Skip to content

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

License

Notifications You must be signed in to change notification settings

Anthonyy232/SeeAct

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Clone repo install miniconda

conda create -n seeact python=3.11
conda activate seeact
pip install seeact
pip install pillow playwright
playwright install

Clone and run docker from bruin-web

create an account with username: anthony, password test

python runner.py

About

[ICML'24] SeeAct is a system for generalist web agents that autonomously carry out tasks on any given website, with a focus on large multimodal models (LMMs) such as GPT-4V(ision).

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.9%
  • JavaScript 2.1%