———   secure self-hosted sandboxes for your ai agents   ———

  _{WHY MICROSANDBOX?}

Building AI agents that generate and execute code? — You'll need secure sandboxes^✨!

To run your ai-generated code, you could try a few things:

• Run directly on machine? — Risky for the machine [→]
• Run in docker containers? — Limited isolation for untrusted code [→]
• Run in traditional VMs? — Minutes to start up, heavy resource usage
• Run in cloud sandboxes? — Less control over your infra and lose rapid dev cycles

microsandbox gives you the best of all the worlds, all on your own infrastructure:

•   True VM-Level Security Isolation with Fast Startup Times
•   Self-Hosted with Full Control
•   Fast Local Development Iteration Cycles
•   Seamless Transition from Local to Production
•   Data Sovereignty and Privacy
•   Compatible with Standard Container Images
•   Wide SDK Ecosystem
•   Integration with Any MCP Enabled AI

• • •

  _{QUICK START}

Get started with few easy steps:

demo.mp4

^{[ASCIINEMA →]}

1    Get API Key

• Get your API key by [SELF HOSTING →]

• Set the MSB_API_KEY environment variable to the key.

  export MSB_API_KEY=msb_***

2    Install SDK

Python

pip install microsandbox

JavaScript

npm install microsandbox

Rust

cargo add microsandbox

Note

There are SDKs for other languages as well! Join us in expanding support for your favorite language.

3    Execute Code in Sandbox

microsandbox offers a growing list of sandbox environment types optimized for different execution requirements. Choose the appropriate sandbox (e.g., PythonSandbox or NodeSandbox) to run your code in a secure tailored environment.

Python

import asyncio
from microsandbox import PythonSandbox

async def main():
    async with PythonSandbox.create(name="test") as sb:
        exec = await sb.run("name = 'Python'")
        exec = await sb.run("print(f'Hello {name}!')")

    print(await exec.output()) # prints Hello Python!

asyncio.run(main())

JavaScript

import { NodeSandbox } from "microsandbox";

async function main() {
  const sb = await NodeSandbox.create({ name: "test" });

  try {
    let exec = await sb.run("var name = 'JavaScript'");
    exec = await sb.run("console.log(`Hello ${name}!`)");

    console.log(await exec.output()); // prints Hello JavaScript!
  } finally {
    await sb.stop();
  }
}

main().catch(console.error);

Rust

use microsandbox::{SandboxOptions, PythonSandbox};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let mut sb = PythonSandbox::create(SandboxOptions::builder().name("test").build()).await?;

    let exec = sb.run(r#"name = "Python""#).await?;
    let exec = sb.run(r#"print(f"Hello {name}!")"#).await?;

    println!("{}", exec.output().await?); // prints Hello Python!

    sb.stop().await?;

    Ok(())
}

Note

When you run the code for the first time, it will take a while to download the sandbox image unless you already have it downloaded. After that, it will run much faster.

For more information on how to use the SDK, check out the SDK README.

• • •

  _{USE CASES}

Coding & Dev Environments

Let your AI agents build real apps with professional dev tools. When users ask their AI to create a web app, fix a bug, or build a prototype, it can handle everything from Git operations to dependency management to testing in a protected environment.

Your AI can create complete development environments in milliseconds and run programs with full system access. The fast startup means developers get instant feedback and can iterate quickly. This makes it perfect for AI pair programming, coding education platforms, and automated code generation where quick results matter.

Data Analysis

Transform raw numbers into meaningful insights with AI that works for you. Your AI can process spreadsheets, create charts, and generate reports safely. Whether it's analyzing customer feedback, sales trends, or research data, everything happens in a protected environment that respects data privacy.

Microsandbox lets your AI work with powerful libraries like NumPy, Pandas, and TensorFlow while creating visualizations that bring insights to life. Perfect for financial analysis tools, privacy-focused data processing, medical research, and any situation where you need serious computing power with appropriate safeguards.

Web Browsing Agent

Build AI assistants that can browse the web for your users. Need to compare prices across stores, gather info from multiple news sites, or automate form submissions? Your AI can handle it all while staying in a contained environment.

With microsandbox, your AI can navigate websites, extract data, fill out forms, and handle logins. It can visit any site and deliver only the useful information back to your application. This makes it ideal for price comparison tools, research assistants, content aggregators, automated testing, and web automation workflows that would otherwise require complex setup.

Instant App Hosting

Share working apps and demos in seconds without deployment headaches. When your AI creates a useful tool, calculator, visualization, or prototype, users can immediately access it through a simple link.

Zero-setup deployment means your AI-generated code can be immediately useful without complex configuration. Each app runs in its own protected space with appropriate resource limits, and everything cleans up automatically when no longer needed. Perfect for educational platforms hosting student projects, AI assistants creating live demos, and users needing immediate value.

• • •

  _{PROJECTS  ^{B E T A}}

Beyond the SDK, microsandbox supports project-based development with familiar package-manager workflows. Think of it like npm or cargo, but for sandboxes!

Create a Sandboxfile, define your environments, and manage your sandboxes with simple commands.

Create a Sandbox Project

msb init

This creates a Sandboxfile in the current directory, which serves as the configuration manifest for your sandbox environments.

Add a Sandbox to the Project

msb add app \
    --image python \
    --cpus 1 \
    --memory 1024 \
    --start 'python -c "print(\"hello\")"'

The command above registers a new sandbox named app in your Sandboxfile, configured to use the python image.

You should now have a Sandboxfile containing a sandbox named app:

cat Sandboxfile

# Sandbox configurations
sandboxes:
  app:
    image: python
    memory: 1024
    cpus: 1
    scripts:
      start: python -c "print(\"hello\")"

Tip

Run msb <subcommand> --help to see all the options available for a subcommand.

For example, msb add --help.

Running a Sandbox

Run a Sandbox Defined in Your Project

msb run --sandbox app

or

msr app

This executes the default start script of your sandbox. For more control, you can directly specify which script to run — msr app~start.

When running project sandboxes, all file changes and installations made inside the sandbox are automatically persisted to the ./menv directory. This means you can stop and restart your sandbox any time without losing your work. Your development environment will be exactly as you left it.

Run an Temporary Sandbox

For experimentation or one-off tasks, temporary sandboxes provide a clean environment that leaves no trace:

msb exe --image python

or

msx python

Temporary sandboxes are perfect for isolating programs you get from the internet. Once you exit the sandbox, all changes are completely discarded.

Installing Sandboxes

The msb install command sets up a sandbox as a system-wide executable. It installs a slim launcher program that allows you to start your sandbox from anywhere in your system with a simple command.

msb install --image alpine

or

msi alpine

After installation, you can start your sandbox by simply typing its name in any terminal:

alpine

This makes frequently used sandboxes incredibly convenient to access — no need to navigate to specific directories or remember complex commands. Just type the sandbox name and it launches immediately with all your configured settings.

Tip

You can give your sandbox a descriptive, easy-to-remember name during installation:

msi alpine:20250108 slim-linux

This allows you to create multiple instances of the same sandbox image with different names and configurations. For example:

• msi python python-data-science - A Python environment for data analysis
• msi python python-web - A Python environment for web development

Installed sandboxes maintain their state between sessions, so you can pick up exactly where you left off each time you launch them.

• • •

  _DEVELOPMENT

Interested in contributing to microsandbox? Check out our Development Guide for instructions on setting up your development environment, building the project, running tests, and creating releases.

For contribution guidelines, please refer to CONTRIBUTING.md.

• • •

  _LICENSE

This project is licensed under the Apache License 2.0.