Bm25l Length Normalized Document Ranking For Variable Length Documents

via “bm25 ranked document retrieval”

MCP server that gives AI coding agents on-demand access to private project docs. BM25 ranked search, multi-project support, one setup for any MCP-compatible agent (Claude Code, Cursor, Codex, Gemini CLI, and more).

Unique: Utilizes the BM25 algorithm specifically optimized for private documentation retrieval, enhancing relevance scoring over traditional keyword searches.

vs others: More efficient than standard keyword search engines for project documentation due to its relevance-focused scoring.

via “bm25l length-normalized document ranking for variable-length documents”

Various BM25 algorithms for document ranking

Unique: Implements the BM25L variant with modified length normalization formula that prevents saturation bias, addressing a known limitation of standard BM25 when document lengths vary widely

vs others: Better than BM25Okapi for heterogeneous corpora with extreme length variation, but requires empirical evaluation to confirm improvement on specific datasets