* [AutoRAG v2.2.0](https://github.com/Marker-Inc-Korea/AutoRAG) – Self-evolving librarian agent that searches document collections and curates results into clean knowledge units using pluggable retrieval methods.

* [Smart Connections 4.7.0](https://github.com/brianpetro/obsidian-smart-connections) – AI-powered tool that connects notes and suggests relevant content to enhance information management.

* [CortexDB v2.74.0](https://github.com/liliang-cn/cortexdb) – Pure-Go, single-file embedded AI memory and knowledge graph library that provides hybrid vector and lexical retrieval, RDF/SPARQL graph features, and MCP tools via SQLite.

* [ClawMem v0.37.0](https://github.com/yoloshii/ClawMem) – On-device context engine providing retrieval-augmented memory, hooks, and an MCP server for Claude Code, OpenClaw, and Hermes agents.

* [GNO v1.35.0](https://github.com/gmickel/gno) – Local knowledge engine for notes, code, PDFs, and Office docs with hybrid search, citations, and verified, explainable answers via CLI, Web UI, REST API, SDK, and MCP.

* [Lux v0.37.0](https://github.com/lux-db/lux) – Redis-compatible sharded key-value store with multi-threaded architecture, built-in vector search, time series, GEO, and real-time subscriptions.

* [ID-based RAG FastAPI v0.9.0](https://github.com/danny-avila/rag_api) – Integration of Langchain with FastAPI for document indexing and retrieval using PostgreSQL/pgvector.

* [ReadAny v1.3.6](https://github.com/codedogQBY/ReadAny) – AI-powered e-book reader with semantic search, intelligent chat, local vector store, annotations, TTS, and knowledge management.

* [QVAC sdk-v0.17.0](https://github.com/tetherto/qvac) – Local-first, cross-platform SDK for building peer-to-peer AI apps with local model inference, speech, translation, and RAG.