ShowUI
ShowUI is an open-source, end-to-end, lightweight vision-language-action model designed for GUI agents.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 1.9k
- Source
- GitHub
- Added
- 2026-06-07
- Last verified
- 2026-06-07
Overview
ShowUI is an open-source, end-to-end, lightweight vision-language-action model designed for GUI agents. It can perform computer operation tasks through visual and language understanding, suitable for scenarios requiring automation of graphical user interfaces. Developers can obtain pre-trained models via platforms such as Hugging Face and fine-tune or deploy them according to specific needs.
Key features
- ▪Open-source and end-to-end
- ▪Lightweight model
- ▪Supports vision-language-action
- ▪Designed for GUI agents
Use cases
Pros
- ＋Easy to integrate
- ＋Supports multiple tasks
- ＋Continuously updated and maintained
Limitations / notes
- －May require additional hardware support
- －Dependent on specific datasets
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
How can I get the ShowUI model?
Pre-trained models can be downloaded via platforms such as Hugging Face.
What tasks does ShowUI support?
Supports various GUI-related tasks including navigation, API calls, and more.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.