A lightweight, file-backed vector database for Node.js and browsers with Pinecone-compatible filtering and hybrid BM25 search.

BM25 search, reranker, and hybrid fusion for hybrid RAG systems

BM25 search for coding agent sessions

BM25 search over llms.txt doc indexes (Strands, Kiro, AWS); sources addable at runtime.

Agentic document retrieval over markdown — BM25 search + tree navigation via MCP. Inspired by PageIndex and Pagefind.

Research Knowledge Vault MCP Server — BM25 search, graph traversal, lint, and index operations for Obsidian-compatible research wikis.

Standalone code intelligence CLI — hybrid vector + BM25 search, dependency analysis, PageRank

Configurable BM25 Text Search Engine with simple semantic search support

Persistent memory wiki for LLM agents — sub-agent orchestration, auto-learning, and BM25 search

MCP server for searching past Claude Code conversation history. Local BM25 search over JSONL logs with persistent index, secret redaction, solved-hint, and instant claude --resume.

A complete search engine and RAG pipeline in your browser, server, or edge network with support for full-text, vector, and hybrid search in less than 2kb.

Intelligent MCP skills server — BM25 search, progressive disclosure, Ed25519 integrity

MCP server for Festo/CODESYS PLC engineering — IEC 61131-3 ST generation, validated PLCopen XML, embedded knowledge base (27 topics, 19 manuals, BM25 search), 38-block ST library, optional CODESYS IDE driving and hardware commissioning

Persistent inverted index and BM25 search engine with proximity penalty.

MCP server for Obsidian vault with BM25 search, backlinks, tags, and more

A derived, rebuildable SQLite index over a git-primary Markdown corpus, with an HTTP-agnostic MicroCMS-like read-only query API and always-on FTS5 (BM25) search, built on the plgg family

MCP (Model Context Protocol) server for HeurChain — tiered agent memory with BM25 search, session lifecycle, procedural memory, ambient capture, and frictionless session-context injection

HSA - Hierarchical Semantic Analysis MCP Server for AI Code Agents. Token-optimized context engine with BM25+ search, Merkle tree change detection, 84+ built-in library docs, persistent memory, and real-time dashboard.

Unified PostGraphile v5 search plugin — abstracts tsvector, BM25, pg_trgm, and pgvector behind a single adapter-based architecture with composite searchScore

High-performance BM25 implementation in TypeScript