Repo · Search & RAG

Deep Recall

Answer-aware recall over a folder of Markdown notes (Claude Code plugin + Python CLI/MCP) whose pluggable reranker can be TypeSafe Jev, scoring each…

Open github.com ↗

From the repository

Answer-aware memory for Markdown notes: hybrid search + pluggable passage reranker, as a Claude Code plugin

How builders describe it

Answer-aware recall over a folder of Markdown notes (Claude Code plugin + Python CLI/MCP) whose pluggable reranker can be TypeSafe Jev, scoring each passage window by the probability that it states the answer.

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