Claude Skill

CelestoAI/SmolVM

SmolVM is an open-source AI sandbox infrastructure for secure code execution, browser automation, and AI agent deployment. Built with Python, it offers sandbox isolation and agent runtime.

Overview

Stars612
Forks48
LanguagePython
Last pushed2026-06-17
Last synced2026-06-17
View on GitHub

Repository

OwnerCelestoAI
RepositorySmolVM
Full nameCelestoAI/SmolVM
Repo ID1,158,200,188

Install this Skill

pip install smolvm

Registry

Typeopenclaw_skill
Quality score85/100
Verificationreadme_parsed
Last verified2026-06-08
Platforms
ClaudeOpenClawCodexOpenAI Agents
Capabilities
browsermemoryimagevideoterminalworkflowagent-runtimebrowser-agentbrowser-usecomputer-use
Detected files
README.mddocsexamplespyproject.tomltests
Config keys
URL

Summary

SmolVM is an open-source AI sandbox infrastructure designed for secure code execution, browser automation, and AI agent operations. Built with Python, it provides a lightweight runtime environment that enables developers to run untrusted code, control browsers programmatically, and deploy AI agents safely. With features like sandbox isolation, browser-use support, and agent runtime capabilities, SmolVM is ideal for building and testing AI-driven automation workflows.

Chinese description

开源AI沙盒基础设施,支持代码执行、浏览器使用及AI代理。

Key features

  • Sandbox isolation for secure code execution
  • Browser automation and computer-use support
  • Agent runtime for AI agent deployment
  • Lightweight and open-source infrastructure

Use cases

  • Running untrusted code in a secure sandbox
  • Automating browser tasks with AI agents
  • Building and testing AI agent workflows
  • Developing safe code execution environments

README excerpt

<div align="center"> # SmolVM #### Secure, isolated computers that AI agents can use to browse, run code, and get real work done. <img src="https://ik.imagekit.io/gradsflow/celestoai/logo/celesto%20cover%20low_vFigbRaJI.png"> [![CodeQL](https://github.com/CelestoAI/SmolVM/actions/workflows/github-code-scanning/codeql/badge.svg)](https://github.com/CelestoAI/SmolVM/actions/workflows/github-code-scanning/codeql) [![Run Tests](https://github.com/CelestoAI/SmolVM/actions/workflows/pytest.yml/badge.svg)](https://github.com/CelestoAI/SmolVM/actions/workflows/pytest.yml) [![License](https://img.shields.io/badge/License-Apache_2.0-orange.svg)](https://opensource.org/licenses/Apache-2.0) [![Python 3.10+](https://img.shields.io/badge/python-3.10+-orange.svg)](https://www.python.org/downloads/) [Quick start](#quickstart) • [Examples](#examples) • [Features](https://docs.celesto.ai/smolvm/features) • [Performance](#performance) • [Docs](https://docs.celesto.ai) • [Community Slack](https://join.slack.com/t/celestoai/shared_invite/zt-3qc7h8gno-Nb5_PElEWHDNnGqdVzC~4Q) </div> --- 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. <br> <table> <tr> <td width="50%" valign="top"> <p><img src="https://api.iconify.design/lucide/zap.svg?color=%236e7681" width="24" height="24" align="absmiddle" alt=""> <strong>Sub-second boot</strong></p> <p>Your agent has a running VM before the API call returns (~500&nbsp;ms). No waiting for provisioning or image pulls.</p> <p><a href="#performance">Read more →</a></p> </td> <td width="50%" valign="top"> <p><img src="https://api.iconif

Topics

Explore more

Data from GitHub. Synced on 2026-06-17