zcx960/AIA-selection-assistan

MewuAI 喵呜AI | 跨平台开源 AI 屏幕协作软件：AI 圈选重点、截图问答、离线 OCR、原位翻译、录屏与视频标注。Cross-platform open-source AI screen collaboration software: AI key point selection, screenshot Q&A, offline OCR, in-place translation, screen recording, and video annotation

Press ⌥C on anything. Transform with AI, scripts, and shortcuts on any selection. 100% local and private.

A native macOS assistant that reads the current screen and browser context when you need it.

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

Your desktop AI agent, always ready

Local-first floating desktop AI assistant for Windows — selection actions, OCR, notes, and a tool-calling agent.

On-screen aware AI assistant for your desktop. Uses current app context, multiple LLMs, and MCP tools to help you act across apps.

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Browser extension for invoking the DeepSeek AI large model.