> ## Documentation Index
> Fetch the complete documentation index at: https://docs2.openclaw.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Onboarding (macOS app)

The macOS app's first-run flow: pick where the Gateway runs, connect a
verified AI backend, grant permissions, and hand off to the agent's own
bootstrap ritual.
For CLI onboarding and a comparison of both paths, see [Onboarding Overview](/start/onboarding-overview).

<Steps>
  <Step title="Approve macOS warning">
    <Frame>
      <img src="https://mintcdn.com/clawdhub/zr61AlCx-k7XN8so/assets/macos-onboarding/01-macos-warning.jpeg?fit=max&auto=format&n=zr61AlCx-k7XN8so&q=85&s=7ade99ff85eba6a2fe743ff1f7799087" alt="" width="1132" height="818" data-path="assets/macos-onboarding/01-macos-warning.jpeg" />
    </Frame>
  </Step>

  <Step title="Approve find local networks">
    <Frame>
      <img src="https://mintcdn.com/clawdhub/zr61AlCx-k7XN8so/assets/macos-onboarding/02-local-networks.jpeg?fit=max&auto=format&n=zr61AlCx-k7XN8so&q=85&s=e9fcec535d0cdca207cff0cf2379e951" alt="" width="1132" height="818" data-path="assets/macos-onboarding/02-local-networks.jpeg" />
    </Frame>
  </Step>

  <Step title="Welcome and security notice">
    <Frame caption="Read the security notice displayed and decide accordingly">
      <img src="https://mintcdn.com/clawdhub/zr61AlCx-k7XN8so/assets/macos-onboarding/03-security-notice.png?fit=max&auto=format&n=zr61AlCx-k7XN8so&q=85&s=8866e4aaac170614a163d990091addac" alt="" width="1262" height="1570" data-path="assets/macos-onboarding/03-security-notice.png" />
    </Frame>

    Security trust model:

    * By default, OpenClaw is a personal agent: one trusted operator boundary.
    * Shared/multi-user setups need lock-down: split trust boundaries, keep tool access minimal, and follow [Security](/gateway/security).
    * Local onboarding defaults new configs to `tools.profile: "coding"` so fresh setups keep filesystem/runtime tools without the unrestricted `full` profile.
    * If hooks/webhooks or other untrusted content feeds are enabled, use a strong modern model tier and keep strict tool policy/sandboxing.
  </Step>

  <Step title="Local vs Remote">
    <Frame>
      <img src="https://mintcdn.com/clawdhub/zr61AlCx-k7XN8so/assets/macos-onboarding/04-choose-gateway.png?fit=max&auto=format&n=zr61AlCx-k7XN8so&q=85&s=7e923f389e6d774363064140691b4fbe" alt="" width="1262" height="1570" data-path="assets/macos-onboarding/04-choose-gateway.png" />
    </Frame>

    Where does the **Gateway** run?

    * **This Mac (Local only):** onboarding configures auth and writes credentials locally.
    * **Remote (over SSH/Tailnet):** onboarding does **not** configure local auth;
      credentials must already exist on the gateway host. The remote gateway token
      field stores the token the macOS app uses to connect to that Gateway;
      existing `gateway.remote.token` SecretRef values are preserved until you
      replace them.
    * **Configure later:** skip setup and leave the app unconfigured.

    <Tip>
      **Gateway auth tip:**

      * Gateway auth mode defaults to `token` even for loopback binds, so local WS clients must authenticate.
      * Setting `gateway.auth.mode: "none"` lets any local process connect; use that only on fully trusted machines.
      * Use a token for multi-machine access or non-loopback binds.
    </Tip>
  </Step>

  <Step title="CLI">
    Local setup installs the global `openclaw` CLI via npm, pnpm, or bun,
    preferring npm first. Node remains the recommended runtime for the Gateway
    itself. Existing compatible installations are reused.
  </Step>

  <Step title="Connect your AI">
    Once the Gateway is ready, onboarding looks for AI access you already have:
    a Claude Code, Codex, or Gemini CLI login, or `OPENAI_API_KEY` /
    `ANTHROPIC_API_KEY`. The best option is tested with a real completion and
    only saved after it answers; when a test fails the app automatically tries
    the next option and shows why the previous one failed. If several options
    are found you can switch between them before continuing.

    If nothing is found (or nothing works), the manual key/token picker loads the
    Gateway's active text-inference provider plugins instead of using a fixed app
    list. The selected provider supplies its starter model and config; OpenClaw
    verifies the credential with the same live test before storing its auth profile. Next
    remains locked until one backend has passed, so the first agent chat cannot
    start without working inference. The Crestodian chat stays available from this
    page (and later under Settings → Crestodian) for help in plain language.

    Configure Later skips this step.
  </Step>

  <Step title="Permissions">
    <Frame caption="Choose what permissions do you want to give OpenClaw">
      <img src="https://mintcdn.com/clawdhub/zr61AlCx-k7XN8so/assets/macos-onboarding/05-permissions.png?fit=max&auto=format&n=zr61AlCx-k7XN8so&q=85&s=6c45fa49282cf491a1425a714ec68f18" alt="" width="1262" height="1570" data-path="assets/macos-onboarding/05-permissions.png" />
    </Frame>

    Onboarding requests TCC permissions for: Automation (AppleScript), Notifications, Accessibility, Screen Recording, Microphone, Speech Recognition, Camera, and Location.
  </Step>

  <Step title="Onboarding Chat (dedicated session)">
    After setup, the app opens a separate agent onboarding chat so the agent can
    introduce itself and guide next steps without mixing that exchange into the
    normal conversation history. This follows the Crestodian setup conversation;
    it does not replace it. See [Bootstrapping](/start/bootstrapping) for what
    happens on the gateway host during the agent's first real turn.
  </Step>
</Steps>

## Related

* [Onboarding overview](/start/onboarding-overview)
* [Getting started](/start/getting-started)