Show HN: VetoBench – benchmarking AI memory beyond retrieval

By mart1adelina · 2026-07-08 · 2 points · 0 comments

https://github.com/adelinamart/robrain/tree/main/packages/vetobench

VetoBench is an open-source benchmark that measures whether AI agents repeat engineering decisions a team has already rejected. Instead of evaluating retrieval accuracy, it evaluates decision quality: does the agent propose a previously vetoed approach, and does it recognize whe…

Open the full discussion on BetterNews