TencentQQGYLab/AppAgent
AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
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.
Stars
6,582
Forks
736
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
mitdbg/palimpzest
A System for Optimized Semantic Computation
SamurAIGPT/GPT-Agent
🚀 Introducing 🐪 CAMEL: a game-changing role-playing approach for LLMs and auto-agents like...
bubbuild/republic
Build LLM workflows like normal Python while keeping a full audit trail by default.
lwcsrf/netflux
Minimalist framework for authoring custom agentic applications in python; emphasizes task...
dlMARiA/Syzygy-of-thoughts
Syzygy-of-thoughts