MCP server for building knowledge graphs from documents. It ingests PDF/PPTX/DOCX files, transcribes to Markdown, and uses LLM to bootstrap entity patterns and build a JSONL knowledge graph with RAG chunks.
An MCP server for document parsing, ingestion, query (including multimodal), and lightweight knowledge graph inspection, enabling RAG workflows via the Model Context Protocol.
A local-first, LLM-agnostic MCP server that lets you ask hard questions about your documents, media, and code, and get traceable answers entirely offline.