A Space to test what a coding-agent guardrail says about a shell command

A developer built a Hugging Face Space that lets users paste a shell command an AI coding agent might run and see whether the laya-guard guardrail returns allow, review or block, plus which step made the decision. The guard is laya-guard (MIT licensed), a free local guardrail that judges every tool_call on-device using regex plus Laya and provides hooks for Claude Code, Codex, Cursor, Gemini CLI and 7 more agents. The Space runs a small CPU model via gr.Server (a FastAPI subclass) with GET / and POST /api/judge routes, uses preload_from_hub to fetch model files at build time, and relies on an unused @spaces.GPU function so a free account can host it now that CPU Basic requires PRO.

Hi all I made a small Space where you can paste a shell command an AI coding agent might run and see what a guardrail would answer before it runs: allow, review ask the user or block, and which step decided it. How it’s built, in case it’s useful to anyone doing the same: @spaces.GPU function to exist, so there’s one that is never called and visitors’ GPU quota isn’t touched. That’s how a free account can host a small CPU model now that CPU Basic needs PRO. gr.Server a FastAPI subclass : GET / , POST /api/judge . GRADIO SSR MODE=false is needed for the custom / route. preload from hub pulls the model files at build time, so a woken Space doesn’t download them. The guard itself is laya-guard MIT , hooks for Claude Code, Codex, Cursor, Gemini CLI and 7 more agents: GitHub - scs0209/laya-guard: Free local guardrail for AI coding agents: every tool call judged on-device regex + Laya , allow/review/block · GitHub https://github.com/scs0209/laya-guard Feedback welcome, especially commands it gets wrong.