index.mdx

title	Introduction
description	Sandboxes for every agent. Embeddable, stateful, snapshots, and hardware isolation.
icon	house

BoxLite lets you spin up lightweight Linux VMs and run OCI containers inside them — in milliseconds, from your own code, with no daemon and no root. Unlike ephemeral sandboxes that destroy state after each execution, BoxLite Boxes are stateful workspaces — install packages, create files, build up environment state, then come back later and pick up where you left off.

Runs on macOS (Apple Silicon), Linux (KVM), and Windows (WSL2).

Why BoxLite?

A library you import — no daemon, no cloud account, no root. Local first, cloud when you're ready. Boxes retain packages, files, and environment across stop/restart. No rebuilding on every interaction. Fork, checkpoint, and restore full sandbox state. Branch execution like `git branch` for environments. Each sandbox is a real micro-VM with its own Linux kernel. VM-level security with container-level ergonomics.

Quick start

```python # pip install boxlite import asyncio import boxlite

async def main():
    async with boxlite.SimpleBox(image="alpine:latest") as box:
        result = await box.exec("echo", "Hello from BoxLite!")
        print(result.stdout)

asyncio.run(main())
```

```typescript // npm install @boxlite-ai/boxlite import { SimpleBox } from '@boxlite-ai/boxlite';

const box = new SimpleBox({ image: 'alpine:latest' });
try {
  const result = await box.exec('echo', 'Hello from BoxLite!');
  console.log(result.stdout);
} finally {
  await box.stop();
}
```

BoxRun — sandbox management

BoxRun is the management layer for BoxLite sandboxes. Create, list, stop, and delete boxes through a CLI, REST API, Python SDK, or web dashboard — all in a single binary.

curl -fsSL https://boxlite.ai/boxrun/install | sh
boxrun shell ubuntu

BoxLite creates and runs micro-VMs. BoxRun manages them — tracking state, persisting data, and exposing operations over HTTP and CLI.

SDKs and platforms

SDK	Install
Python	pip install boxlite
Node.js	npm install @boxlite-ai/boxlite
Rust	Git dependency
C	Link libboxlite

Platform	Architecture	Requirements
macOS	Apple Silicon	macOS 12+
Linux	x86_64 / ARM64	KVM enabled
Windows	WSL2	KVM support

Next steps

Execute code, connect LLMs, transfer files, and automate browsers — step-by-step. AI agent integration, security configuration, and production patterns. Full API reference for the Python, Node.js, Rust, and C SDKs. How BoxLite works under the hood — microVMs, the jailer, networking, and storage. Ask questions, share projects, and chat with the BoxLite team on Discord.