Adrian is the first open-source security monitoring toolkit that analyses not just what your agent does, but what it thinks. Based on research from OpenAI and DeepMind, Adrian installs with just 2 lines of code and applies security monitoring to your AI agents. When your agent starts looping, gets compromised, becomes misaligned or generally starts misbehaving you get notified on Slack or Discord. Adrian is free, forever, and even supports running entirely locally on your system.

Framer — Launch websites with enterprise needs at startup speeds.

Launch websites with enterprise needs at startup speeds.

Agents don’t behave like software, so your security shouldn’t either. Adrian is the open-source runtime security toolkit built to secure agents that think. I had always wanted to start my own business, and as an ethical-hacker, I spent years breaking into some of the best protected organisations and governments on the planet. This gave me an unfair advantage in understanding how security risks truly play out. I quit his job in 2025 and met my cofounder Steve Street. I have the technical and product mind, Steve is strong in commercial delivery. We both saw the same problem: security tooling for AI agents was short sighted, generic, and locked behind a 12-18 months procurement cycle. We said we were going to make the best security monitoring system on the market, and gave it away for free, forever. I could not be more excited to be launching Adrian today.

Framer — Launch websites with enterprise needs at startup speeds.

Launch websites with enterprise needs at startup speeds.

Adrian

The open-source runtime security toolkit for your agents

The open-source runtime security toolkit for your agents