create figma variables with a desktop automation solution

Python based Desktop assistant integrated with Openai API to generate AI responses that works on voice commands and performs actions like opening and searching on web pages and device applications, messaging contacts

Automated file organizer for your Downloads folder with per-rule lifecycles.

Desktop automation server for AI agents, enabling remote control of mouse, keyboard, and screen capture via programmable tools.

A real-time hand gesture recognition system for desktop control, offering a hands-free, camera-based user experience.

POC realizada durante o Curso Python e Tecnologias Abertas ministrado pela equipe da BotCity, com o intuito de apresentar as ferramentas e plugins da plataforma.

Automatically change your wallpaper folder on KDE desktop

Clipboard monitor that converts copied text to speech (TTS) using configurable engines (Edge-TTS, Piper, SAPI). Streams audio locally.

Desktop application management tool with intelligent window orchestration. Manage and arrange multiple applications across monitors with customizable grid and side-by-side layouts. Windows 10/11.

This project enables hands-free media control using voice and gesture recognition. It uses Google Speech Recognition and MediaPipe with OpenCV to detect commands, which are executed via PyAutoGUI. Compatible with platforms like YouTube and VLC, it enhances accessibility and user interaction.

A smart desktop organization app that auto-tags and sorts your files using optional AI-powered metadata. Features undo support, database tracking, customizable rules, and a simple GUI.

Evaluation of GPT-4o-mini on OSWorld desktop automation benchmark. Compares screenshot-only vs accessibility tree-enhanced approaches across 10 tasks (Chrome, LibreOffice, file ops, etc). Documents critical coordinate extraction failures and provides architectural recommendations for GUI agents.

Organizes your desktop files into folders of the choosen category

Intelligent AI Assistant with Computer Vision capabilities powered by Claude. Features screen capture, visual analysis, and intelligent automation. Control via web interface or desktop GUI for seamless human-computer interaction.

A Python automation tool that reads employee data from a CSV file and automatically generates ID cards. It resizes and places each employee photo, adds their name and ID, and saves the final cards as ready-to-use images.

Desktop and Browser Automation

Automation tests for MTA on IDE

Kirim pesan otomatis ke aplikasi chat apapun (WhatsApp Desktop, Telegram, Line, dsb) hanya dengan Python dan PyAutoGUI.

Fetch National Geography photo of the day and set as your desktop wallpaper.

AI-driven desktop automation