Open source software for image correlation, distance and analysis

Genshin Impact vs The Legend of Zelda: Breath of the Wild

Python library that transforms screenshots into actionable data by intelligently detecting UI elements and generating structured descriptions

Set-of-Mark detection pipeline for macOS — Apple Vision, YOLO11, and VLM on MLX. Transforms screenshots into numbered element maps and structured JSON manifests.

🚀 AI-powered Windows troubleshooting assistant using Google Gemini 2.5 Pro. Analyzes system specs, processes error screenshots, and provides intelligent solutions with Chain-of-Thought reasoning. Professional PyQt6 GUI with enterprise security.

📱 AI-powered remote phone support for parents. Send a screenshot → Get annotated step-by-step instructions. 爸妈手机急救站 - 再也不用吼着教爸妈用手机了

AI Scraping Stack — web intelligence platform for competitor analysis & automated scraping. Multi-agent pipeline extracts insights from URLs, analyzes screenshots with VLMs, generates production-ready HTML/React code. 10+ providers with cascade fallback, zero-cost mode with Ollama + OpenRouter. Built with FastAPI, Pydantic, MCP

AI-powered UI testing automation - Test Web, Mobile (Android/iOS), Desktop apps like a human with visual AI analysis

🐞BugPilot is an AI-powered QA Agent that transforms screenshots and tester notes into structured, professional bug reports and automatically creates JIRA tickets using LLaMA 4 Scout vision model. Supports both web and mobile app screenshots.

AI agents that can control real computers, navigate the web, and execute multi-step tasks using Scrapybara and OpenAI’s Computer Use (CUA) models

Marvel Snap screenshot pipeline — ByteDance models via goosecli, local Google Photos ingestion, game reconstruction and analysis