LLMpress aims to cut LLM token use for large codebases

LLMpress is a tool meant to reduce the number of tokens sent to an LLM while keeping as much useful information as possible. It does not try to invent a new method. Instead, it combines existing techniques that can make code and prompts smaller.

For code, it uses language-aware minification, while trying to keep links back to the original readable source when possible. It can also apply optional . Its approach is meant to shrink code more aggressively while still making it possible to map the compact version back to the original code.

The long-term goal is to help where large codebases are repeatedly sent to an LLM.

Key points

  • LLMpress focuses on reducing tokens sent to an LLM.
  • It targets that send large codebases to a model.
  • It uses code minification and optional .
  • It uses an approach to keep code tied to the original source.
  • Its value depends on whether cost drops without hurting answer quality.
Read original