{"slug": "a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command", "title": "A Space to test what a coding-agent guardrail says about a shell command", "summary": "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.", "body_md": "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.\n\nHow it’s built, in case it’s useful to anyone doing the same:\n\n`@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.\nThe 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)\n\nFeedback welcome, especially commands it gets wrong.", "url": "https://wpnews.pro/news/a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command", "canonical_source": "https://discuss.huggingface.co/t/a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command/190936#post_1", "published_at": "2026-10-23 05:32:08+00:00", "updated_at": "2026-10-23 05:40:18.920802+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "ai-safety", "developer-tools"], "entities": ["laya-guard", "Hugging Face Spaces", "Claude Code", "Codex", "Cursor", "Gemini CLI", "scs0209"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command", "markdown": "https://wpnews.pro/news/a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command.md", "text": "https://wpnews.pro/news/a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command.txt", "jsonld": "https://wpnews.pro/news/a-space-to-test-what-a-coding-agent-guardrail-says-about-a-shell-command.jsonld"}}