CalibratedDecisions.

Repo · Search & RAG

jev-search (larguesa)

Complementary semantic search CLI and agent skill: Jev scores whether each candidate line expresses the intent you are looking for, so agents find by…

Open github.com ↗

From the repository

Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.

How builders describe it

Experimental semantic line search with TypeSafe Jev via OpenRouter. Python CLI with no runtime dependencies.
Complementary semantic search CLI and agent skill: Jev scores whether each candidate line expresses the intent you are looking for, so agents find by meaning what keyword search misses across repo docs, LLM wikis and Obsidian notes; in six simulated tasks lexical + Jev recovered 29 of 34 labeled…

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