Hi, I’m Farhan, a software engineering student. I’ve built an MCP project and an agent that handles prompt-injection risks and human approvals. I’m interested in contributing to Archestra’s MCP or agent-security work. Is there a suitable issue I could discuss with the team before starting?

New blog post :writing_hand:

We run Jev on 100 real AI tool calls for the annotator pipeline. The errors exposed problems in both the models and our benchmark.

👋 Hi everyone!

Hi archestra team,

I wanted to contribute these prs (found them when playing with the platform) for some minor fixes.

please take a look when you have moment: