# Guardrail

> Open-source pre-execution security for AI coding agents - FvdHMBAI/guardrail

- **Website:** https://github.com/FvdHMBAI/guardrail
- **Pricing:** open source
- **Categories:** Developer Tools, Writing & Content
- **Tags:** developer-tools, writing-content, data-analytics
- **Platforms:** macOS, Linux, CLI
- **Last verified:** 2026-09-10
- **Canonical page:** https://linkrena.com/tools/guardrail

## About

GuardRail blocks what your AI coding agent does , before it does it. 13 free, MIT-licensed guards hook into Claude Code and refuse git push origin main , DELETE without WHERE , rm -rf on protected paths and leaked secrets before the command runs. Every block lands in an audit log.

Free forever for the 13 core guards. Teams that need a PII shield on agent output and EU AI Act reports: GuardRail Pro, EUR 29 per developer and month .

My AI agent tried to mass-delete a production database. One guard said no.

The agent was debugging a slow query. It found the table, decided the data was stale, and ran DELETE FROM profiles . No WHERE clause. 23 databases, every single customer record. Gone in one command.

Except it wasn't gone. GuardRail blocked the command before it executed. The agent got a clear error, adjusted its approach, and fixed the actual performance issue instead.

That's the difference between validating what an LLM says and blocking what an AI agent does .

What you actually install. Run guardrail status after install and these are the numbers you see.

That's it. One command. Every command your AI agent runs is now guarded. No config needed.

Works with Claude Code out of the box (native hook support). Agent-runtime adapters for Codex CLI and Gemini CLI are planned.

## Related tools

- [Texbrain](https://linkrena.com/tools/texbrain): FOSS browser-based LaTeX editor with live preview, on-demand packages and git integration.
- [TexLite](https://linkrena.com/tools/texlite): TexLite: Lightweight self-hosted collaborative LaTeX editor and Overleaf alternative - SWUFE-DB-Group/TexLite
- [Yass](https://linkrena.com/tools/yass): Yet Another Stock Screener — screen stocks using fundamental signals, backtest with point-in-time data, evaluate with Monte Carlo analysis - jamesjxliao/yass
- [It Was Never You](https://linkrena.com/tools/it-was-never-you): Re-write their wrongs.
- [Slideops](https://linkrena.com/tools/slideops): Turn a repository into a slide deck that tells you when it stops matching the code - glukicov/slideops
- [C++ Stories](https://linkrena.com/tools/c-stories): "Hardening" seems to be a very popular term in the C++ World in 2026.