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

# Installation

> Get OpenPawz running on macOS, Linux, or Windows in under 5 minutes.

# Installation

<Note>First build takes a few minutes while Rust compiles dependencies. Subsequent builds are incremental and much faster.</Note>

## Prerequisites

| Requirement       | Version       | Install                                                              |
| ----------------- | ------------- | -------------------------------------------------------------------- |
| **Node.js**       | 18+           | [nodejs.org](https://nodejs.org/)                                    |
| **Rust**          | Latest stable | [rustup.rs](https://rustup.rs/)                                      |
| **Platform deps** | —             | See [Tauri prerequisites](https://v2.tauri.app/start/prerequisites/) |

### Linux (Debian/Ubuntu)

```bash theme={null}
sudo apt update
sudo apt install libwebkit2gtk-4.1-dev build-essential curl wget file \
  libxdo-dev libssl-dev libayatana-appindicator3-dev librsvg2-dev
```

### macOS

```bash theme={null}
xcode-select --install
```

### Windows

Install [Visual Studio Build Tools](https://visualstudio.microsoft.com/visual-cpp-build-tools/) with the "Desktop development with C++" workload and the Windows 10/11 SDK.

## Clone and build

```bash theme={null}
# Clone the repository
git clone https://github.com/OpenPawz/openpawz.git
cd openpawz

# Install frontend dependencies
pnpm install

# Run in development mode (hot-reload)
pnpm tauri dev
```

The first build will take a few minutes while Rust compiles all dependencies. Subsequent builds are incremental.

## Production build

```bash theme={null}
pnpm tauri build
```

The built app will be in `src-tauri/target/release/bundle/` — platform-specific installer (.dmg, .deb, .msi, etc.).

## Verify

After launching, OpenPawz opens to the Today dashboard. Go to **Settings → Providers** to configure your first AI provider, then create agents and start chatting.

## Recommended: Ollama (local AI)

Ollama powers three systems in OpenPawz: **low-cost tool execution**, **semantic memory**, and **offline chat**. We strongly recommend installing it for zero-cost local inference, but these roles can also be filled by cloud models from any provider.

```bash theme={null}
# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# Worker model — executes MCP tool calls (any model works; local = $0)
ollama pull qwen2.5-coder:7b

# Embedding model — semantic memory + tool discovery (any embedding model works; local = $0)
ollama pull nomic-embed-text

# Chat fallback — offline conversations when no API is available
ollama pull llama3.2:3b
```

Pawz auto-detects Ollama on `localhost:11434`, auto-starts it if needed, and auto-pulls the embedding model on first launch.

### Worker Model Setup

The worker model (`worker-qwen`) is what makes tool execution free. When your cloud AI agent (Gemini, Claude, GPT) needs to run a tool via the [MCP Bridge](/guides/mcp-bridge), it delegates to the local worker instead of making additional API calls.

To set up the worker:

1. Go to **Settings → Advanced → Ollama**
2. Click **Setup Worker Agent**
3. This creates a custom `worker-qwen` model with the right system prompt

Or from the command line:

```bash theme={null}
ollama pull qwen2.5-coder:7b  # Base model (~4.7 GB)
```

The one-click setup in Settings creates the optimized `worker-qwen` variant automatically.

<Note>
  Without Ollama, tool calls go through your paid AI provider. With Ollama, they're free. See the [MCP Bridge guide](/guides/mcp-bridge) for the full Architect/Worker architecture.
</Note>