Skip to main content
A Celesto computer is a sandboxed Linux machine for an AI agent. It gives the agent a real workspace with files, a shell, process isolation, optional browser capabilities, and APIs for lifecycle control. Think of it as the agent’s workbench. Your application asks Celesto to create a computer, sends commands or file operations to it, and deletes it when the work is finished.

​
What an agent can do

Run shell commands

Execute scripts, package managers, tests, build tools, and diagnostics.

Read and write files

Keep source code, generated files, logs, and artifacts inside the sandbox.

Expose ports

Publish preview apps, APIs, notebooks, dashboards, and webhooks.

Pause and resume

Stop a computer when work pauses, then start the same computer later.

​
The lifecycle

1

Create

Choose a template such as scratch or coding-agent, then create a computer with the SDK or CLI.
2

Run work

Send commands, write files, publish ports, or connect an agent framework.
3

Stop or delete

Stop the computer when you want to resume later. Delete it when the saved state is no longer needed.

​
Hosted or local

Use the hosted Celesto Platform when you want managed infrastructure, APIs, and orchestration. Use local SmolVM when you want open-source sandboxes on your own machine.

Hosted platform

Managed computers from Python, TypeScript, JavaScript, or the Celesto CLI.

Local SmolVM

Open-source microVM sandboxes for local development and private runs.
Last modified on July 1, 2026