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

# Quickstart

> Get Spaceduck running and send your first message in under 5 minutes.

After completing this guide, you'll have a running Spaceduck gateway with a chat model connected and ready to use.

## Install

<Tabs>
  <Tab title="macOS / Linux">
    ```bash theme={null}
    curl -fsSL https://spaceduck.ai/install.sh | bash
    ```
  </Tab>

  <Tab title="Windows">
    ```powershell theme={null}
    irm https://spaceduck.ai/install.ps1 | iex
    ```
  </Tab>
</Tabs>

<Info>
  Prefer to install manually? See the [From Source](/install/from-source) guide.
</Info>

## Configure your chat model

Open [http://localhost:3000](http://localhost:3000) and click the **Settings** icon in the sidebar, then go to **Chat**.

1. Select a **Provider** from the dropdown (e.g., llama.cpp, Bedrock, Gemini)
2. Enter the **Base URL** if using a local provider
3. Set your **API key** if using a cloud provider
4. Choose a **Model**

Changes to provider, model, and system prompt hot-apply immediately — no restart needed.

<Tip>
  If you're unsure which provider to start with, see the [Model Providers overview](/providers/overview) for a comparison.
</Tip>

## Send your first message

Go back to the chat view and type something. You should see a streaming response from your configured model.

<Check>
  If you see a response, Spaceduck is working. Your conversations are now being stored in SQLite with automatic fact extraction.
</Check>

## Optional: enable semantic recall

By default, Spaceduck uses keyword search (FTS5) for cross-conversation memory. To enable vector-based semantic recall:

1. Go to **Settings > Memory**
2. Toggle **Semantic recall** on
3. Select an embedding provider and model
4. Click **Test** to verify the connection

<Info>
  Semantic recall requires a separate embedding model. You can use the same provider as your chat model, or run a dedicated embedding server. See [llama.cpp embeddings](/providers/llamacpp#embeddings) for a local setup.
</Info>

## Optional: install tools

<AccordionGroup>
  <Accordion title="Browser automation (Playwright)">
    ```bash theme={null}
    bunx playwright install chromium
    ```

    Enables web browsing and page interaction via the `browser` tool.
  </Accordion>

  <Accordion title="Document scanning (Marker)">
    ```bash theme={null}
    pip install marker-pdf   # requires Python 3.10+, PyTorch
    ```

    When `marker_single` is on your PATH, the `marker_scan` tool is automatically registered. Upload PDFs via the paperclip button in the chat UI.
  </Accordion>

  <Accordion title="Voice dictation">
    **Web UI:** Click the mic button in the chat input. Hold to record, release to transcribe via [Whisper](https://github.com/openai/whisper) or AWS Transcribe.

    ```bash theme={null}
    pip install openai-whisper   # Option A: local Whisper (Python 3.9+, ffmpeg)
    ```

    When `whisper` is on your PATH, the mic button appears in the chat UI.

    Alternatively, configure **AWS Transcribe** credentials in your environment for cloud-based STT.

    **Desktop app (macOS):** Press the **Fn/Globe key** from any application to activate a system-wide dictation pill with real-time waveform. See [Desktop App](/platforms/desktop) for setup.
  </Accordion>
</AccordionGroup>

## Choose your client

Spaceduck supports multiple clients — all connecting to the same gateway.

| Client          | Best for                          | How to connect                        |
| --------------- | --------------------------------- | ------------------------------------- |
| **Web UI**      | Default experience                | Open `http://localhost:3000`          |
| **Desktop app** | Native macOS/Linux/Windows window | See [Desktop App](/platforms/desktop) |
| **CLI**         | Scripting and automation          | See [CLI](/platforms/cli)             |
| **WhatsApp**    | Mobile access                     | Requires Baileys setup                |

## What you now have

* A running gateway at `http://localhost:3000`
* A chat model connected and streaming responses
* Persistent conversation history in SQLite
* Automatic fact extraction after every turn
* Keyword-based cross-conversation recall (or semantic recall if you enabled it)

## Next steps

<CardGroup cols={2}>
  <Card title="Model Providers" icon="server" href="/providers/overview">
    Learn about chat vs embedding providers and the two-server pattern.
  </Card>

  <Card title="Memory" icon="brain" href="/concepts/memory">
    Understand how Spaceduck remembers and recalls facts across conversations.
  </Card>
</CardGroup>