https://github.com/OSU-NLP-Group/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).
https://github.com/OSU-NLP-Group/SeeAct

agent

Last synced: 9 days ago
JSON representation

[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).

• Host: GitHub
• URL: https://github.com/OSU-NLP-Group/SeeAct
• Owner: OSU-NLP-Group
• License: other
• Created: 2023-12-21T18:22:11.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-08-26T13:10:02.000Z (8 months ago)
• Last Synced: 2024-09-18T19:57:33.789Z (7 months ago)
• Topics: agent
• Language: Python
• Homepage: https://osu-nlp-group.github.io/SeeAct/
• Size: 375 MB
• Stars: 586
• Watchers: 16
• Forks: 72
• Open Issues: 14
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• acu - Code
• awesome-ui-agents - SeeAct GPT-4V(ision) is a Generalist Web Agent, if Grounded