CalibratedDecisions.

Repo · Search & RAG

jev-tool-search

Benchmark and experimental engine comparing BM25, embeddings, rerankers, and TypeSafe Jev for selecting among 525 real MCP tools.

Open github.com ↗

From the repository

Tool search for LLM agents: BM25 vs embeddings vs rerankers vs Jev on 525 real MCP tools, plus an experimental Jev search engine

agentsai-sdkbenchmarkbm25jevllmmcptool-search

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects