Vibe Coding DiscoverOpen-AutoGLM
View on GitHubAn Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
An open-source phone-use agent that interprets screen content with AutoGLM vision-language models, plans actions, and controls Android, iOS, or HarmonyOS devices. Includes a Python API and CLI, with ADB, HDC, and WebDriverAgent-based device control.
Use Cases
Automate mobile apps from natural-language instructionsSearch and compare products across shopping appsNavigate phone interfaces and complete multi-step tasksControl Android, iOS, and HarmonyOS devicesRun mobile UI automation over remote device connections
Built With
- Language
- Python
- Frameworks
- OpenAI API · ADB · HDC · WebDriverAgent · vLLM · SGLang
Tags
phone agent · computer use · mobile automation · multimodal · UI automation · Android · iOS · HarmonyOS · ADB · HDC · natural language tasks