claude-swarm — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by cj-vana · MCP Server · ★ 115

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is claude-swarm safe to install? View the security audit →

About claude-swarm

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 Lockin

ai-agentsclaudemcporchestrationtmuxtypescript

Quick Facts

Stars115
Forks10
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score73.9585263715649/100
Last Updated2026-02-11
Created2025-12-24
Platformsclaude-code, mcp, node
Est. Tokens~959k

claude-swarm alternative? Top 6 similar tools

Looking for a claude-swarm alternative? If you're comparing claude-swarm with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • amux by mixpeek · ⭐ 492

    Open-source control plane for AI coding agents. Run an AI engineering team: parallel Claude Code, Codex, and G

  • sandboxed.sh by Th0rgal · ⭐ 513

    Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • claude-emporium by Vvkmnn · ⭐ 82

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • OmoiOS by kivo360 · ⭐ 78

    Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat

  • intellegix-code-agent-toolkit by intellegix · ⭐ 57

    Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Cl

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is claude-swarm?

claude-swarm is MCP server for orchestrating parallel Claude Code worker swarms with protocol-based behavioral governance, persistent state, and real-time monitoring dashboard. It is categorized as a MCP Server with 115 GitHub stars.

What programming language is claude-swarm written in?

claude-swarm is primarily written in TypeScript. It covers topics such as ai-agents, claude, mcp.

How do I install or use claude-swarm?

You can find installation instructions and usage details in the claude-swarm GitHub repository at github.com/cj-vana/claude-swarm. The project has 115 stars and 10 forks, indicating an active community.

What license does claude-swarm use?

claude-swarm is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to claude-swarm?

The top alternatives to claude-swarm on Agent Skills Hub include amux, sandboxed.sh, maestro. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools