OCR & Documents
HUANGCHIHHUNGLeo/claude-real-video
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
PythonMITupdated Oct 23, 2026
🏆 #1,359 overall#208 of 318 in OCR & Documents
witchan /ios-mcp
让 Claude、Codex、Cursor 等 AI 助手看懂 iPhone 屏幕并直接操作手机的 iOS 自动化工具与 MCP Server，支持 UI 树获取、元素定位、截图与 OCR 识别、点击滑动、文字输入、应用管理和日志读取，适用于自动化测试与 iOS 逆向调试
$ git clone https://github.com/witchan/ios-mcp.gitStars
689
689
Forks
122
122
Language
Objective-C
License
MIT
Created
Apr 7, 2026
0.6 years old
Last push
Sep 27, 2026
Categories
More in OCR & Documents
OCR & Documents
awlevin/typesafe-computer-use
Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.
PythonMITupdated Sep 29, 2026
OCR & Documents
AGIHunt/blurt🔥 active
The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡：Agent 时代的输入法。
🎙️ Speech Recognition
SwiftMITupdated Nov 9, 2026
OCR & Documents
yusufkaraaslan/Skill_Seekers
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
PythonMITupdated Sep 30, 2026
OCR & Documents
Zipstack/unstract🔥 active
LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
PythonAGPL-3.0updated Nov 9, 2026
OCR & Documents
Data from GitHub · snapshot Nov 9, 2026