# microsandbox **Repository Path**: njxisang/microsandbox ## Basic Information - **Project Name**: microsandbox - **Description**: No description available - **Primary Language**: Unknown - **License**: Apache-2.0 - **Default Branch**: main - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2026-04-16 - **Last Updated**: 2026-04-16 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README
microsandbox-banner-xl-dark
microsandbox-banner-xl

——   every agent deserves its own computer   ——


GitHub release Discord Apache 2.0 License

**Microsandbox** spins up **lightweight VMs in milliseconds** from our SDKs. Runs locally on your machine. No server to set up. No lingering daemon. It is all embedded and rootless! ## - **Hardware Isolation**: Hardware-level isolation with microVM technology. - **Instant Startup**: Average boot times under 100 milliseconds. - **Embeddable**: Spawn VMs right within your code. No setup server. No long-running daemon. - **Secrets That Can't Leak**: Unexploitable secret keys that never enter the VM. - **OCI Compatible**: Runs standard container images from Docker Hub, GHCR, or any OCI registry. - **Long-Running**: Sandboxes can run in detached mode. Great for long-lived sessions. - **Agent-Ready**: Your agents can create their own sandboxes with our [Agent Skills](https://github.com/superradcompany/skills) and [MCP server](https://github.com/superradcompany/microsandbox-mcp).
## rocket-darkrocket  Getting Started ####   Install the SDK > ```sh > cargo add microsandbox # 🦀 Rust > ``` > ```sh > uv add microsandbox # 🐍 Python > ``` > ```sh > npm i microsandbox # 🟦 TypeScript > ``` ####   Install the CLI **(Optional)** > ```sh > curl -fsSL https://install.microsandbox.dev | sh > ``` ## > **Requirements**: Linux with KVM enabled, or macOS with Apple Silicon.
> **Warning**: Microsandbox is still **beta software**. Expect breaking changes, missing features, and rough edges.
## sdk-darksdk  SDK The SDK lets you create and control sandboxes directly from your application. `Sandbox::builder("...").create()` boots a microVM as a child process. No infrastructure required. ####   Run Code in a Sandbox > ```rs > use microsandbox::Sandbox; > > #[tokio::main] > async fn main() -> Result<(), Box> { > let sandbox = Sandbox::builder("my-sandbox") > .image("python") > .cpus(1) > .memory(512) > .create() > .await?; > > let output = sandbox > .exec("python", ["-c", "print('Hello from a microVM!')"]) > .await?; > println!("{}", output.stdout()?); > > sandbox.stop_and_wait().await?; > Ok(()) > } > ``` > >
>  Python Example → > > ```python > import asyncio > from microsandbox import Sandbox > > async def main(): > sandbox = await Sandbox.create( > "my-sandbox", > image="python", > cpus=1, > memory=512, > ) > > output = await sandbox.exec("python", ["-c", "print('Hello from a microVM!')"]) > print(output.stdout_text) > > await sandbox.stop_and_wait() > > asyncio.run(main()) > ``` > >
> >
>  TypeScript Example → > > ```typescript > import { Sandbox } from "microsandbox"; > > const sandbox = await Sandbox.create({ > name: "my-sandbox", > image: "python", > cpus: 1, > memoryMib: 512, > }); > > const output = await sandbox.exec("python", ["-c", "print('Hello from a microVM!')"]); > console.log(output.stdout()); > > await sandbox.stopAndWait(); > ``` > >
> The first call to `create()` pulls the image if it isn't cached locally, so it may take longer depending on your connection. Subsequent runs reuse the cache.
SDK Docs
## cli-darkcli  CLI The `msb` CLI provides a complete interface for managing sandboxes, images, and volumes. ####   Run a Command > ```sh > msb run python -- python3 -c "print('Hello from a microVM!')" > ``` ####   Named Sandboxes > ```sh > # Create and start a named sandbox > msb create --name my-app python > ``` > > ```sh > # Execute commands > msb exec my-app -- python -c "import this" > msb exec my-app -- curl https://example.com > ``` > > ```sh > # Lifecycle > msb stop my-app > msb start my-app > msb rm my-app > ``` ####   Image Management > ```sh > msb pull python # Pull an image > msb image ls # List cached images > msb image rm python # Remove an image > ``` ####   Install & Uninstall Sandboxes > ```sh > msb install ubuntu # Install ubuntu sandbox as 'ubuntu' command > ubuntu # Opens Ubuntu in a microVM > ``` > ```sh > msb install --name nodebox node # Custom command name > msb install --tmp alpine # Ephemeral: fresh sandbox every run > msb install --list # List installed commands > msb uninstall nodebox # Remove an installed command > ``` ####   Status & Inspection > ```sh > msb ls # List all sandboxes > msb ps my-app # Show sandbox status > msb inspect my-app # Detailed sandbox info > msb metrics my-app # Live CPU/memory/network stats > ``` > [!TIP] > > Run `msb --tree` to see all available commands and their options.
CLI Docs
## agents-darkagents  AI Agents Give your AI agents the ability to create and manage their own sandboxes. ####   Agent Skills > Teach any AI coding agent how to use microsandbox by installing the [Agent Skills](https://github.com/superradcompany/skills). Works with Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, and more. > > ```sh > npx skills add superradcompany/skills > ``` ####   MCP Server > Connect any MCP-compatible agent to microsandbox with the [MCP server](https://github.com/superradcompany/microsandbox-mcp). Provides structured tool calls for sandbox lifecycle, command execution, filesystem access, volumes, and monitoring. > > ```sh > # Claude Code > claude mcp add --transport stdio microsandbox -- npx -y microsandbox-mcp > ```
## docs-darkdocs  Documentation For guides, API references, and examples, visit the [microsandbox documentation](https://docs.microsandbox.dev).
## contributing-darkcontributing  Contributing Interested in contributing to `microsandbox`? Check out our [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines and [DEVELOPMENT.md](./DEVELOPMENT.md) for build, test, and release instructions.
## license-darklicense  License This project is licensed under the [Apache License 2.0](./LICENSE).
## acknowledgements-darkacknowledgements  Acknowledgements Special thanks to all our contributors, testers, and community members who help make microsandbox better every day! We'd like to thank the following projects and communities that made `microsandbox` possible: [libkrun](https://github.com/containers/libkrun) and [smoltcp](https://github.com/smoltcp-rs/smoltcp)