Claude Skill
juyterman1000/entroly
Entroly-Daemon compresses 2M-token repos into a principal engineer's context with 95% fewer tokens. Built for Cursor, Claude Code, Opus, Codex, GPT & custom providers. Open-source Rust daemon.
Overview
Repository
Install this Skill
pip install entroly # or: npm i -g entroly · brew install juyterman1000/entroly/entrolyRegistry
pip install entroly # or: npm i -g entroly · brew install juyterman1000/entroly/entrolypip install entroly # core: MCP server + Python enginepip install entroly[proxy] # + HTTP proxypip install entroly[native] # + Rust enginepip install entroly[full] # everything
Summary
Entroly-Daemon is a self-evolving daemon that compresses large code repositories (up to 2 million tokens) into a razor-sharp principal engineer's context, reducing token usage by 95%. It is built for Cursor, Claude Code, Opus, Codex, GPT, and custom providers, making AI interactions more efficient and cost-effective.
Entroly-Daemon：自我进化的守护进程。将200万token的代码仓库压缩成首席工程师级别的精准上下文。减少95%的token消耗——专为Cursor、Claude Code、Opus、Codex、GPT及自定义提供商打造。
Key features
- Self-evolving daemon architecture
- Compresses 2M-token repos into concise context
- 95% token reduction for cost savings
- Supports Cursor, Claude Code, Opus, Codex, GPT & custom providers
- Open-source and built in Rust for performance
Use cases
- Optimizing large codebases for AI code assistants
- Reducing API costs in LLM-powered development workflows
- Enhancing context quality for Claude Code and Cursor
- Streamlining token budgets for enterprise AI deployments
README excerpt
<p align="center"> <a href="docs/i18n/README.zh-CN.md">中文</a> • <a href="docs/i18n/README.ja.md">日本語</a> • <a href="docs/i18n/README.ko.md">한국어</a> • <a href="docs/i18n/README.pt-BR.md">Português</a> • <a href="docs/i18n/README.es.md">Español</a> • <a href="docs/i18n/README.de.md">Deutsch</a> • <a href="docs/i18n/README.fr.md">Français</a> • <a href="docs/i18n/README.ru.md">Русский</a> • <a href="docs/i18n/README.hi.md">हिन्दी</a> • <a href="docs/i18n/README.tr.md">Türkçe</a> </p> <p align="center"> <img src="docs/assets/entroly_wordmark.svg" width="820" alt="Entroly"> </p> <p align="center"><b>Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding.</b><br> Compress context, keep provider caches hot, and verify every answer with a <b>$0 hallucination guard</b>.</p> <p align="center"> <sub>Drop-in for <b>Cursor, Claude Code, Codex, Aider + 34 more</b> and custom providers — 30s, no code changes.</sub> </p> <p align="center"> <sub>Auditable context control plane · every answer gets a receipt: what was used, what was omitted, why, and the risks that remain · local-first · Rust + WASM · reversible · savings measured on real workloads</sub> </p> <p align="center"> <img src="https://img.shields.io/pypi/v/entroly?color=blue&label=PyPI" alt="PyPI"> <img src="https://img.shields.io/npm/v/entroly-wasm?color=red&label=npm" alt="npm"> <img src="https://img.shields.io/badge/License-Apache_2.0-green" alt="License"> <img src="https://img.shields.io/badge/Token_Savings-tested_70--95%25-brightgreen" alt="Token savings"> <img src="https://img.shields.io/badge/Hallucination-HaluEval--QA_0.844_AUROC_·_%240-blueviolet" alt="Hallucination guard"> <img src="https://img.shields.io/badge/Engine-Rust_+_WASM-orange?logo=rust" alt="Rust + WASM"> </p>