A code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
AI Computer Use for Claude Code — The open-source alternative to OpenAI Codex's playwright-interactive. Dual-engine: Win32 API + Playwright. Control WeChat, DingTalk, Feishu, QQ, Slack, Teams, and any web/Electron app. Automated QA, viewport testing, visual feedback loops.
A FastAPI-based backend utilizing Google Cloud Vision API to provide intelligent, real-time visual question-answering via REST endpoints and WebSockets.
Claude Code plugin that audits your project before you deploy. 40+ checks across security, visual QA, code quality, testing, error handling, build config, and performance. One command, structured report, actionable fixes. Auto-detects your stack.
Reasoning-based, vectorless RAG over a large document using a hierarchical tree (PageIndex) and a Vision-Language Model (Llama 4 Scout), no embeddings, no vector store, no text chunking.
Vision + LLM pipeline: YOLOv8 object detection, GPT-4V scene understanding, and automated visual QA with streaming API
Enable AI-driven control of Windows apps with native desktop and web automation using Win32 API and Playwright in one skill.
Add a description, image, and links to the visual-qa topic page so that developers can more easily learn about it.
To associate your repository with the visual-qa topic, visit your repo's landing page and select "manage topics."