RAG Vault is an open-source tool that lets users run a local Model Context Protocol (MCP) server to search and interact with their own private documents (such as API specs, research papers, code docs) via Retrieval Augmented Generation (RAG) techniques. Designed for privacy and offline use, it enables AI assistants (e.g., Claude, Cursor, Codex) to access local knowledge bases with hybrid search, chunking, and reranking for high accuracy, and offers a web UI and REST API for management. Ideal for developers, technical teams, and privacy-conscious professionals seeking secure and powerful document search and RAG pipelines on their own hardware.
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.