OXR

Indra OCR is a CPU-oriented document OCR and parsing tool developed by Datalab. It converts PDFs and images into Markdown, plain text, or JSON containing recognized lines, bounding boxes, layout blocks, labels, reading order, confidences, rotation, and skew information. It can use a digital PDF's text layer where it passes checks and OCR only missing content, or OCR every page. The pipeline uses ONNX Runtime models without PyTorch to detect lines, recognize text, classify blocks such as headings, lists, tables, captions, footnotes, headers, and forms, and order them for reading. Its local viewer displays page overlays, Markdown, source lines, JSON, confidences, and per-stage timings. An optional math mode recognizes mathematical lines and emits inline LaTeX. The Python package and CLI are distributed under Apache 2.0, while the model weights use a modified OpenRAIL-M license with additional commercial-use conditions. The models are downloaded from Hugging Face on first use; the repository reports a model size of about 18 MB. OCR support covers Latin, Cyrillic, Greek, Devanagari, Bengali, and Chinese scripts, while other scripts can be processed through digital PDF text layers. The project documents limitations for handwriting, degraded scans, complex tables, vertical text, and some scripts in scanned images.

OpenRAG is an open-source agentic Retrieval-Augmented Generation platform for ingesting, processing, filtering, and searching timestamped Markdown, documents, and other knowledge through an AI-backed conversational interface. It uses Langflow for document ingestion and retrieval workflows, Docling for parsing messy real-world data, and OpenSearch for semantic and enterprise search; its agentic workflows support re-ranking and multi-agent coordination. The platform is built with FastAPI and Next.js, runs with Docker or Podman, provides Python and TypeScript/JavaScript SDKs for chat integration, and includes a built-in Model Context Protocol server at the /mcp endpoint exposing RAG chat, semantic search, document ingestion, knowledge filters, and settings-management tools to compatible AI assistants.

doc7 is an open-source document-to-Markdown tool that converts PDFs, Office files, scans, screenshots, charts, formulas, and diagrams into AI-ready Markdown using an OpenAI-compatible multimodal vision model. It renders and understands complete pages rather than relying on character extraction, preserving text, tables, formulas, chart and diagram relationships, image meaning, and visible UI state; the video also describes page-level retry and resume. The model can run locally through LM Studio or Ollama or through a remote endpoint, with no required OCR stack or document-processing service. The same binary provides an interactive CLI, batch processing, model checks, MCP support, a Go SDK, and an asynchronous HTTP service, with installers for macOS, Linux, and Windows.

SurfSense is a free, open-source desktop application and NotebookLM-style AI agent for researching, transforming, and editing documents on the user's machine. It indexes files locally, supports local or OpenAI-compatible remote models, and returns cited answers from sources including PDF, Word, Excel, PowerPoint, CSV, image, Markdown, plain-text, and HTML files. It can create or edit documents as copies, fill and flatten PDF forms, add watermarks and page elements, merge or split PDFs, modify tracked Word changes and comments, edit spreadsheet values and formulas, transform sources into PDFs, podcasts with transcripts, mind maps, flashcards, and quizzes, and use OCR for supported scanned documents and images. The application is distributed for Windows, macOS Apple Silicon, and Linux; it has no account requirement, uses an Apache-2.0 license, and can run offline or air-gapped when paired with a local model.

MiniCPM-OCR is an open-source family of AI models from OpenBMB for document parsing, OCR, and OCR-result quality assessment. MiniCPM-OCR 1.0 parses Chinese and English documents and PDFs, including scans, photographs, curved or skewed pages, and recaptured documents. It recognizes text, tables, formulas, charts, seals, and structured information, and can output parsed content as Markdown or JSON. MiniCPM-OCR Jev is a companion OCR correctness decision model. Given an image and its OCR result, it returns a score from 0 to 1 for text, formula, and table recognition, helping identify reliable results and regions that require review. The models support local deployment through vLLM, SGLang, llama.cpp, and Ollama, as well as a pip SDK, API, free hosted API, and online demos. The repository provides model weights, quantized variants, deployment and fine-tuning tutorials, and related skills; the project, documentation, code, and model weights are released under the Apache License 2.0.