screen-automation 话题在 GitHub 上没有填写简介，这里按 Star 数汇总最相关的热门仓库。
把 DeepSeek Harness 打包成能直接装的安卓 APK：不用 Termux、不用 root、不用配电脑，读屏/点按/虚拟屏/定时任务和整套技能都随包；它还能在手机上自己编译、打包、签名、发布。 Android APK for DeepSeek Harness — no Termux, no root, no PC. Screen control, virtual display, scheduled tasks and bundled skills out of the box; it builds, signs and releases itself on the phone.
🚀 AI-Powered Windows Automation Server using Model Context Protocol (MCP) | Control Windows apps, automate tasks, and manage systems through natural language commands with Claude, ChatGPT & other AI assistants | 80+ automation tools
Automates chat replies for Messenger and WhatsApp using PyAutoGUI for UI actions, Pyperclip for clipboard capture, and Groq for AI responses. Cycles configured chat positions, skips replying to your own messages, supports dry-run and logging, and includes cursor tools and easy config for fast testing and demos. Ideal for portfolio demos & research.
Python desktop AI assistant for screen awareness, voice interaction, persistent memory, and computer automation
Auto-play Chinese chess using Pikafish engine + screen automation
A Python automation script using screen recognition with OpenCV, GUI automation with PyAutoGUI, and human-like interactions to reduce detection risk. This bot works by detecting request templates on screen and clicking the donation buttons intelligently.
Windows macro recorder for games and Roblox, with visual workflows, screen detection, OCR, and local automation.
Stronger hands for your AI — the RPA it can actually drive. Record a task once; AI optimizes, combines, and composes it into deterministic automations that control your real apps & browser. Pure-vision, local, MCP-native. The smarter the AI, the stronger it gets.
A computer-use agent with its own desktop and its own cursor — Windows 11 and Linux. It works while you keep using yours. Claude computer-use + PySide6.
Automate screen interactions using visual coordinates and image detection. Built with Python, modular architecture, and robust error handling.
Windows-native autonomous AI agent for desktop automation with vision-based UI navigation, multi-step workflow execution, and LLM-powered reasoning.
Small local OCR and visual-grounding servers for screen automation and agent workflows.
Screen automation tool for Windows - HTTP API for keyboard, mouse, screenshots & UI automation
Python screen-automation bots that farm, harvest, and build in Growtopia using template matching and calibrated click targets.
豆糕 DouGao —— 安卓 AI 手机助手：VLM 看屏自动操作 + 文件直改；无障碍 / Shizuku / Root 三通道控屏，多任务房间可中途纠错
OS runtime for agents — the machine as a toolbox: declared capabilities, post-assertions, undo, audit; no model in the kernel.
A voice-first desktop assistant that notices what you're doing, acts on real apps, and builds her own tools when she needs to.
Screen-reading chess agent: finds a board on screen, reads the position with OpenCV, picks a move with Stockfish and plays it with the mouse.
Your AI co-pilot for desktop tasks
Anthropic native computer use extension for the pi coding agent. Registers the computer tool executor and ensures computer_20250124 is injected on anthropic-messages payloads when opt-in is enabled.