clawhost — security grade SAFE, quality 67/100

Security audit verdict: SAFE · quality 67/100

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 antoinersx · Codex Skill · ★ 357

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

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

About clawhost

Deploy OpenClaw on your own VPS with one click. Full privacy, dedicated resources, no shared infrastructure. Website · Blog · Self-Host Guide What is ClawHost? ClawHost is an open-source, self-hostable cloud hosting platform that lets anyone deploy an AI agent runtime — OpenClaw or Hermes — on a dedicated VPS in under a minute. It handles server provisioning, DNS, SSL, firewall configuration, and agent installation automatically. Key Highlights One-Click Deploy — Pick a plan, pay, and your agent runtime is live within minutes Multi-Agent — Deploy either OpenClaw or Hermes; each ships with its own gateway service Hetzner Cloud — Reliable, high-performance VPS provisioning powered by Hetzner Dedicated VPS — Real servers with full root access, not shared containers Browser Terminal

clawclawhostdeployopenclawself-host

Quick Facts

Stars357
Forks92
LanguageTypeScript
CategoryCodex Skill
LicenseMIT
Quality Score66.7468404433636/100
Last Updated2026-08-01
Created2026-02-01
Platformscli, node
Est. Tokens~21k

Compatible Skills

These tools work well together with clawhost for enhanced workflows:

  • clawhost — semantic(1.00)+rare_topics+same_lang+similar_pop+shared_platform (75%)
  • human-mcp — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)
  • claw-orchestrator — semantic(0.18)+complementary+rare_topics+same_lang+similar_pop+shared_platform (61%)
  • ClawLink — semantic(0.15)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • openclaw-claude-code-skill — semantic(0.23)+complementary+same_lang+similar_pop+shared_platform (58%)

clawhost alternative? Top 6 similar tools

Looking for a clawhost alternative? If you're comparing clawhost 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.

  • clawhost by bfzli · ⭐ 349

    One-click cloud hosting for OpenClaw AI agents.

  • hope-agent by shiwenwen · ⭐ 1.6k

    🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手,也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autono

  • clawhost by fastclaw-ai · ⭐ 390

    openclaw hosting service

  • ClawLink by CN-Syndra · ⭐ 313

    An AI Agent Social Network — Let your AI (Claw) talk to other people's AIs directly. Autonomous agent-to-agent

  • human-mcp by mrgoonie · ⭐ 293

    Bringing Human Capabilities to AI Agents

  • DuckyClaw by tuya · ⭐ 137

    Edge-Hardware (SoC/MCU) oriented Claw🦞

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is clawhost?

clawhost is One-click cloud hosting for OpenClaw AI agents.. It is categorized as a Codex Skill with 357 GitHub stars.

What programming language is clawhost written in?

clawhost is primarily written in TypeScript. It covers topics such as claw, clawhost, deploy.

How do I install or use clawhost?

You can find installation instructions and usage details in the clawhost GitHub repository at github.com/antoinersx/clawhost. The project has 357 stars and 92 forks, indicating an active community.

What license does clawhost use?

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

What are the best alternatives to clawhost?

The top alternatives to clawhost on Agent Skills Hub include clawhost, hope-agent, clawhost. 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