Rag Vault is a locally hosted retrieval-augmented generation (RAG) pipeline server designed to power AI coding assistants for searching, retrieving, and indexing private documentation such as research papers, code documentation, and internal specs. It prioritizes privacy and control, running entirely on the user's machine by default, and can be integrated as an MCP server for tools like Cursor, Claude Code, Codex, and more. Rag Vault offers robust search features—hybrid vector and keyword (BM25) search, instant ingestion, security controls, and a web UI for uploading, managing, and searching files. It is ideal for developers, technical teams, and researchers who need a secure, high-performance knowledge base for AI applications.
Visit Rag Vault's official website for product details and getting started.
Comprehensive API reference and setup instructions for RAG Vault.
Report bugs and request features directly on the GitHub repository.