GH Repository · TencentQQGYLab
AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
- stars
- 6,881
- 30-day movement
- +52/day
- Related entries
- 60
- Connections
- 1
agent-appPythonllmgpt4pythongpt4vgenerative-aichatgptagent
AppAgent is an LLM-based multimodal agent framework from Tencent's QQGYLab that is designed to operate smartphone apps. It is written in Python, MIT-licensed, and relies on GPT-4/GPT-4V-class models per its topics.
Reach for it when you want an open-source, MIT-licensed framework that drives smartphone apps with multimodal LLM agents.
Use it to
- Operate smartphone apps via multimodal LLM agents
- Build on an existing agent-app framework in Python
- Explore GPT-4V-driven smartphone interaction
- Extend an agent designed to mimic smartphone users
For Developers researching LLM agents that control smartphone apps
- Role
- agent-app
- Language
- Python
- Licence
- MIT
- Forks
- 755
- Open issues
- 88
- Last push
- 2025-03-19
topicsllm-agentsmartphonemultimodalgpt4vpythonautomation