document-intelligence

RAG-powered document intelligence assistant built for the Midnight Hackathon AI Track. Users upload confidential documents (medical records, contracts, financial statements, legal files) and interrogate them through a natural-language chat interface. The system returns grounded, cited answers without exposing raw document contents unnecessarily.

The #1 Obsidian MCP for AI memory — freshness-aware, cited, local-first and read-only by default. Dataview, Bases, PDFs, every agent.

AI document intelligence for Paperless-ngx — semantic search, receipt extraction, and one-click DATEV export with a built-in bilingual web UI. 100% local via Ollama, ships as an MCP server for Claude Code.

Fully local document intelligence for DeepSeek Harness. Parse PDF, Office files, images, and scanned documents with offline OCR. | DeepSeek Harness 全本地文档智能插件，支持 PDF、Office、图片与离线 OCR

A live, evolving collection of open-source AI agents and real examples showing how businesses can use AI to automate work, save time, and explore new ideas.

A full-stack RAG demo you can run locally or deploy to a VPS: upload a PDF, build a per-browser vector index (FAISS), chat with an LLM using retrieved context. The UI is a React + TypeScript SPA; the API is FastAPI + LangChain with a multi-agent pipeline, Sentry tunneling, & sensible production defaults (CORS, rate limits, session disk cleanup)

Air-gapped enterprise RAG workstation — local inference, zero cloud egress. Built with Microsoft Foundry Local.

https://youtu.be/u8KJYQgUOs8 AI-powered paralegal assistant that extracts, summarizes, and analyzes legal documents. Upload PDF/DOCX contracts to get instant summaries, extract key clauses, and perform intelligent document analysis using OpenAI.

Healthcare document-intelligence prototype for prior-authorization readiness review

Zero-dependency local document intelligence substrate. Extract semantic embeddings, multi-topic clusters, revision diffs, and structural signal packets offline at the edge in <1ms. Ships pre-trained vector geometry directly in the runtime.

LLM-powered semantic search and question-answering system for intelligent document retrieval using Next.js, OpenAI, and vector embeddings.

AI-driven document intelligence for security and policy analysis

A production-grade, AI-powered document intelligence platform designed to transform raw files into actionable data. It features an end-to-end pipeline for automated quality analysis, OCR, layout-preserving translation, semantic search, and smart print/binding recommendations. Built as a scalable monorepo using Next.js, FastAPI, and PostgreSQL.

Organize and search Paperless-ngx documents with local AI, auto-classification, receipt extraction, and accounting export.

DocuMind is a document intelligence app where users can upload files, extract knowledge, and query them in natural language, combining semantic search (Qdrant), graph insights (Neo4j), and LLM reasoning.

Privacy-preserving legal document intelligence with local embeddings, regex-based risk scoring, and Hinglish explanation engine.

DocSense AI: AI-powered document intelligence and entity analysis platform It would be useful for: - HR resume screening - Legal contract review - Research document analysis - Business intelligence - Compliance document review - Academic project/report analysis - Personal document organization - Knowledge extraction from PDFs and images

An enterprise-grade, high-performance RAG (Retrieval-Augmented Generation) document intelligence platform. Features multi-PDF upload, real-time citation-backed vector search using Qdrant & Groq, and persistent cross-device chat history powered by Supabase and Firebase.

Microsoft Word add-in for Knowledge Stack — chat, edit, review, summarize, format, and extract data from Word documents with permission-scoped retrieval and chunk-level citations. React + TypeScript + Fluent UI + Office.js.

AI-powered digital reading platform with intelligent, context-aware interaction.