TencentQQGYLab/AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

47
/ 100
Emerging

This project offers an intelligent assistant that can operate smartphone apps by mimicking human actions like tapping and swiping. It learns to perform tasks either by observing you or through self-exploration, creating a knowledge base for future use. This tool is for anyone who wants to automate repetitive actions on their Android phone, like social media tasks or data entry across apps.

6,582 stars. No commits in the last 6 months.

Use this if you need to automate interactions with smartphone apps for tasks such as filling out forms, navigating complex menus, or performing repetitive actions without needing backend system access.

Not ideal if you require an agent that integrates directly with app APIs or system-level functions, as this tool operates purely through visual and interactive imitation.

mobile-app-automation workflow-automation digital-assistant task-delegation mobile-testing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

6,582

Forks

736

Language

Python

License

MIT

Last pushed

Mar 19, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/TencentQQGYLab/AppAgent"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.