safedep/gryph

132 stars · Last commit 2026-05-31

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

README preview

<p align="center">
  <a href="https://safedep.io">
    <picture>
      <source srcset="docs/assets/gryph-banner-dark.svg" media="(prefers-color-scheme: dark)">
      <source srcset="docs/assets/gryph-banner-light.svg" media="(prefers-color-scheme: light)">
      <img src="docs/assets/gryph-banner-light.svg" alt="Gryph - Security Layer for AI Coding Agents" width="100%">
    </picture>
  </a>
</p>

<h3 align="center">AI coding agents have no security boundaries. Gryph is building one.</h3>

<p align="center">
  Everyone runs YOLO mode. Nobody checks what happened. Gryph does.
</p>

<p align="center">
  <a href="#quick-start">Quick Start</a> ·
  <a href="#see-it-in-action">Demo</a> ·
  <a href="#supported-agents">Supported Agents</a> ·

View full repository on GitHub →