> ## Documentation Index
> Fetch the complete documentation index at: https://docs-beta.actrail.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Connect Claude Code to Actrail in about five minutes.

When you're done, your agent's actions flow into the
[console](https://app.actrail.ai) automatically.

<Info>
  You'll need an Actrail account and **Python 3.11 or 3.12** — the system Python on
  macOS is 3.9 and won't work. Use a 3.11/3.12 environment (e.g. `uv venv --python 3.12`).
</Info>

<Steps>
  <Step title="Get an API key">
    In the [console](https://app.actrail.ai), open **Settings → API keys** and create
    one. It starts with `ak_` and is shown in full **once** — copy it now.
  </Step>

  <Step title="Install the SDK">
    <CodeGroup>
      ```bash pip theme={null}
      pip install actrail
      ```

      ```bash uv theme={null}
      uv pip install actrail
      ```
    </CodeGroup>
  </Step>

  <Step title="Connect Claude Code">
    Run this in your project directory:

    ```bash theme={null}
    actrail init --key ak_your_key
    ```

    You should see `✓ Actrail capturing (shadow)`.
  </Step>

  <Step title="Verify">
    ```bash theme={null}
    actrail doctor
    ```

    Confirms your config, hooks, the backend, and whether policy is being consulted.
  </Step>

  <Step title="Use Claude Code">
    Work as usual. Every action is captured as **metadata only**.
  </Step>
</Steps>

<Check>
  You're set up. Claude Code's actions now flow into Actrail — open **Trails** in
  the [console](https://app.actrail.ai) to see them.
</Check>

<Note>
  You're in **shadow mode**: Actrail watches and flags, but nothing is blocked until you
  arm a policy.
</Note>

<CardGroup cols={2}>
  <Card title="See it work" icon="arrow-right" href="/see-it-work">
    Turn a flagged risk into an enforced policy.
  </Card>

  <Card title="SDK reference" icon="book" href="/sdk">
    Every command, all config options, and how the SDK works.
  </Card>
</CardGroup>