#ocr

A native Rust toolkit for OCR, document layout analysis, and vision-language document understanding.

No repository description published.

A ready-to-go translation ocr tool developed with WPF/WPF 开发的一款即用即走的翻译、OCR工具

The developper starter pack for document processing

Rust library and CLI tool for OCR (extracting text from images)

JavaScript OCR and text extraction for images and PDFs.

모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form filling and diff

Full AI context and content layer for coding agents over one MCP server — tree-sitter code-map, document RAG, shared memory, multi-agent comms, web crawl, git history + blame. 300+ languages, 10+ agent harnesses, pure Rust.

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr

Convert PDF documents to Markdown using Vision Language Models — CLI and library

视觉小说翻译器 / Visual Novel Translator

MCP server that turns any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct URLs, local files — into transcripts, key frames, OCR text, and metadata for AI agents.

Document Layout Analysis

Asset-Aware MCP Server — AI Agent precisely accesses tables, figures, sections from PDFs + .docx round-trip editing (DFM) with 46 tools / 13 resources, segmentation export, layout overlay, OCR preprocessing, knowledge graph (LightRAG)

No repository description published.

.NET RAG document processing library that transforms PDF, DOCX, HWP, and more into optimized chunks via a 5-stage pipeline with Rust-based FFI readers.

Anyline React Native Module for iOS and Android

Читання рукописних архівних справ і пошук прізвища в них — для генеалогів. HTR під імперський скоропис, каталоги архівів, поаркушеві покажчики плівок.

A fast, helpful, and open-source document parser for PHP

A Python wrapper for the tesseract-ocr API

No repository description published.

Kreuzberg v4 LTS — long-term support for the v4 line (legacy; superseded by xberg for v5+). MIT-licensed.

高性能OCR识别库，支持上百种语言，提供命令行、图形界面及C API多种调用方式，使用便捷高效。 High-performance OCR library powered by PaddleOCR v4/v5/v6 with MNN backend. Supports 10+ languages (Chinese, English, Japanese, Korean, Arabic, Cyrillic, Thai, etc). Provides Rust crate + C API + CLI tools. Fast, lightweight, easy-to-integrate.