screen-understanding

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Shake your cursor to summon an AI agent that can see your screen and click, type, and act for you on macOS.

Open-source AI copilot for Android: understands the live screen via the Accessibility API, resolves the exact UI element you need in natural language (Hindi, Tamil, English), and visually guides you to it — built for people who find modern app UIs hard to navigate.

A modular perception engine for AI agents that enables efficient screen understanding, reasoning, and autonomous interaction.

A camada de presença entre você e a máquina. Agente desktop open source que vê tela, lê cursor, ouve voz e aprende padrões. Tauri + Rust, AGPL.

macOS-native, screen-aware AI teacher that lives in your menu bar.

🧊 a little buddy who lives on your Mac — talks, sees your screen, remembers how you work