celesto command line tool.
Use this section when you want to:
- Run generated code in an isolated computer.
- Give an AI agent a workspace with files, shell commands, and optional public ports.
- Deploy an agent to Celesto’s managed infrastructure.
- Connect end-user data sources through Gatekeeper.
Quickstart
Install the SDK, create your first computer, run a command, and delete it.
Authentication
Save your API key for the CLI or pass it to the SDK from your environment.
Sandboxed computers
Create computers, use templates, run commands, manage ports, and control lifecycle.
CLI reference
Use
celesto auth and celesto computer commands from your terminal.Deployments
Package and deploy Python agents to Celesto’s managed infrastructure.
OpenAI Agents
Give an OpenAI
SandboxAgent a hosted Celesto computer or local SmolVM.Gatekeeper
Connect your users to providers like Google Drive with delegated OAuth access.
Errors
Handle authentication, validation, rate limit, server, and network errors.
Feature guides
These guides cover the parts of Celesto computers that matter most when you move from a quickstart to real agent workflows.Publish ports
Expose a server, preview app, notebook, or webhook receiver running inside a computer.
Computer sessions
Create, stop, start, resume, and delete computers for temporary or long-lived work.
Computer resources
Choose CPU, memory, disk size, and templates for heavier agent workloads.
Persistent state
Keep files, installed packages, and agent workspace state between sessions.
Choose your SDK
Pages with SDK examples use Mintlify’sView component. Pick Python or TypeScript from the selector at the top of the page, and the examples and table of contents update for that language.
How the SDK fits together
Authenticate
Create an API key in Celesto, then save it once with the CLI or set
CELESTO_API_KEY for SDK code.Your SDK client and CLI commands can call the Celesto API.
Create a computer
Start with the default
scratch computer, or use the coding-agent template when your agent needs common coding tools.You have an isolated Linux computer with an ID and a status.
Run work
Execute shell commands, inspect output, publish a supported port, or connect a terminal.
Your code or agent runs inside the sandbox instead of on your host machine.