CalibratedDecisions.

Repo · Search & RAG

sieve

Local MCP server for coding agents: code enumerates repository/file/search candidates; TypeSafe Jev scores them via jev_grep, jev_rank, and…

Open github.com ↗

How builders describe it

Local MCP server for coding agents: code enumerates repository/file/search candidates; TypeSafe Jev scores them via jev_grep, jev_rank, and jev_search—returning locations and probabilities, never generated prose.

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 56 search & rag projects →

Related projects