OCR middleware
-
achu
A lightweight desktop app for beautifying screenshots and more.
-
anamra
A native macOS capture-to-outcome workspace: screenshot, OCR, voice, AI-assisted drafts, local semantic memory, and confirmable Apple exits.
-
CircleToSearch App
CircleToSearch with multi search engine support for all android
-
cna-oab-attorney-data-scraper
📊 Scrape attorney data from the OAB CNA Directory with this Python tool, collecting names, OAB numbers, and UFs efficiently and reliably.
-
dots.ocr-fix-demo
🖼️ Upload images to experience accurate multilingual OCR results with the enhanced dots.ocr model and fix processor loading issues seamlessly.
-
FireRed-OCR
Extract text from images using a robust OCR model designed for accuracy and efficiency in varied visual contexts.
-
Forkyz Scanner
Crossword-scanning companion app to Forkyz crossword app.
OCR Android -
HappyTaxes
Private bookkeeping for freelancers, small business, or personal finances.
OCR Android -
hop
Free menu bar toolkit for macOS: Pomodoro timer, time tracker, keep-awake, system monitor, clipboard history, file converter, window manager, torrents, file archives, text recognition (OCR), color picker, keyboard lock. Swift + SwiftUI, 18 languages, no telemetry — everything stays on your Mac.
OCR iOS -
Image Toolbox
Edit, create & convert images with powerful AI — your all-in-one studio
-
inspector-rust
Keyboard-first clipboard hyper-toolkit for power users: history, snippets, text expander, screen OCR, region screenshot, inline calculator, color picker, image recolor + ML background cutout. macOS + Windows. Native (Tauri 2 + Rust + React), local, AES-256 encrypted at rest, MIT.
-
Learning-Assistant
错题追踪器，支持 Markdown + LaTeX 编辑、OCR 识别、PDF 导出
-
marginalia
Kindle Scribe handwritten notebooks -> Obsidian Markdown, with OCR and human review.
-
OCR
OCR based on Tesseract 5
OCR Android -
OCR (Tesseract)
Optical character recognition (OCR) functionality based on Tesseract via Intents
OCR Android -
ocr-trigger-clicker
免寫程式的 Windows 自動化工具 — 偵測螢幕文字後自動點擊與按鍵。OCR + 圖像比對雙引擎、多步驟流程、跨解析度相容。
-
officeparser
A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.
-
Offline Translator
On-device translation of text, images and pdf/odt files, with TTS
-
OpenScreenTranslate
一款由 AI 驱动的开源 macOS 菜单栏截图翻译工具，帮助你快速识别并翻译屏幕文本。使用翻译功能前，需要自行申请并配置受支持 AI 服务供应商的 API Key。
-
OwOCR
Optical character recognition for Japanese text
-
pdf_oxide
The fastest Rust PDF library — 0.8ms mean, 5× faster than the industry leaders, 100% pass rate on 3,830 real-world PDFs. Text extraction, Markdown/HTML conversion, PDF creation and editing.
OCR Rust -
pdf2wiki
Convert technical books (native-text PDFs) into clean, chapter-split, LLM-ready Markdown — dual-pass MinerU pipeline with fidelity-preserving post-processing.
-
pdfvision
CLI and TypeScript library for evidence-first PDF reading by AI agents — native text and quality signals first; targeted search, layout, rendering, and OCR when needed.
-
PostgraduateExamPrep
A structured study management system for the 11408 postgraduate entrance exam, with progress logs, textbook notes, OCR search, and a generated dashboard.
-
pypi-security-best-practices
Secure your Python supply chain with this curated list of best practices for safe package installation, vulnerability scanning, and dependency management.
-
qiushi-skill
Build AI agent skills with dialectical methods and practical tools from classical materialist philosophy for clearer judgment and action
-
SassyMCP
One MCP server, 270 tools, replaces 75+ — files, shell, GitHub, Android, desktop vision, security & forensics, persistent memory. Smart context-saving tool loading, safe-delete guardrails, and an orphan-proof self-healing process supervisor. Works with Claude Desktop, Cursor, Windsurf, and any MCP client.
-
shotik
Beautiful open-source screenshot tool for Windows with a built-in MCP server - let Claude see your screen
-
Shots Studio
AI powered screenshots manager and organizer
OCR Android -
tessera
Distill large language models into small, efficient students using a custom stack featuring GPU kernels, sharded training, and high-performance inference.
-
Tesseract OCR
Optical character recognition engine — extract text from images in 100+ languages.
-
tesseract.js-core
Tesseract C++ API in Pure Javascript
-
TRex
Easy to use text extraction tool
-
GLM-OCR-Demo