GitHub Repository

Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding. Local proxy that compresses context, keeps provider caches hot, and verifies LLM output ($0 hallucination guard). Drop-in for Cursor, Claude Code, Codex, Aider + 34 more and custom providers — 30s, no code changes

415 starsPython

Entroly – Compress codebase context for LLMs by 78% using Rust

Name: Entroly – Compress codebase context for LLMs by 78% using Rust
Availability: InStock
Author: savetokens

by savetokens·Mar 22, 2026·1 point·0 comments

Visit Project View on HN

AI Analysis

●●SolidBig BrainNiche Gem

Entropy-based context compression beats naive token stuffing, but the category is crowded.

Strengths

•Shannon entropy scoring and SimHash dedup is a genuinely clever technical approach to context selection.
•Built-in 55-rule SAST scanner and codebase health grades add value beyond compression.
•Rust engine with <10ms overhead shows serious performance consideration.

Weaknesses

•Context optimization for LLMs is well-served by Cursor, Continue, and Cody already.
•78% compression claim needs independent verification against real-world codebases.