State - 세션 상태는 MCP 서버를 통해 컨텍스트 압축을 살아남습니다.
• Parallel Workers - tmux를 통해 여러 Claude Code 노동자를 동시에 실행
• Git Worktree Isolation - 작업자는 안전한 병렬 수정을 위해 격리된 git worktree에서 실행합니다.
• ** Worker Plan Mode** - 구현하기 전에 작업자 분석 코드베이스 및 생성 계획 (자동 승인) -Competitive Planning - 복잡한 기능은 두 개의 컴파일 구현 계획을 가져옵니다. -Confidence Monitoring - Multi-signal scoring은 struggling 근로자를 감지합니다. -Enforced Verification - 설정 가능한 검증 명령을 가진 Test-as-supervisor 패턴 -Auto-retry - 설정할 수 있는 제한을 가진 실패된 특징 -Feature Dependencies - 기능 간의 정의 실행 순서

An MCP server for orchestrating parallel Claude Code worker swarms with protocol-based behavioral governance. Enables multi-hour autonomous coding sessions with persistent state, parallel workers, and runtime enforcement of behavioral constraints.

Installation • Quick Start • Dashboard • Protocols • Tools

---

Features

Worker Orchestration

• Persistent State - Session state survives context compaction via MCP server
• Parallel Workers - Run multiple Claude Code workers simultaneously via tmux
• Git Worktree Isolation - Workers run in isolated git worktrees for safe parallel modification
• Worker Plan Mode - Workers analyze codebases and produce plans before implementing (auto-approved)
• Competitive Planning - Complex features get two competing implementation plans
• Confidence Monitoring - Multi-signal scoring detects struggling workers
• Enforced Verification - Test-as-supervisor pattern with configurable verification commands
• Auto-retry - Failed features automatically retry with configurable limits
• Feature Dependencies - Define execution order between features
• File-Based Task Locking - Atomic mutual exclusion prevents workers from conflicting
• Post-Completion Reviews - Automated code and architecture reviews with actionable findings

Long-Running Autonomy

• Ralph Loop - Fresh Claude context per iteration eliminates context rot for long sessions
• Days-Long Sessions - Supports hours/days of autonomous execution with checkpointing
• Crash Recovery - Automatic session resumption after crashes or machine restarts
• Failure Pattern Learning - Records what works/fails for future worker prompts

Protocol-Based Governance

• Behavioral Protocols - Define constraints on what workers can/cannot do
• Pre-spawn Validation - Verify protocols allow task before worker starts
• Continuous Monitoring - Track constraint violations during execution
• LLM-Generated Protocols - Workers can propose new protocols (validated against base constraints)
• Cross-instance Sync - Share protocols across MCP instances

Monitoring & Dashboard

• Real-time Web Dashboard - Live UI at http://localhost:3456 with Server-Sent Events
• Live Terminal Streaming - Watch worker output with ANSI color support
• Review Worker Visibility - Code and architecture review progress in dashboard
• Violation Tracking - Audit log of all protocol violations
• Git Checkpoints - Commit progress after each feature

Repository Setup

• Auto-Configuration - Set up CI/CD, issue templates, and documentation in parallel