RL research on Android devices
An open phone agent model & framework
Multimodal Agents as Smartphone Users, an LLM-based multimodal agent
Automate native Android apps with AI using accessibility APIs
Build Vision Agents quickly with any model or video provider
Open-source, code-first Python toolkit for building, evaluating, etc.
The most powerful Android RPA agent framework
Framework for building AI-powered interactive digital humans and agent
A computer vision framework to create and deploy apps in minutes
Cheat sheet for Google Cloud developers