Clicky is an experimental AI-powered desktop companion designed to act as an interactive, real-time teaching assistant that lives directly alongside the user’s cursor on macOS. It functions as a menu bar application that can observe the user’s screen, interpret context, and provide guidance through both voice and visual cues, effectively simulating the experience of having a human tutor sitting next to you. The system captures screenshots and combines them with voice input to send contextual queries to AI models, which then respond with both spoken explanations and on-screen visual pointers. One of its defining features is the ability to physically “point” at UI elements across multiple monitors using a cursor overlay, helping users navigate complex software step by step. The architecture includes integrations for speech-to-text, text-to-speech, and AI reasoning models, all routed securely through a proxy to protect API keys.
Features
- AI assistant that observes and understands the user’s screen context
- Real-time voice interaction with speech-to-text and text-to-speech
- Cursor overlay that visually points to UI elements across monitors
- Menu bar-based macOS app with floating control panel
- Secure API proxy architecture to protect credentials
- Multi-modal interaction combining screenshots, voice, and AI responses