Context Window Optimization Python Packages

cocoindex-code

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!

trimwise

Light-weight, query-aware compression for high-signal LLM prompts.

claw-compactor

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

ison-graph

ISONGraph is a multi-language property graph library designed specifically for LLM and AI applications. It provides the most token-efficient way to represent graph data in LLM context windows while maintaining high accuracy for graph-based reasoning tasks.

incontext

Exact dynamic output budgeting for Hermes Agent

fast-pruner

A structure-aware, local prompt compressor and context optimizer for LLM pipelines.