screen-ocr

Windows 本地离线语音输入法：按一下反引号说话就出字，识别全程在本机（Qwen3-ASR，无显卡可用，NVIDIA GPU 可加速）；说错了喊一声「小助手」直接改；热词纠错、屏幕上下文、可选 AI 润色。Local offline voice typing for Windows.

Copy text from anything on your screen. Free for Windows.

Eleven Mac utilities in one menu bar app: a Dynamic Island for any Mac (notch or not), per-app volume & EQ, window shortcuts, clipboard, a real performance monitor and an app cleaner. 0.017–0.033% CPU at idle. Free, open source, no telemetry.

Open-source proactive AI desktop assistant for macOS. Watches your screen, suggests next steps, and runs actions for you — even on a schedule — 100% on your machine.

屏幕 OCR 翻译工具：框选识别并覆盖显示译文，截屏翻译，支持本地/云端 OCR、多种翻译引擎和应用内更新。A screen OCR translation tool that lets you select an area to recognize text and display translations as overlays. Supports screenshot translation, local and cloud OCR, multiple translation engines, and in-app updates.

OCR (Optical Character Recognition): free, open source screen OCR app for Mac. Select any area of the screen with a keyboard shortcut, and its text or QR code goes to the clipboard. Offline, on Apple’s Vision, in all languages Vision has on the installed macOS. Native Swift, Apple silicon, macOS 13+.

Mac-style dictionary popup tool for Windows with OCR and offline support.

Optical character recognition (OCR), storefront signage verification, bounding-box grounding, and typed computer-use decision CLI powered by TypeSafe Jev 1.14.

macOS 语音输入助手：热键启动听写、AI Agent 指令、Quick Ask、屏幕 OCR 上下文与剪切板兜底。

CoursePilot：本地 OCR 网课播放自动化，自动识别并点掉"我还在看"确认弹窗。纯本地、不上传、只点白名单。Windows/macOS。Local OCR course video assistant that auto-dismisses continue-watching popups. Privacy-first, on-device.

Hands and eyes for computer-use agents on Windows: 38 MCP tools with guarded input, real screen perception, live browser over CDP - plus a local voice assistant.

Snip any region of your screen, OCR it with Tesseract, and copy text to clipboard. Lightweight Tkinter utility; buildable to a Windows EXE.

Screen OCR - let AI agent see your screen

Safari's Live Text, but for Chrome. Pause any video, click the badge, and the on-screen text becomes selectable and copyable — powered by Apple's Vision framework, the exact same OCR engine Safari uses. macOS 13+.

截图 OCR + 中英互译，一个快捷键搞定 / Screenshot OCR + Chinese⇄English translation with one global hotkey

Copy text and scan QR codes from anything on your screen: paused videos, screenshots, PDFs, slides, games. Local OCR and QR code scanner for Linux.

Cross-platform screen OCR that continuously reads on-screen text and prints it to the console.

Lookup dictionary definitions on Windows using screen OCR for instant macOS-style word lookups.