Laya guard is a free local guardrail for AI coding agents. Every tool call is judged on-device before it runs, using regex plus a local model, and is allowed, sent for review or blocked. It ships as a PyPI package with a dashboard, supports Claude Code and other agents, and runs on macOS and Linux.
Be the first to rate Laya guard. Your feedback helps other users decide.
Each call is evaluated on your machine before it executes.
The verdict is three-way rather than a binary.
A dashboard records the decisions.
Similar tools in the same category — compare side-by-side
BitRun is a zero-compile runner and terminal dashboard for 1-bit and 1.58-bit ternary language model...
DBJoy is a native macOS client for PostgreSQL with an AI assistant built in. You ask questions about...
ScratchCAD is AI-driven parametric CAD. A Rust solid modelling API built on the OpenCASCADE kernel i...
Guides and comparisons about code tools
Four Show HN launches that verify agent work rather than trusting its summary: an execution record, an AI-app scanner, a local guardrail and adversarial tests.
Five Show HN launches that keep work on your machine: a ternary model runner, a distillation proxy, a PostgreSQL client, CAD over MCP and a local ETL builder.
Four Show HN launches around voice and ops: voice planning for agents, a live game coach, CI for AI phone agents and a self-hosted MCP platform on Kubernetes.
Eight new tools that decide where a coding agent runs, how many run at once, and how you keep working in the same file it is editing.
Eight new tools for what sits under an agent: deterministic memory, an agentic database, distributed inference, hardware checks and spend guards.
