Show HN: Laya guard – a local check before your coding agent runs a command

Category: security

Tags: security, ai-agent, local-first, guardrail, shell-command

Score: 7.3/10 (Innovation: 7, Technical: 6, Documentation: 9, Utility: 7)

Laya-guard is a local guardrail for AI coding agents that judges shell commands before execution, using regex prefiltering and a small multilingual model to block, review, or allow commands. It integrates with 11 agents, offers file protection, and runs entirely locally, addressing a critical security gap in agentic workflows.

Target audience: developers using AI coding agents, devops, security engineers

Repository: https://github.com/scs0209/laya-guard · Python · MIT · 31 stars

View on Hacker News