Noir context — SHA-256 incremental indexer and hybrid retrieval (BM25 + vector kNN + Reciprocal Rank Fusion).

Memory layer engine for AI coding agents — Gemini embeddings + embedded LanceDB hybrid retrieval

TeamBrain hybrid retrieval: SQLite FTS5 + sqlite-vec + RRF behind a RetrievalBackend interface

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.

MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati

The memloom engine: hybrid retrieval, a belief pipeline that keeps contradictions instead of overwriting them, context ingestion, and an entity graph.

OpenClaw enhanced LanceDB memory plugin with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, long-context chunking, and management CLI

Local-first exact, BM25, and hybrid retrieval for Node.js on macOS arm64

Local-first, encrypted memory daemon for AI coding agents — hybrid retrieval, provenance receipts, MCP tools, SQLCipher at rest

Local-first, auto-injecting, self-aware-about-staleness context + memory layer for coding agents (Claude Code, Codex, MCP). Trust contract, hooks-first, hybrid retrieval + compression, zero infra.

Generic hybrid retrieval ranker — fuses vector similarity + text relevance signals (mechanism-agnostic: textScore / vecScore) via normalized RRF/max-score fusion. SearchBackend interface decouples ranking logic from storage. SqliteSearchBackend wires Vect

Generic org-isolated lexical, semantic, and hybrid retrieval companion for Memorix

Shared knowledge stack (chunking, AST, embedders, vector store, hybrid retrieval) for cli + code-search-mcp.

MCP server for Crosmos Memory Engine with hybrid retrieval

Persistent local memory for any MCP client. SQLite + FTS5 + sqlite-vec hybrid retrieval, bi-temporal asOf queries, contradiction detection, LLM-free reflection. Multilingual embeddings. Knowledge Graph. No cloud, no API keys.

Tenant-scoped Knowledge Base: hybrid retrieval (pgvector + BM25), ingest, answer pipeline, persona/skill composition. LLM I/O живёт в @chatman-media/llm-router.

Talon CLI: hybrid retrieval over Obsidian vaults and markdown corpora, with grounded answers, MCP server, and agent-native output.

Local-first memory MCP server for coding agents — markdown vault + Postgres/pgvector hybrid retrieval with self-superseding hygiene.

AI-powered architecture documentation generator with RAG, hybrid retrieval (semantic + structural), and multi-agent workflows using LangChain