Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond (continually updated)
| Date | Stars |
|---|---|
| 2026-07-31 | 314 |
| 2026-08-05 | 314 |
| 2026-08-06 | 314 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome UI Agent
[](https://github.com/sindresorhus/awesome)
[](https://twitter.com/opendilab)
[](https://github.com/opendilab/awesome-ui-agents/stargazers)
[](https://github.com/opendilab/awesome-ui-agents/network)
[](https://github.com/opendilab/awesome-ui-agents/issues)
[](https://github.com/opendilab/awesome-ui-agents/pulls)
[](https://github.com/opendilab/awesome-ui-agents/graphs/contributors)
[](https://opensource.org/licenses/Apache-2.0)
This is a collection of research papers for **UI Agent**, which includes models, tools, and datasets.
And the repository will be continuously updated to track the frontier of UI Agent or related fields.
Welcome to follow and star!
## Table of Contents
- [Awesome UI Agent](#awesome-ui-agent)
- [Table of Contents](#table-of-contents)
- [Overview of UI Agent](#overview-of-ui-agent)
- [Papers](#papers)
- [Models](#models)
- [2026](#2026)
- [2025](#2025)
- [2024](#2024)
- [2023](#2023)
- [Tools](#tools)
- [Datasets](#datasets)
- [Related Repositories](#related-repositories)
- [Contributing](#contributing)
- [License](#license)
## Overview of UI Agent
UI Agent aims to build a generalist agent that can interact with various user interfaces (UIs) in different environments, such as mobile apps, web pages, and PC applications. The agent can understand the UIs through vision-language models and interact with them to complete tasks. The agent can be applied to various scenarios, such as mobile device operation, web browsing, and game playing. The agent can be trained in a simulated environment or with real-world data. The agent can be evaluated in terms of task completion rate, efficiency, and generalization ability.
<p align="center">
<img src="assets/mobile.jpg" alt="Image Description 1" width="80%" height="auto" style="margin: 0 1%;">
</p>
The research on UI Agent is still in its early stage, and there are many challenges to be addressed, such as the scalability of the agent, the robustness of the agent, and the interpretability of the agent. The research on UI Agent is interdisciplinary, involving computer vision, natural language processing, reinforcement learning, human-computer interaction, and software engineering. The research on UI Agent has the potential to revolutionize the way we interact with computers and improve the efficiency and usability of computer systems.
<p align="center">
<img src="assets/pc.jpg" alt="Image Description 1" width="80%" height="auto" style="margin: 0 1%;">
</p>
## Papers
```
format:
- [title](paper link) [links]
- author1, author2, and author3...
- year
- publisher
- key
- code
- experiment environment
```
### Models
#### 2026
- [PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation](https://arxiv.org/abs/2606.05697)
- Nicolas Bougie, Xiaotong Ye, Gian Maria Marconi, Narimasa Watanabe
- Key: persona-conditioned UI/UX evaluation, contrastive reflection fine-tuning, reflective prompt evolution
- ExpEnv: WiserUI-Bench, UIClip/BetterApp, WebDevJudgExcerpt of 35,975 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:42e90ebd76da1ab6, llm:Repository description: 'A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond (continually updated)'. No code; it's a curated resource list about UI agents.
matched fp:42e90ebd76da1ab6, llm:Repository description: 'A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond (continually updated)'. No code; it's a curated resource list about UI agents.
matched fp:42e90ebd76da1ab6, llm:Repository description: 'A curated list of of awesome UI agents resources, encompassing Web, App, OS, and beyond (continually updated)'. No code; it's a curated resource list about UI agents.