Railguard

Railguard, developed by BrightOnLABS, is a modular security framework that adds granular, constraint-based guardrails to AI systems like Claude Code to block dangerous commands while permitting safe operations.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.