Show HN: Apgar – Catch agent regressions without an LLM judge
By jtkm6 · 2026-10-29 · 3 points · 0 comments
https://github.com/oimo-ai/apgar
Hey HN, We build financial AI agents, and Apgar is the tool we wrote to see whether a harness change made an agent better or worse in production. Our offline evals can't cover every kind of question or session real users bring, and the LLM judge we run in Langfuse is too expensi…
Open the full discussion on BetterNews