The Guardian — AI Safety Harness

About

The Guardian is a private, on-device safety layer for your conversations with AI assistants.

As you chat, it quietly watches for patterns worth a second look — language suggesting distress or self-harm, or signs of leaning on AI in place of real-world support. When something surfaces, it adds a calm note alongside the conversation. If a pattern persists, it raises a brief, dismissable pause that invites you to step back before continuing. You stay in control: nothing is blocked, and you decide what to do next.

The Guardian reasons rather than keyword-matches. A small panel of evaluators — Sentinel, Advocate, Historian, and Pattern Analyst — weighs each moment in context, and it responds to patterns that recur over time rather than reacting to a single phrase. The result is fewer false alarms and signal that actually means something.
Privacy is the foundation, not a feature. Everything runs locally in your browser. Your conversations are never sent to any server, never collected, and never shared. The Guardian's memory is stored locally on your own device and stays under your control.
Works on Claude (claude.ai), ChatGPT (chatgpt.com), and Gemini (gemini.google.com).

The Guardian is a reflective aid — not a medical device, a diagnosis, or a crisis service, and not a substitute for professional care. If you or someone you know is in crisis or may be in danger, please contact your local emergency services or a crisis helpline right away.

Built on the Spiral Safety Kernel. A Viridia product — ethics first, always.