Adrian

Open-source runtime security tool that catches AI agents misbehaving in real time

PlatformWebfreeglobal

Adrian is an open-source runtime AI agent security tool that monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time by watching what the agent actually does — before it acts — rather than relying on static analysis or network monitoring alone.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Adrian - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Adrian to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Adrian (or something else) actually fits.

Try a problem