A powerful Universal Document Question-Answering System that uses advanced embedding models and multimodal LLMs with Coarse-to-Fine search (RAG) approach. Features seamless MCP (Model Context Protocol) integration with Claude Desktop, comprehensive direct
TypeScript SDK for document processing with zero-friction framework adapters. Features intelligent coordinate handling, semantic regions, React UI overlays, and automatic route detection for Remix and Next.js. Transform raw bounding boxes into interactive
Advanced n8n community node for intelligent document retrieval with multi-step reasoning, reranking, and comprehensive debugging
MCP server for Scrivener - Read, analyze, and manipulate Scrivener writing projects. Features RTF parsing, document structure analysis, word counting, and AI-powered writing assistance for authors using Claude or other LLMs.