SmolVM

SmolVM gives AI agents their own disposable computer. Each boots in milliseconds, runs any code or software you throw at it, persists files and state across sessions, and disappears when you’re done — built for scale in production.

Sub-second boot

VMs ready in ~413 ms.

Hardware isolation

Stronger security than containers.

Network controls

Domain allowlists for network access control.

Browser sandbox

Full browser agents can see and control.

Host mounts

Give sandboxes access to local directories.

Snapshots

Save and restore VM state instantly.

Building with agent sandboxes? Get SmolVM release notes, implementation patterns, and early-access updates.Join the SmolVM interest list

Quickstart

Install SmolVM

curl -sSL https://celesto.ai/install.sh | bash

This installs everything you need and configures your machine. See Installation for manual install and requirements.

Run your first sandbox

Python
CLI

Create quickstart.py:

quickstart.py

from smolvm import SmolVM

vm = SmolVM()
result = vm.run("echo 'Hello from the sandbox!'")
print(result.stdout.strip())
vm.stop()

Run it:

python quickstart.py

smolvm sandbox create --name my-sandbox
smolvm sandbox ssh my-sandbox
echo 'Hello from the sandbox!'
exit
smolvm sandbox stop my-sandbox

You should see:

Hello from the sandbox!

CLI usage

Create and manage sandboxes from the terminal:

smolvm sandbox create --name my-sandbox
smolvm sandbox ssh my-sandbox
smolvm sandbox list
smolvm sandbox stop my-sandbox

Run coding agents in an isolated sandbox:

smolvm claude start
smolvm codex start
smolvm pi start

Mount host directories for read-only access:

smolvm sandbox create --mount ~/Projects/my-app
smolvm sandbox create --mount ~/Projects/my-app:/code --mount ~/data:/mnt/data

Save and restore VM state with snapshots:

smolvm sandbox snapshot create my-sandbox
smolvm sandbox snapshot list
smolvm sandbox snapshot restore snap_abc123 --resume

Start a visible browser sandbox:

smolvm browser start --live
smolvm browser list
smolvm browser stop sess_a1b2c3

See the CLI reference for the full command list.

Python SDK

Create and manage sandboxes from Python:

from smolvm import SmolVM

with SmolVM() as vm:
    result = vm.run("echo 'Hello from the sandbox!'")
    print(result.stdout.strip())

Customize memory and disk for heavier workloads:

vm = SmolVM(memory=2048, disk_size=4096)

Mount host directories:

with SmolVM(mounts=["~/Projects/my-app"]) as vm:
    result = vm.run("ls /workspace")
    print(result.stdout)

Expose a port from the sandbox to your host:

with SmolVM() as vm:
    vm.run("python3 -m http.server 8000 &")
    host_port = vm.expose_local(guest_port=8000)
    print(f"http://127.0.0.1:{host_port}/")

See the API reference for the full SDK documentation.

Evaluating secure code execution, browser agents, or long-running agent environments? Tell us what you’re building and we’ll send the useful SmolVM updates — or follow up personally if you’re evaluating now.

Next steps

AI agent integration

Plug SmolVM into PydanticAI, OpenAI Agents, LangChain, and more

Port forwarding

Expose services running inside a sandbox to your host machine

Custom images

Build specialized images with your own tools pre-installed

API reference

Explore the complete SmolVM API

Get Started

Features

Guides

Architecture

Operations

SmolVM: secure microVM sandboxes for AI agents

SmolVM

Sub-second boot

Hardware isolation

Network controls

Browser sandbox

Host mounts

Snapshots

Quickstart

CLI usage

Python SDK

Next steps

AI agent integration

Port forwarding

Custom images

API reference

​SmolVM

Sub-second boot

Hardware isolation

Network controls

Browser sandbox

Host mounts

Snapshots

​Quickstart

​CLI usage

​Python SDK

​Next steps

AI agent integration

Port forwarding

Custom images

API reference

SmolVM

Quickstart

CLI usage

Python SDK

Next steps