A system for agentic LLM-powered data processing and ETL

ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.

OpenOCR: An Open-Source Toolkit for General OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.

Local-first, open-source AI assistant for your data. Unify tasks, notes, docs, photos, and bookmarks. Private, self-hosted, and extensible via APIs.

PowerPoint .NET library for reading, modifying, and generating PPTX presentations without Microsoft Office

📄 Production-ready MCP server for PDF processing - 5-10x faster with parallel processing and 94%+ test coverage

Generic framework for historical document processing

TWIX is an open-source data extraction tool that reconstructs structured data from documents at scale, accurately and at low cost, by inferring the shared underlying visual template across documents

⚡ Cloud-native, AI-powered, document processing pipelines on AWS.

Open-source document management platform leveraging AWS managed services. RESTful API for document storage, processing, full-text search, and metadata management. Multi-tenant serverless architecture with auto-scaling... deployed entirely in your AWS account.

MCP server for seamless document format conversion and processing

Plug-and-play document AI with zero-shot models.

Open-source document chat platform with semantic search, RAG (Retrieval Augmented Generation), and multi-provider AI support (OpenRouter, OpenAI, ImageRouter).

Conversion of PDF documents to structured Markdown, optimized for Retrieval Augmented Generation (RAG) and other NLP tasks. Extract text, tables, and images with preserved formatting for enhanced information retrieval and processing.

A Python framework for multi-modal document understanding with Amazon Bedrock

Retrieval of fully structured data made easy. Use LLMs or custom models. Specialized on PDFs and HTML files. Extensive support of tabular data extraction and multimodal queries.

Open-source toolkit to extract structured knowledge graphs from documents and tables — power analytics, digital twins, and AI-driven assistants.

An include filter for Pandoc

A Model Context Protocol (MCP) server implementation exposes document processing capabilities through natural language, supporting both direct human interaction and AI agent tool calling.