Okareo

If you're building voice or text agents and need to run them through their paces, this connects Claude to Okareo's full evaluation stack. You can register models, create test scenarios, run evaluations with quality checks, and simulate multi-turn conversations with synthetic users right from your editor. The remote mode handles auth via OAuth and lets you switch between Okareo organizations without bouncing out to the web UI. It also exposes voice monitoring tools to ingest and analyze completed conversations from providers like Twilio or Deepgram. Useful when you want to find edge cases and regression test agents without leaving your workflow.