juyterman1000/entroly

420 stars · Last commit 2026-07-13

Local context-control plane for AI coding agents: select evidence, compress recoverably, keep caches hot, and verify answers. MCP/proxy/SDK for Cursor, Claude Code, Codex, and Aider.

README preview

<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>Know exactly what your AI agent saw.</b><br>
Entroly creates replayable <b>Context Commits</b>: content-addressed proof of the evidence selected, omitted, and kept recoverable for each model request.</p>

View full repository on GitHub →