Metadata-Version: 2.4
Name: tokensaver
Version: 0.1.0
Summary: A lightweight pre-processor to minimize LLM token usage
Home-page: https://github.com/yourusername/tokensaver
Author: Abhijit Chatterjee
Author-email: abhijit@gritt.cloud
License: MIT
Project-URL: Homepage, https://github.com/grittcloud/tokensaver
Project-URL: HuggingFace Space, https://huggingface.co/spaces/grittai/tokensaver
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Dynamic: license-file

# 💻 TokenSaver

A lightweight Python library to **minimize LLM token usage** before sending prompts to GPT, Claude, Mistral, etc.  

## ✨ Features
- **Text Cleaning** → collapse whitespace, normalize newlines.
- **JSON Minify** → compact JSON to reduce tokens.
- **Entity Compression** → replace long repeated names with short placeholders.

## Installation
```bash
pip install tokensaver
