macOS CLI for OCR and searchable PDFs using Apple's Vision framework
Tape Measure app by hand tracking for Apple Vision Pro
Chess board app for Spatial SharePlay 【Apple Vision Pro】
This project serves as a showcase for the remarkable ideas behind visionOS. It can be likened to a gallery that demonstrates the vast range of capabilities offered by visionOS.
Flip Board Game for Spatial SharePlay 【Apple Vision Pro】
Facial Analysis that combines the Vision Pro + Vision Framework
MCP server for Claude Code — Apple Vision OCR & image analysis, fully offline, no API keys
Preflight router that decides locally whether each document page reaches a multimodal model as text, on-device OCR, or an image. Cuts vision-token cost. macOS.
Gesture + voice control for macOS. Pinch to move cursor. Swipe for arrows. Circle to screenshot. Speak to run commands.
Local AI that indexes, understands, and tells the story of everything on your machine. Powered by Gemma 4 via Ollama.
Swift Package to add a head-anchored Persona camera to visionOS projects in 2 lines of code - float a facecam in your field of view for recording Apple Vision Pro demo videos
Privacy-first document intelligence for Claude — OCR, PDF extraction, barcode reading, face detection. All on-device via Apple Vision. Nothing leaves your Mac.
AI-powered recipe extraction using Apple Vision OCR and LLM reasoning. Converts photos of recipes into structured data with allergen and FODMAP analysis.
OBS macOS background removal with a Protected Region - keep your microphone (or any static object in front of you) from being cut out. Fork of gxalpha/obs-mac-backgroundremoval.
On-device OCR for images and scanned PDFs using Apple Vision on macOS
UniOCR - Unified multilingual OCR service. Supports PaddleOCR / Apple Vision engines with deep MLX-VLM neural network hardware acceleration. A blazing-fast, local-first API for enterprise AI workflows (n8n/Bob).
Open-source MCP server for FreezeText — OCR anything on your Mac screen from Claude/Cursor. Screen capture, region OCR, image OCR, searchable history.
iOS-focused RouteLO delivery management app with Apple Vision OCR, consented CLOVA fallback, and shared receipt normalization
可沿用的會議總結多代理系統：錄音+投影片照片 → 逐字稿/OCR → 結構化繁中總結 → Obsidian wiki + Word。本機 mlx-whisper 轉錄 + Apple Vision OCR，含驗證/查證/恢復。
The simplest possible video player for Apple Vision
Add a description, image, and links to the apple-vision topic page so that developers can more easily learn about it.
To associate your repository with the apple-vision topic, visit your repo's landing page and select "manage topics."