jev-search-rerank-eval

Does a TypeSafe Jev rerank beat embedding search? Graded relevance eval (9,831 pairs, 164 zh/en queries) over the Agent Skills Hub catalog, with the judge-circularity bias measured.

Numbers, harnesses, and comparisons you can rerun on your hardware instead of trusting a screenshot. Tags in the wild: benchmarks, rag, agents. The repo has install steps, env vars, and recent commits if you are deciding whether to depend on it.