Celesto

Celesto 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

Open, off, or destination-restricted outbound access.

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 Celesto release notes, implementation patterns, and early-access updates.Join the Celesto interest list

Quickstart

Install Celesto

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 celesto import Celesto

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

Run it:

python quickstart.py

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

You should see:

Hello from the sandbox!

CLI usage

Create and manage sandboxes from the terminal:

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

Run coding agents in an isolated sandbox:

celesto claude start
celesto codex start
celesto opencode start
celesto pi start

Mount host directories for read-only access:

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

Save and restore VM state with snapshots:

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

Start a visible browser sandbox:

celesto browser start --live
celesto browser list
celesto browser stop sess_a1b2c3

See the CLI reference for the full command list.

Python SDK

Create and manage sandboxes from Python:

from celesto import Celesto

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

Customize memory and disk for heavier workloads:

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

Mount host directories:

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

Expose a port from the sandbox to your host:

with Celesto() 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 Celesto updates — or follow up personally if you’re evaluating now.

Next steps

AI agent integration

Plug Celesto 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 Celesto API

Get Started

Features

Guides

Architecture

Operations

Celesto: secure microVM sandboxes for AI agents

Celesto

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

​Celesto

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

Celesto

Quickstart

CLI usage

Python SDK

Next steps