jxmorris12/gptzip

A compression based language model

14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.

Data Compression using Arithmetic Encoding in Python

Free CLI from Everest that compresses Codex tool output.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Drop-in prompt compression for production LLM apps. Cut your token bill 40-60% without changing your code. Python SDK, LLMLingua-2, MIT.

Code for BLT research paper

Caveman Compression is a semantic compression method for LLM contexts. It removes predictable grammar while preserving the unpredictable, factual content that defines meaning.

A Lossless Compression Library for AI pipelines