# Playground
URL: /docs/playground

Run real alineo workflows end-to-end from your browser — live sandboxes, real command output, nothing simulated.



This is the playground. Every workflow here executes for real: it creates live
[OpenSandbox](https://open-sandbox.ai) containers, writes real files into them, streams real
command output back, and tears everything down when it finishes. There is no replay and no mock
data — what you see is what the SDK does.

It talks to the same [alineo sandbox API](https://github.com/DrejT/alineo/tree/main/apps/sandbox)
that powers the standalone dashboard at [sandbox.alineo.tech](https://sandbox.alineo.tech). By
default it points at the hosted endpoint; if you'd rather run against your own machine, start a
server locally and switch the endpoint below.

<PlaygroundConnect />

## Run your own server [#run-your-own-server]

The hosted endpoint is hard-capped and shared. For unlimited runs, or to poke at the internals,
run the stack locally:

<Steps>
  <Step>
    Start OpenSandbox in Docker:

    ```bash
    bunx alineo-cli init
    ```
  </Step>

  <Step>
    From a clone of the [alineo repo](https://github.com/DrejT/alineo), start the sandbox API:

    ```bash
    cd apps/sandbox && bun run start
    ```

    It listens on `http://localhost:3000`. For the agent workflow, also set `GEMINI_API_KEY` in its
    environment.
  </Step>

  <Step>
    Back here, open **Change** on the connection panel and pick **Local**.
  </Step>
</Steps>

## Workflows [#workflows]

Each one composes several SDK primitives into a single real task. Start with **Run untrusted
code** — it's the shortest.

<WorkflowGrid />

## How it maps to code [#how-it-maps-to-code]

The playground drives the HTTP API, but every step corresponds directly to a call you'd make
from the [Core SDK](/docs/core) or [Agent SDK](/docs/agent):

| Playground step     | SDK call                                            |
| ------------------- | --------------------------------------------------- |
| Create sandbox      | `client.sandbox({ image, resources })`              |
| Write / read a file | `sb.writeFile(path, content)` / `sb.readFile(path)` |
| Run a command       | `await sb.exec(cmd)` — streamed                     |
| Checkpoint          | `await sb.checkpoint()`                             |
| Fork                | `await sb.fork(tag)`                                |
| Load an agent       | `Alineo.load(spec, { adapter })`                    |
| Prompt an agent     | `for await (const ev of agent.prompt(text))`        |