bytedance/Dolphin alternatives

when you want an Apache-2.0 VLM-based OCR/document parser as a direct model alternative.

GLM-OCR: Accurate × Fast × Comprehensive

when you want a unified end-to-end VLM OCR model as a direct alternative for document parsing.

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

when you need an MIT-licensed, small-model document parser that is lightweight and easy to integrate.

An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.

when you want a lightweight pipeline focused on extracting structured metadata and page content from papers/books.

Lightweight Doc-to-agent-ready knowledge pipeline. Three-stage Bronze→Silver→Gold architecture extracts structured elements, page content, and AI-enriched metadata from research papers and books. Generate PRDs, workflows, topic clusters, and Claude Code skills from PDFs. No OCR required.

when you want an Apache-2.0 ONNX-based pipeline for PDF-to-markdown/JSON with efficient CPU inference.

A high-performance, open-source PDF data extraction tool. 一站式开源高性能数据提取工具，将复杂 PDF 文档转换为 Markdown 和 JSON 格式，使用onnx模型。

when you need a mature, feature-rich pipeline for PDF/Office-to-markdown with strong community support.

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

when you need a C# library for direct text extraction from PDFs without ML inference.

Read and extract text and other content from PDFs in C# (port of PDFBox)

when you need a Node.js library for text and table extraction from PDFs without deep-learning dependencies.

🚜 Parse text and tables from PDF files.

when you are working with historical documents and need a specialized off-the-shelf element extractor.

(ICFHR 2020 oral) Code for "docExtractor: An off-the-shelf historical document element extraction" paper

when you need a zero-dependency Java server-side PDF-to-JSON/text converter without ML.

converts binary PDF to JSON and text, for server-side PDF processing and command-line use. Zero dependency.

when you need a focused OCR library for text detection and recognition, not full layout/markdown parsing.

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.

when you need a classic deep-learning text recognition model for standalone OCR tasks without layout parsing.

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

when you want a simple CLI wrapper for PDF-to-Markdown without deploying a large model.

Standalone CLI wrapper and docs for Nutrient's PDF-to-Markdown extractor