Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions docs/get-started/quickstart.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -241,6 +241,21 @@ Manage later
If you picked a different option, the `Model` line shows that provider's model and label instead.
For example, you might see `gpt-5.4 (OpenAI)`, `claude-sonnet-4-6 (Anthropic)`, `gemini-2.5-flash (Google Gemini)`, `llama3.1:8b (Local Ollama)`, `nvidia-routed (Model Router)`, or `<your-model> (Other OpenAI-compatible endpoint)`.

## Confirm Onboarding Finished Before You Chat

The sandbox exists only after `nemoclaw onboard` completes.
The installer auto-launches the wizard, but some paths do not run it for you: remote or Brev hosts where the installer cannot locate the freshly installed binary, or any host where a blocking preflight check fails.
In those cases the installer prints a `To finish setup, run:` block instead of starting the wizard, and the sandbox does not exist yet.

If you did not see the **NemoClaw is ready** summary above, run onboarding explicitly before you connect or chat:

```bash
nemoclaw onboard
```

To confirm the sandbox exists, run `nemoclaw <sandbox-name> status`.
Do not run `nemoclaw <sandbox-name> connect` or `openclaw tui` until onboarding has created the sandbox; otherwise the connect step fails because no sandbox exists.

## Run Your First Agent Prompt

Chat with the agent from the terminal or the browser.
Expand Down
Loading