Metadata-Version: 2.4
Name: querysh
Version: 0.1.7
Summary: A shell interface for MLX models
License: MIT
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: mlx-lm>=0.0.6
Requires-Dist: rich>=13.7.0
Dynamic: license-file
Dynamic: requires-python

# querysh

A command-line interface that uses local, offline AI to help you write and execute shell commands. Powered by MLX-optimized Llama 3.2 1B Instruct model running entirely on your machine.

## Features

- Natural language to shell command conversion
- Command validation and safety checks
- Interactive command execution
- Rich terminal interface
- Support for command suggestions and modifications
- Fully local and offline operation using MLX-optimized Llama 3.2 1B Instruct model
- No internet connection or API keys required

## Installation

### Requirements
- Python 3.8 or higher
- macOS (for MLX support)

### Dependencies
- mlx-lm>=0.0.6
- rich>=13.7.0

### Install from PyPI
```bash
pip install querysh
```

### Install from source
```bash
git clone https://github.com/pabl0cesar/querysh.git
cd querysh
pip install -e .
```

## Usage

Simply run the `querysh` command in your terminal:

```bash
querysh
```

Then describe what you want to do in natural language. For example:
- "List all files in the current directory"
- "Find all Python files modified in the last week"
- "Create a backup of my documents folder"

The AI will suggest appropriate shell commands, and you can choose to execute them or modify them.

## Development

### Setup

1. Clone the repository:
```bash
git clone https://github.com/pabl0cesar/querysh.git
cd querysh
```

2. Create and activate a virtual environment:
```bash
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
```

3. Install development dependencies:
```bash
pip install -e ".[dev]"
```
