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

# GlassKit Docs

> Open-source toolkit for building smart-glasses AI apps.

GlassKit is an open-source toolkit for building smart-glasses AI apps. Your coding agent can use the skill, docs, and runnable examples to build apps that understand what wearers see and hear, then guide them in real time.

GlassKit currently starts with Rokid Glasses. The long-term goal is a developer platform for building, hosting, and shipping smart-glasses apps across more devices.

<CardGroup cols={3}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Choose the fastest path: install the agent skill, copy the Rokid starter, or copy a complete example.
  </Card>

  <Card title="GitHub" icon="github" iconType="brands" href="https://github.com/RealComputer/GlassKit">
    Browse source, examples, issues, and demo videos in the repository.
  </Card>

  <Card title="Discord" icon="discord" iconType="brands" href="https://discord.gg/v5ayGKhPNP">
    Join the Discord for project discussion and help.
  </Card>
</CardGroup>

## Demos

The GitHub README includes demo videos. These demos cover the core GlassKit building blocks for Rokid Glasses: camera and microphone capture, WebRTC streaming, a monochrome on-lens display, touchpad and offline voice controls, OpenAI Realtime, Overshoot, and object detection.

<CardGroup cols={2}>
  <Card title="Drink-making coach" icon="flask" href="https://github.com/RealComputer/GlassKit/tree/main/examples/rokid-overshoot-openai-realtime">
    Proactive drink-making coach that watches ingredients, picks a recipe, and guides each step.
  </Card>

  <Card title="Sushi speedrun timer" icon="stopwatch" href="https://github.com/RealComputer/GlassKit/tree/main/examples/rokid-rfdetr">
    Physical-task timer that uses RF-DETR to detect configured objects and advance HUD splits after confirmation.
  </Card>

  <Card title="IKEA assembly assistant" icon="box" href="https://github.com/RealComputer/GlassKit/tree/main/examples/rokid-openai-realtime">
    Voice-first assembly assistant that streams microphone and camera input to OpenAI Realtime.
  </Card>

  <Card title="Live scene reader" icon="eye" href="https://github.com/RealComputer/GlassKit/tree/main/examples/rokid-overshoot">
    Scene reader that sends live camera context to Overshoot and displays inference text on the HUD.
  </Card>

  <Card title="Rokid feature demo" icon="gears" href="https://github.com/RealComputer/GlassKit/tree/main/examples/rokid-feature-demo">
    Device-feature reference app for touchpad navigation, offline voice commands, camera, microphone, audio, and reusable screen controllers.
  </Card>

  <Card title="Searchable life recording" icon="magnifying-glass" href="https://dev.to/tash-2s/i-recorded-13-hours-of-my-day-with-smart-glasses-for-ai-heres-what-i-built-and-what-i-learned-5f1c">
    Full-day smart-glasses recording demo that makes long first-person recordings browsable and searchable.
  </Card>
</CardGroup>

## How apps work

A typical GlassKit app has four pieces:

1. A Rokid Glasses Android app captures camera and microphone input, handles touchpad gestures, and renders a HUD.
2. WebRTC carries live media between the glasses, your backend, and AI services.
3. A backend coordinates session setup, workflow state, model calls, tool calls, and app-specific decisions.
4. The wearer gets real-time feedback through display and audio.

The exact architecture varies by example. Some pieces can run offline, including local voice commands, device controls, and local vision or privacy processing.

## Requirements

Many examples need:

* [Rokid Glasses and a development cable](/guides/how-to-get-rokid-glasses)
* Android Studio or `adb`
* `uv` for Python backends or `node` for TypeScript backends
* API keys depending on the example, such as `OPENAI_API_KEY`

Each example README has the exact setup steps and environment variables.