REPOGEO REPORT · LITE

OpenGVLab/ScaleCUA

Default branch main · commit 5d92feea · scanned 5/14/2026, 5:27:06 AM

GitHub: 1,110 stars · 78 forks

AI VISIBILITY SCORE

35 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

1 pass · 1 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface OpenGVLab/ScaleCUA, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Reposition the README's opening to clearly state its purpose as an AI research project

Why:

CURRENT

# ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

<p align="center">
&nbsp&nbsp📑 <a href="https://arxiv.org/abs/2509.15221">Paper</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/datasets/OpenGVLab/ScaleCUA-Data">Dataset</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://huggingface.co/collections/OpenGVLab/scalecua-68c912cf56f7ff4c8e034003">Model</a>&nbsp&nbsp | &nbsp&nbsp🖥️  <a href="https://github.com/OpenGVLab/OpenCUA">Model Demo</a>&nbsp&nbsp 
</p>

COPY-PASTE FIX

# ScaleCUA: Scaling Open-Source Computer Use Agents with Cross-Platform Data

ScaleCUA is an open-source research project providing large-scale datasets and trained models for developing advanced AI computer use agents (CUAs). These agents are designed to operate autonomously across diverse cross-platform environments, including Windows, macOS, Ubuntu, and Android, leveraging Vision-Language Models (VLMs).

<p align="center">
&nbsp&nbsp📑 <a href="https://arxiv.org/abs/2509.15221">Paper</a>&nbsp&nbsp | &nbsp&nbsp🤗 <a href="https://huggingface.co/datasets/OpenGVLab/ScaleCUA-Data">Dataset</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://huggingface.co/collections/OpenGVLab/scalecua-68c912cf56f7ff4c8e034003">Model</a>&nbsp&nbsp | &nbsp&nbsp🖥️  <a href="https://github.com/OpenGVLab/OpenCUA">Model Demo</a>&nbsp&nbsp 
</p>

hightopics#2

Add more specific AI/ML research topics

Why:

CURRENT

computer-use-agents, data, gui-agents, models, online-evaluation-suite, scalecua

COPY-PASTE FIX

computer-use-agents, data, gui-agents, models, online-evaluation-suite, scalecua, vision-language-models, ai-agents, large-scale-dataset, machine-learning-research, cross-platform-ai

mediumhomepage#3
Add the project's paper link as the homepage URL
Why:
COPY-PASTE FIX
```
https://arxiv.org/abs/2509.15221
```

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface OpenGVLab/ScaleCUA

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

microsoft/playwright

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

microsoft/playwright · recommended 1×
appium/appium · recommended 1×
asweigart/pyautogui · recommended 1×
RaiMan/SikuliX1 · recommended 1×
robotframework/robotframework · recommended 1×

CATEGORY QUERY
How to develop autonomous agents capable of interacting with GUIs across multiple operating systems?
you: not recommended
AI recommended (in order):
1. Playwright (microsoft/playwright)
2. Appium (appium/appium)
3. PyAutoGUI (asweigart/pyautogui)
4. SikuliX (RaiMan/SikuliX1)
5. Robot Framework (robotframework/robotframework)
6. UIPath
7. Microsoft Power Automate Desktop
AI recommended 7 alternatives but never named OpenGVLab/ScaleCUA. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Where can I find large-scale datasets and models for training computer interaction agents?
you: not recommended
AI recommended (in order):
1. Gymnasium
2. DeepMind Lab
3. Habitat
4. Google Research's Open X-Embodiment Dataset
5. RL Unplugged
6. Hugging Face
7. RoboNet
AI recommended 7 alternatives but never named OpenGVLab/ScaleCUA. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
warn
Suggestion:
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of OpenGVLab/ScaleCUA?
pass
AI named OpenGVLab/ScaleCUA explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts OpenGVLab/ScaleCUA in production, what risks or prerequisites should they evaluate first?
pass
AI named OpenGVLab/ScaleCUA explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo OpenGVLab/ScaleCUA solve, and who is the primary audience?
pass
AI named OpenGVLab/ScaleCUA explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of OpenGVLab/ScaleCUA. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/OpenGVLab/ScaleCUA.svg)](https://repogeo.com/en/r/OpenGVLab/ScaleCUA)

HTML

<a href="https://repogeo.com/en/r/OpenGVLab/ScaleCUA"><img src="https://repogeo.com/badge/OpenGVLab/ScaleCUA.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

OpenGVLab/ScaleCUA — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite