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 →