open autoglm

We have hosted the application open autoglm in order to run this application in our online workstations with Wine or directly.

Quick description about open autoglm:

Open-AutoGLM is an open-source framework and model designed to empower autonomous mobile intelligent assistants by enabling AI agents to understand and interact with phone screens in a multimodal manner, blending vision and language capability to control real devices. It aims to create an �AI phone agent� that can perceive on-screen content, reason about user goals, and execute sequences of taps, swipes, and text input via automated device control interfaces like ADB, enabling hands-off completion of multi-step tasks such as navigating apps, filling forms, and more. Unlike traditional automation scripts that depend on brittle heuristics, Open-AutoGLM uses pretrained large language and vision-language models to interpret visual context and natural language instructions, giving the agent robust adaptability across apps and interfaces.

Features:

• Multimodal phone screen understanding (vision + language)
• Autonomous control of smartphone actions (tap, swipe, type)
• Framework for scripting and deploying mobile AI agents
• Integration with device automation layers like ADB
• Example demos for real apps to quickly prototype agents
• Open framework for research and custom workflows

Programming Language: Python.
Categories: