# CrabTrap: Secure Agents in Production

CrabTrap is an LLM-as-a-judge HTTP proxy to secure agents in production. It intercepts and audits AI agent requests in real time. Try it on GitHub now.

**URL Source:** https://www.brex.com/crabtrap

---

OPEN SOURCE

Deploy agents. Safely.

CrabTrap is an LLM-as-a-judge HTTP proxy to secure agents in production. It intercepts every request your AI agent makes, evaluates it against a policy, and allows or blocks it in real time.

Start using CrabTrap in 30 seconds.

Click the terminal to copy setup commands.

_[Interactive module: CrabTrapDemo-SetupPrompt]_

[View on Github](https://github.com/brexhq/CrabTrap/blob/main/QUICKSTART.md) | [Read the Blog Post](https://github.com/brexhq/CrabTrap/blob/main/QUICKSTART.md)

Watch the demo

![CrabTrap video 16x9](https://brand.brex.com/asset/9682a9f7-d425-49b6-9e7e-93a06b5faafc/mp4/CrabTrap-video-16x9.mp4)

SEE THE LLM JUDGE IN ACTION

Watch as CrabTrap decides to block or approve requests and logs whether each decision was a static rule match or an LLM judgment.   
Edit or add new rules to watch CrabTrap intercept them. 

_[Interactive module: CrabTrapDemo-PolicyDemo]_

Come build with us.

We don't wait for the ecosystem to catch up. We find a gap, build the fix, and ship it. If that sounds like your kind of engineering, we're hiring.  


[View open roles](https://www.brex.com/careers) | [Read the Blog Post](https://www.brex.com/journal/building-crabtrap-open-source)