Skip to main content

A simple GUI tool for cleaning text copied from LLM outputs

Project description

ClipClean 🧹

A simple GUI tool for cleaning text copied from LLM (Large Language Model) outputs. Removes problematic Unicode characters, fixes formatting issues, and makes text ready for use in documents or other applications.

Features

  • Simple Interface: Clean, focused GUI designed for quick text cleaning
  • LLM-Optimized: Specifically targets common issues in AI-generated text
  • Dark/Light Mode: Automatic theme detection based on system settings
  • Auto-Paste: Automatically loads clipboard content when opened
  • Smart Cleaning: Handles Unicode normalization, smart quotes, special dashes, and more
  • Real-time Stats: Shows character count and reduction percentage
  • Settings Persistence: Remembers your preferences between sessions
  • Enhanced UX: Visual feedback, status indicators, and smooth interactions

Common Issues It Fixes

  • Smart quotes ("")
  • Special dashes (, -)
  • Non-breaking spaces and other invisible characters
  • Excessive whitespace and line breaks
  • Unicode characters that don't display properly
  • Markdown formatting artifacts

Installation

From PyPI (recommended)

pip install clipclean

Standalone Executables

Download pre-built executables from the Releases page:

  • Windows: clipclean-windows.exe
  • macOS: clipclean-macos

From Source

git clone https://github.com/kevinobytes/clipclean.git
cd clipclean
pip install -e .

Usage

Simply run the application:

clipclean

Quick Workflow

  1. Copy text from your LLM (ChatGPT, Claude, etc.)
  2. Open ClipClean (it auto-pastes)
  3. Click "Clean" or let auto-clean do it
  4. Copy the cleaned text

Keyboard Shortcuts

  • Ctrl+V - Paste from clipboard
  • Ctrl+C - Copy cleaned text
  • F5 or Ctrl+Return - Clean text
  • Ctrl+L - Clear all
  • Escape - Clear all

Theme Options

  • Auto: Automatically detects system theme (default)
  • Light: Light theme for all environments
  • Dark: Dark theme for all environments

Settings

  • Auto-paste on startup: Automatically pastes clipboard content when the app opens
  • Auto-clean on paste: Automatically cleans text when pasted
  • Theme preference: Saved between sessions

Requirements

  • Python 3.8+
  • tkinter (included with Python)
  • pyperclip

Development

# Clone and set up development environment
git clone https://github.com/yourusername/clipclean.git
cd clipclean
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
pip install -e .

# Run from source
python -m clipclean.gui

License

MIT License - see LICENSE file for details.

Contributing

Contributions welcome! Please feel free to submit issues or pull requests.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

clipclean-1.0.0.tar.gz (176.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

clipclean-1.0.0-py3-none-any.whl (12.0 kB view details)

Uploaded Python 3

File details

Details for the file clipclean-1.0.0.tar.gz.

File metadata

  • Download URL: clipclean-1.0.0.tar.gz
  • Upload date:
  • Size: 176.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.1

File hashes

Hashes for clipclean-1.0.0.tar.gz
Algorithm Hash digest
SHA256 64a552a9dfdb32d2d1b85c54452ba8e16d2e0b8a34b366280be12640bf76a9c5
MD5 54919313b53b97a9e2dd6c392c256564
BLAKE2b-256 3bb589e372d7887893ab935e1b9b9b8cbd1c260c98047385ec54d31ade715fbc

See more details on using hashes here.

File details

Details for the file clipclean-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: clipclean-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 12.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.1

File hashes

Hashes for clipclean-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 5e837c6c0043d13eee75699c429e172bbd2b0fa423ec9fe3ed9807dc4214e0ba
MD5 1f2d14365bf02af52aed130eef1306c7
BLAKE2b-256 e2a4d866178322181f2792063a923e4a8f5a1e3171360706cdffbf4120eaee63

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page