> For the complete documentation index, see [llms.txt](https://docs.rawk.sh/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rawk.sh/readme.md).

# Introduction

**Welcome to Rawk** — Mineral Intelligence™ in a rock-like sealed computer.

Rawk is a physical AI assistant powered by [OpenClaw](https://openclaw.ai). It's a plug-and-play Linux device that runs locally, designed for people who want their AI assistant on their own hardware, not someone else's cloud.

***

## 📚 Documentation

* [**Quick Start**](/getting-started/quick-start.md) — Unbox to first conversation in 5 minutes
* [**Setup Guide**](/getting-started/setup-guide.md) — Network configuration and OpenClaw onboarding
* [**FAQ**](/reference/faq.md) — Common questions and troubleshooting
* [**Technical Specs**](/reference/technical-specs.md) — Hardware, software, what's inside
* [**Developer Guide**](/advanced/developer-guide.md) — SSH access, customization, hacking

***

## What is Rawk?

Rawk is a sealed, lichen-green Linux computer that:

* Runs OpenClaw — a powerful AI assistant framework
* Connects via WhatsApp, Telegram, or web chat
* Executes commands, browses the web, manages files
* Runs entirely on your local network (no cloud dependency except AI inference)
* Costs $99 and is designed to be wrecked and rebuilt

Think of it as AI in a rock. Mineral Intelligence™.

***

## Need Help?

* **Community:** [Discord](https://discord.com/invite/clawd)
* **Issues:** [GitHub Issues](https://github.com/fabryx-dao/rawk/issues)
* **Email:** <support@rawk.sh>

🪨 Built by FABRYX DAO LLC — A Mineral Arts Guild


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.rawk.sh/readme.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
