SmolVM — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

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

by CelestoAI · Codex Skill · ★ 915

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

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

About SmolVM

SmolVM Secure, isolated computers that AI agents can use to browse, run code, and get real work done. Quick start • Examples • Features • Performance • Docs • Community Slack SmolVM gives AI agents their own disposable computer. Each microVM boots in milliseconds, runs any code or software you throw at it, persists files and state across sessions, and disappears when you're done — ready to handle thousands of sandboxes in production. <img src="https://api.iconify.design/lucide/zap.svg?color=%236e7681" width="24" height="24"

agent-runtimebrowser-agentbrowser-usecomputer-useopenclawsandbox

Quick Facts

Stars915
Forks73
LanguagePython
CategoryCodex Skill
LicenseApache-2.0
Quality Score68.8272236139831/100
Open Issues14
Last Updated2026-09-14
Created2026-02-15
Platformsbrowser, python
Est. Tokens~17k

Compatible Skills

These tools work well together with SmolVM for enhanced workflows:

  • golf — semantic(0.31)+complementary+rare_topics+same_lang+similar_pop+shared_platform (60%)
  • agentscope-runtime — semantic(0.26)+complementary+rare_topics+same_lang+similar_pop+shared_platform (58%)
  • AWorld — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (57%)

SmolVM alternative? Top 6 similar tools

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

  • clawless by open-gitagent · ⭐ 525

    ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers

  • TuriX-CUA by TurixAI · ⭐ 3.2k

    This is the official website for TuriX Computer-use-Agent

  • open-cowork by OpenCoworkAI · ⭐ 2.1k

    Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — w

  • cuga-agent by cuga-project · ⭐ 879

    CUGA is an open-source generalist agent harness for the enterprise, supporting complex task execution on web a

  • unbrowse by unbrowse-ai · ⭐ 759

    Unbrowse — api native browser Skill/CLI/MCP/SDK for any agent. Auto-discovers APIs from browser traffic, gener

  • swarmclaw by swarmclawai · ⭐ 636

    Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory,

More Codex Skill Tools

Explore other popular codex skill tools:

View all Codex Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is SmolVM?

SmolVM is Secure and persistent computer for AI agents -- built for long-running agents, build your own Grokbot, and Muse.. It is categorized as a Codex Skill with 915 GitHub stars.

What programming language is SmolVM written in?

SmolVM is primarily written in Python. It covers topics such as agent-runtime, browser-agent, browser-use.

How do I install or use SmolVM?

You can find installation instructions and usage details in the SmolVM GitHub repository at github.com/CelestoAI/SmolVM. The project has 915 stars and 73 forks, indicating an active community.

What license does SmolVM use?

SmolVM 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 SmolVM?

The top alternatives to SmolVM on Agent Skills Hub include clawless, TuriX-CUA, open-cowork. 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