High-performance BM25 implementation in TypeScript
Configurable BM25 Text Search Engine with simple semantic search support
A simple, easy to use implementation of the Okapi BM25 algorithm.
Computes BM25 Vectorization of Text.
Shared knowledge core - parser, search (BM25), graph builder for CrewX
OpenCodeHub — BM25 + RRF hybrid search
Bayesian probability transforms for BM25 retrieval scores
Query Markup Documents - On-device hybrid search for markdown files with BM25, vector search, and LLM reranking
TypeScript port of tcvdb_text — BM25 sparse vector encoder for Tencent Cloud VectorDB
Unified PostGraphile v5 search plugin — abstracts tsvector, BM25, pg_trgm, and pgvector behind a single adapter-based architecture with composite searchScore
Chroma BM25 sparse embedding function implemented in TypeScript
A lightweight, file-backed vector database for Node.js and browsers with Pinecone-compatible filtering and hybrid BM25 search.
BM25 full-text search engine for CrewX documents and code
KINDX - On-device hybrid search engine for markdown documents with BM25, vector embeddings, and LLM reranking
OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI
TypeScript SDK for Ratel — context engineering platform for AI agents. BM25 tool retrieval, MCP ingestion, framework-neutral gateway tools.
TypeScript bindings for Lattice embedded property-graph database with vector and BM25 full-text search
Hybrid RAG over GitHub repos: BM25 + Pinecone + cited answers.
Fast, accurate text search with BM25 scoring and stemming.
Configurable BM25 Text Search Engine with simple semantic search support
Local-first memory and hybrid retrieval library for LLM agents with pluggable stores, BM25 plus vector search, and a four-stage memory pipeline.
Postgres and pgvector adapter for @jeffs-brain/memory: tsvector BM25, halfvec cosine, and RRF hybrid retrieval.
Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1
MCP server for project-scoped, self-curated memory with hybrid search (BM25 + sqlite-vec).
BM25 embedder, scorer, and search engine
CLI and HTTP server for BM25 Turbo
The fastest BM25 information retrieval engine — 28K QPS on 8.8M docs
A graph-first, embedded multi-model database engine
A fast, streaming-friendly BM25 search engine with mmap support
Local markdown semantic search with hybrid BM25+vector retrieval and LLM reranking
SIFS Is Fast Search: instant local code search for agents
Per-palace BM25 lexical-index subprocess for the trusty-* ecosystem (issue #156)
A minimal Rust library for creating sparse vector representations (embeddings) using the BM25 algorithm for information retrieval.
BM25 embedder, scorer, and search engine
BM25 reranker for RAG: in-memory term-frequency reranking against a small candidate set. Stateless, zero deps.
Fast document indexer for finding duplicates and searching content
Okapi Bm25 for Japanese
fornix-bm25 — reserved
Knitsearch adds FTS5-backed full-text search to ActiveRecord models. Search by rich text, associated records, or multiple models in one query. Index updates synchronously via SQLite triggers, atomic with source writes. BM25-ranked results returned as a chainable Relation. Supports typo tolerance, phrase matching, prefix matching, highlighting, snippets, and more.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.
No description provided.