mnotgod96 / AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.
https://appagent-official.github.io/
MIT License
4.97k stars 538 forks source link

Added the option to leverage AppAgent for Figma (Option 3) #89

Closed dusskapark closed 1 month ago

dusskapark commented 2 months ago

Hello @mnotgod96 and @icoz69

Firstly, I would like to express my sincere gratitude for making such an interesting project available on GitHub. As a product designer, I found AppAgent to be a compelling tool that could revolutionize the way we conduct user testing and research. I was particularly inspired by the potential of automating many of the challenges we face in these areas.

With this in mind, I embarked on a journey to port AppAgent to Figma, a tool widely used by designers. I believe this adaptation could provide significant benefits to the design community by enabling more efficient and effective user testing.

In this pull request, I have implemented the core functionality of AppAgent in a Figma environment. I have used automated Chrome tabs to mimic the functionality of the Figma API, which currently does not support prototypes. I have also added an experimental persona function, which was not present in the original Tencent project.

I have updated the README with detailed instructions on how to use these new features. For a more visual guide, I have also created a video demonstrating the usage of these features in action. Please refer to the following video link for additional explanation:

Video link Video Label

In addition to these changes, I have made a minor modification to the common utility functions for logging purposes. I assure you that this change does not interfere with the existing functionality in any way.

I hope you find these contributions valuable. I look forward to hearing your feedback.