A lightweight, resident clipboard-based text polishing tool powered by a ~50 M parameter text-correction model designed for speed, minimal interference, and easy integration into your everyday workflows.

Project Overview

This project aims to build a standalone text polishing utility that runs in the background and corrects typos, spacing errors, and obvious mis-words in any text copied to the clipboard. Unlike LLM-based rewriting tools, it will:

Not rewrite sentences or alter meaning
Be extremely lightweight (~50 M parameters)
Be hotkey-triggered for instant use
Keep the model pre-loaded in memory for speed
Act as a conditioning pass for copied or transcribed text, markdown fragments, and notes

Features

Lightweight Model Inference
Global Hotkey Integration
Resident Background Service
Custom Post-Processing Hooks
Configurable Aggression

Installation

pip install -e .

Usage

Run the daemon with:

clipboard-polisher

Configuration

The tool uses a configuration file config.py that sets up model name, hotkey, and other settings.

Development

This project is designed to be easily expandable with agent APIs, dictionaries, multi-profile modes, and more.

License

MIT License

File & Folder Structure (Proposed)

clipboard-polisher/
├── src/
│   ├── main.py               # Entry point
│   ├── model_loader.py       # Load and cache model
│   ├── hotkey.py             # Hotkey + clipboard handler
│   ├── config.py             # Settings, profiles
│   └── utils.py              # Diff, logging, helpers
├── requirements.txt
├── README.md
├── setup.py
├── service/
│   └── clipboard-polisher.service   # systemd unit
└── tests/
    └── test_polish.py