Skip to content

ShowUI

A vision-language-action model for GUI agents

Visit official site

What ShowUI is

The model is described as a lightweight vision-language-action model built for GUI agents by showlab.

What you can do with it

  • Feed image and text inputs
  • Predict an interface action
  • Drive clicks, typing and selection

Getting started

  • Install the listed dependencies
  • Clone the code repository
  • Launch the interface and load the model

Pros & cons

✓ What we like

  • Action prediction follows user instructions
  • Training and deployment on Hugging Face are listed

! What to watch out for

  • Setup needs dependencies and a repo clone
  • The model targets GUI automation tasks

FAQ

What does it combine?

Visual input, language understanding and action prediction.

Where is it released?

Hugging Face is named as the release platform.

Last reviewed: 2026-11-15

More AI coding tools tools

View all →

How we review