Metadata-Version: 2.4
Name: screenshot-assistant
Version: 0.1.0
Summary: A Wayland screenshot assistant with LLM integration
Author-email: tcsenpai <tcsenpai@discus.sh>
Requires-Python: >=3.11
Requires-Dist: build>=1.2.2.post1
Requires-Dist: mss>=10.0.0
Requires-Dist: pillow>=11.1.0
Requires-Dist: python-dotenv>=1.0.1
Requires-Dist: python-xlib>=0.33
Requires-Dist: requests>=2.32.3
Requires-Dist: tk>=0.1.0
Requires-Dist: twine>=6.0.1
Description-Content-Type: text/markdown

# Screenshot Assistant

A Wayland screenshot assistant with LLM integration. Capture screenshots and analyze them using Ollama's LLaVA model.

## Installation

```bash
pip install screenshot-assistant
```

## Requirements

- Wayland compositor (Sway, Hyprland, or other wlroots-based)
- grim (screenshot utility)
- slurp (area selection)
- imv (image viewer)
- Ollama with LLaVA model installed

## Usage

You can run the assistant in two ways:

1. As a command:

```bash
screenshot-assistant
```

2. Using the provided run script:

```bash
./run
```

## Configuration

Create a `.env` file with the following options:

```env
OLLAMA_URL=http://localhost:11434/api/generate
OLLAMA_MODEL=llava
WINDOW_TITLE=Screenshot Assistant
SCREENSHOT_MODE=active  # Options: all, active, select
```

## Development

To set up for development:

```bash
git clone https://github.com/tcsenpai/screenshot-assistant.git
cd screenshot-assistant
uv venv .venv
uv pip install -e .
```
