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

# Quickstart

> Get agtOS running in 5 minutes

Get from zero to a working agtOS instance in about 5 minutes. Choose your path:

<Tabs>
  <Tab title="Desktop App (recommended)">
    The fastest way to get started. No terminal or Node.js required.

    <Steps>
      <Step title="Download the app">
        Get the desktop app for your platform from [GitHub Releases](https://github.com/agtos-ai/agtos/releases):

        | Platform | Download                       |
        | -------- | ------------------------------ |
        | macOS    | `.dmg` (Apple Silicon + Intel) |
        | Windows  | `.msi` installer               |
        | Linux    | `.AppImage` or `.deb`          |
      </Step>

      <Step title="Launch and onboard">
        Open the app. The onboarding wizard starts automatically and walks you through:

        1. **Dependencies** — checks what's available on your system
        2. **AI Provider** — enter your Anthropic API key (and optionally an OpenAI key)
        3. **Speech Models** — downloads voice models (\~460MB) for local speech processing
        4. **Microphone Test** — verifies your mic works with real-time audio levels
        5. **Preferences** — choose your TTS voice, language, and push-to-talk hotkey

        <Tip>
          Don't have a Claude API key? You can skip it and use local-only mode with [Ollama](https://ollama.ai). Or get a key from [console.anthropic.com](https://console.anthropic.com).
        </Tip>
      </Step>

      <Step title="Start chatting">
        After onboarding, the dashboard opens with voice and text chat ready to use:

        * **Voice** — click the microphone or press your push-to-talk hotkey (default: `Alt+Space`) from any app
        * **Text** — type in the chat panel on the dashboard
        * **System tray** — agtOS runs in the background with a health indicator

        The app also works as an MCP server — connect it to Claude Desktop for tool access.
      </Step>
    </Steps>
  </Tab>

  <Tab title="CLI (developers)">
    For developers who want full control, source access, and terminal-based workflow.

    **Prerequisites:** Node.js 22+ ([download](https://nodejs.org))

    <Steps>
      <Step title="Install">
        ```bash theme={null}
        git clone https://github.com/agtos-ai/agtos.git
        cd agtos
        npm install
        ```
      </Step>

      <Step title="Run the setup wizard">
        ```bash theme={null}
        npx agtos setup
        ```

        The wizard checks dependencies, prompts for API keys, and validates them against the actual provider API.

        The wizard prompts for:

        * **Anthropic API key** — enter your `sk-ant-api03-...` key from [console.anthropic.com](https://console.anthropic.com), or press Enter to skip
        * **OpenAI API key** (optional) — enter your `sk-...` key from [platform.openai.com](https://platform.openai.com), or press Enter to skip

        You need at least one cloud provider key for chat and voice. Without any keys, agtOS runs in local-only mode with [Ollama](https://ollama.ai).
      </Step>

      <Step title="Download voice models (optional)">
        ```bash theme={null}
        npx agtos models download --default
        ```

        Downloads the default speech model set (\~460MB) for local voice processing. Without models, agtOS runs in text-only mode.
      </Step>

      <Step title="Start the server">
        ```bash theme={null}
        npx agtos start
        ```

        ```
          ✓ Health endpoint
          ✓ Voice pipeline
          ✓ MCP server
          ✓ Task scheduler
          ✓ API routes

        agtOS server is running!
          Dashboard:  http://localhost:4102
          Voice WS:   ws://localhost:3000/audio
          MCP:        http://localhost:4100/mcp
        ```
      </Step>

      <Step title="Try it out">
        ```bash theme={null}
        npx agtos chat
        ```

        Or open the dashboard at `http://localhost:4102`, or connect from Claude Desktop:

        ```json theme={null}
        {
          "mcpServers": {
            "agtos": { "url": "http://localhost:4100/mcp" }
          }
        }
        ```
      </Step>
    </Steps>

    **Optional:** Start Redis for cross-session memory and task scheduling:

    ```bash theme={null}
    docker compose up -d redis
    ```
  </Tab>
</Tabs>

## What's next?

<CardGroup cols={2}>
  <Card title="Use Cases" icon="lightbulb" href="/use-cases">
    See what you can build with agtOS.
  </Card>

  <Card title="Explore Features" icon="compass" href="/features/voice-pipeline">
    Voice pipeline, memory, MCP tools, dashboard, and more.
  </Card>

  <Card title="Configuration Guide" icon="gear" href="/configuration/authentication">
    Configure providers, models, and advanced options.
  </Card>

  <Card title="FAQ" icon="circle-question" href="/guides/faq">
    Common questions about setup, voice, memory, and privacy.
  </Card>
</CardGroup>