# Quickstart

Your first cloud sandbox and your first pool. Start a desktop in the cloud, verify a file hash, then apply a pool and claim from it.

> Agent discovery: use [the Cua documentation index](https://cua.ai/docs/llms.txt) to find related pages and their Markdown URLs.





Start a Linux desktop in the cloud, hash a file inside it and check the hash
on your machine, then create a pool of your own and claim a sandbox from it.

## Prerequisites

- The `cua` CLI, signed in (`cua auth login --remote` without a browser):

```bash test="cli-shape" id="cua-auth-login"
curl -fsSL https://cua.ai/install.sh | sh
cua auth login
```

- For scripts: Python `>=3.11,<3.14` with [`uv`](https://docs.astral.sh/uv/),
  or Node.js 20. They read `CUA_CLIENT_ID` and `CUA_CLIENT_SECRET` from
  `cua auth keys create NAME` ([credentials](</docs/cua-sdk/guides/cloud#credentials>)).

Usage is billed while a sandbox runs; releasing it ends the charge.

## Run a cloud sandbox


  

**CLI**



```bash test="cli-shape" id="cua-sb-create"
cua sb create linux --on cloud --name first-fleet
printf 'pear\napple\npear\nbanana\n' > fruit.txt
cua sb cp fruit.txt first-fleet:/tmp/fruit.txt
cua sb exec first-fleet sha256sum /tmp/fruit.txt
shasum -a 256 fruit.txt
cua sb screenshot first-fleet -o first-fleet.png
```

  


  

**Python**



The script pins `cua-sandbox==0.9.0` and runs `Image.linux()` with
`local=False` (`CUA_FLEET_IMAGE` overrides the image).

```bash skip="third-party-cli"
curl -fsSLO https://cua.ai/docs-assets/scripts/first-cloud-fleet/first_cloud_fleet.py
uv run first_cloud_fleet.py
```

  


  

**TypeScript**



```bash skip="host-install"
npm install @trycua/cua@0.4.1 && npm install --save-dev tsx
curl -fsSLo first-cloud-fleet.ts \
  https://cua.ai/docs-assets/scripts/first-cloud-fleet/first-cloud-fleet.ts.txt
npx tsx first-cloud-fleet.ts
```

  




Both hashes are
`d9359aad71bda9a11a4fd2e8d72044d6f0f77519c6b6fb30d251806febcfb4d0`. Your
machine computed the second one, so the check does not rely on the guest. The
canonical image keeps warm capacity, so this takes seconds; another image's
first start can take a few minutes.

## Create a pool and claim from it

The sandbox above ran on a pool the SDK manages. Apply a pool you own, with
one warm replica, claim a sandbox from it, and delete it:

```python test="docs,fleet" id="first-pool" prelude="fakefleet,pool-name"
import os

from cua_sandbox import CloudOptions, Image, Pool, PoolOptions, Sandbox, SandboxSpec

pool = await Pool.apply(
    os.environ["CUA_POOL_NAME"],             # globally unique, lowercase
    SandboxSpec(image=Image.linux(), services={"env": 3211}),
    PoolOptions(replicas=1),
)
async with Sandbox.ephemeral(cloud=CloudOptions(pool=pool.name)) as sb:
    print((await sb.shell.run("uname -a")).stdout.strip())
await pool.delete()
```

## Result

```text output
Claimed ...
Verified SHA-256: d9359aad71bda9a11a4fd2e8d72044d6f0f77519c6b6fb30d251806febcfb4d0
Screenshot: .../first-cloud-fleet.png
Claim released
```

## Clean up

```bash test="cli-shape" id="cua-sb-rm-first-fleet"
cua sb rm -f first-fleet
```

The scripts release their sandbox even when a step fails. A killed process's
sandbox expires after its TTL (15 minutes); idle managed pools are deleted
after 30 minutes, or now with `cua fleet pools gc`
([Troubleshoot](</docs/fleets/guides/troubleshoot#clean-up-leftovers>)).

## Next

- [Create capacity and claim from it](</docs/fleets/guides/capacity-and-claims>)
- [Manage pools with Terraform](</docs/fleets/guides/terraform>)
- [Keep sandboxes warm](</docs/fleets/guides/warm-pools>)