95 Forks
753 Stars
753 Watchers

SeeAct

[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).

How to download and setup SeeAct

Open terminal and run command
git clone https://github.com/OSU-NLP-Group/SeeAct.git
git clone is used to create a copy or clone of SeeAct repositories. You pass git clone a repository URL.
it supports a few different network protocols and corresponding URL formats.

Also you may download zip file with SeeAct https://github.com/OSU-NLP-Group/SeeAct/archive/master.zip

Or simply clone SeeAct with SSH
[email protected]:OSU-NLP-Group/SeeAct.git

If you have some problems with SeeAct

You may open issue on SeeAct support forum (system) here: https://github.com/OSU-NLP-Group/SeeAct/issues