oomol-lab/pdf-craft alternatives

Vision-model OCR to Markdown; choose when you need a model-agnostic vision OCR API or prefer OpenAI-compatible backends over DeepSeek.

OCR & Document Extraction using vision models

Vision-language model for document image parsing; choose when you want to use this specific model directly for Markdown generation.

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

OCR-free markdown conversion using vision models; a direct peer when you prefer an on-premises vision-model-based toolkit.

An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)

Fast Rust document parser for text-based PDFs; choose when you don't need OCR and want a lightweight library for Markdown extraction.

A fast, helpful, and open-source document parser

API service combining classic OCR with LLM post-processing; pick when you want a self-hosted extraction API rather than a Python library.

Document (PDF, Word, PPTX ...) extraction and parse API using state of the art modern OCRs + Ollama supported models. Anonymize documents. Remove PII. Convert any document or picture to structured JSON or Markdown

Extracts structured data from PDFs/images using traditional document analysis; choose when you need JSON output rather than Markdown/EPUB.

Transforms PDF, Documents and Images into Enriched Structured Data

Pipeline using layout models and external OCR engines; a flexible open-source converter without relying on a commercial vision API.

Get your documents ready for gen AI

Java-based PDF parser for AI-ready data; a JVM-native alternative for text-based PDFs, but not specialized for scanned books.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Combines Tesseract OCR with LLM correction and formatting; choose when you want to use local/API LLMs for post-processing instead of a unified vision model.

Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs

Mature pipeline for converting complex PDFs to Markdown/JSON using layout detection and OCR; a strong but internally different alternative.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

ETL for document structuring with multiple OCR backends; choose when you need to handle many document types beyond just PDFs.

Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

Adds a searchable text layer to scanned PDFs; pick when you only need searchable PDFs, not Markdown/EPUB conversion.

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Document management system for archiving scanned PDFs, not a conversion library.

Open Source Document Management System for Digital Archives (Scanned Documents)

Browser-based PDF toolkit with 90+ end-user features, not a swappable library for developers.

PDFCraft is a free, privacy-focused PDF toolkit that runs entirely in your browser. With 90+ professional tools, you can edit, convert, merge, split, and secure your PDF files without ever uploading them to a server.

PDF viewer optimized for research papers, not a conversion tool.

Sioyek is a PDF viewer with a focus on textbooks and research papers