clawdhome — security grade SAFE, quality 74/100

Security audit verdict: SAFE · quality 74/100

Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by ThinkInAIXYZ · Codex Skill · ★ 314

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

🔒 Is clawdhome safe to install? View the security audit →

About clawdhome

ClawdHome English | 中文 Native macOS control plane for securely running and managing multiple isolated OpenClaw gateway instances on a single Mac. ClawdHome is built for people who want one machine to host multiple OpenClaw "Shrimps" without mixing identities, data, permissions, or operational risk. It combines a SwiftUI admin app, a privileged XPC helper daemon, and macOS multi-user isolation into a single workflow for setup, monitoring, cloning, maintenance, and recovery. Website: clawdhome.app Downloads: GitHub Releases Changelog: English | 中文 Community Groups Feishu Group WeChat Group

isolationlocal-firstmacosmulti-instanceopenclawprivate-ai-assistantsecurityzero-trust

Quick Facts

Stars314
Forks49
LanguageSwift
CategoryCodex Skill
LicenseApache-2.0
Quality Score73.8958114083339/100
Open Issues1
Last Updated2026-07-24
Created2026-02-20
Est. Tokens~17k

Compatible Skills

These tools work well together with clawdhome for enhanced workflows:

clawdhome alternative? Top 6 similar tools

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

  • CoWork-OS by CoWork-OS · ⭐ 457

    Local-first personal agentic OS and everything app for coding, knowledge work, web design, automations, and ar

  • memorix by AVIDS2 · ⭐ 797

    Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Wi

  • room by quoroom-ai · ⭐ 796

    Open-source earning-focused swarm intelligence engine. Self-governing AI collectives (queen, workers, quorum v

  • pasteguard by sgasser · ⭐ 738

    AI gets the context. Not your private data. Local-first privacy proxy for browser chat, AI APIs, and coding ag

  • vestige by samvallad33 · ⭐ 628

    Cognitive Deterministic Memory Security OS for Agentic AI. Deterministic root-cause retrieval that reaches bac

  • project-raven by Laxcorp-Research · ⭐ 413

    Open-source AI meeting copilot - real-time transcription, echo cancellation, and AI assistance. Captures syste

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is clawdhome?

clawdhome is ClawdHome securely isolates and manages multiple OpenClaw gateway instances on one Mac.. It is categorized as a Codex Skill with 314 GitHub stars.

What programming language is clawdhome written in?

clawdhome is primarily written in Swift. It covers topics such as isolation, local-first, macos.

How do I install or use clawdhome?

You can find installation instructions and usage details in the clawdhome GitHub repository at github.com/ThinkInAIXYZ/clawdhome. The project has 314 stars and 49 forks, indicating an active community.

What license does clawdhome use?

clawdhome is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to clawdhome?

The top alternatives to clawdhome on Agent Skills Hub include CoWork-OS, memorix, room. 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 Codex Skill tools