Deploy agents on Celesto

Celesto deployments run agent code on managed infrastructure. The deployment API is being updated to match the new resource-style SDK used by Computer.

The current public SDK release focuses on sandboxed computers. Use sandboxed computers to create a cloud workspace, run commands, publish preview ports, and clean up resources while deployment docs are refreshed.

What to use today

For agent development and preview workflows, create a coding-agent computer and run your app inside it:

celesto computer create --template coding-agent
celesto computer run einstein "python3 --version"
celesto computer run einstein "python3 -m http.server 8000 &"
celesto computer port publish einstein --port 8000

For Python code, use the Computer resource:

from celesto import Computer


computer = Computer(template_id="coding-agent")
print(computer.name)

result = computer.run("python3 --version")
print(result["stdout"])

computer.delete()

For TypeScript code, use the Computer resource:

import { Computer } from "@celestoai/sdk";

const computer = await Computer.create({ templateId: "coding-agent" });
console.log(computer.name);

const result = await computer.run("python3 --version");
console.log(result.stdout);

await computer.delete();

Next steps

Sandboxed computers

Create computers, run commands, publish ports, and manage lifecycle.

Publish a GitHub app

Use a Celesto computer to build and preview an app from a repository.

Last modified on July 4, 2026

Pi coding agent Sandbox an OpenAI agent with Celesto or SmolVM

⌘I

Start Here

Features

Guides

Agents and Integrations

Deploy agents on Celesto

What to use today

Next steps

Sandboxed computers

Publish a GitHub app

​What to use today

​Next steps

Sandboxed computers

Publish a GitHub app

What to use today

Next steps