REPOGEO REPORT · LITE

niuzaisheng/ScreenAgent

Default branch main · commit 2312c852 · scanned 6/2/2026, 9:28:17 AM

GitHub: 600 stars · 66 forks

AI VISIBILITY SCORE

40 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 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 niuzaisheng/ScreenAgent, 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 README's introductory paragraph to differentiate from traditional RPA

Why:

CURRENT

We have built the ScreenAgent project, creating an environment for Visual Language Model agents (VLM Agent) to interact with real computer screens. In this environment, the agent can observe screenshots and manipulate the GUI by outputting mouse and keyboard operations. We have also designed an automatic control process, which includes planning, action, and reflection stages, guiding the agent to continuously interact with the environment and complete multi-step tasks. In addition, we have built the ScreenAgent dataset, which collects screenshots and action sequences when completing various daily computer tasks.

COPY-PASTE FIX

Integrate the following sentence into the first introductory paragraph of the README: 'Unlike traditional GUI automation tools, ScreenAgent provides a comprehensive research framework for developing and evaluating VLM agents that understand and control any desktop environment through natural language.'

mediumtopics#2

Expand repository topics for better categorization

Why:

CURRENT

agent, ai, llm, vlm

COPY-PASTE FIX

agent, ai, llm, vlm, gui-automation, desktop-automation, human-computer-interaction, research-framework

mediumreadme#3

Clarify project license in README

Why:

COPY-PASTE FIX

Add a section or line in the README, e.g., 'This project is licensed under the terms specified in the [LICENSE](LICENSE) file. Please refer to the file for full details on usage and distribution.'

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 niuzaisheng/ScreenAgent

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

UIPath Studio

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

UIPath Studio · recommended 1×
Microsoft Power Automate for Desktop · recommended 1×
Automation Anywhere Enterprise A2019 · recommended 1×
Blue Prism · recommended 1×
PyAutoGUI · recommended 1×

CATEGORY QUERY
Looking for a tool to automate complex desktop tasks using an AI agent.
you: not recommended
AI recommended (in order):
1. UIPath Studio
2. Microsoft Power Automate for Desktop
3. Automation Anywhere Enterprise A2019
4. Blue Prism
5. PyAutoGUI
6. Robocorp
AI recommended 6 alternatives but never named niuzaisheng/ScreenAgent. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What frameworks enable visual language models to control graphical user interfaces?
you: not recommended
AI recommended (in order):
1. OpenAI's GPT-4V
2. Gemini 1.5 Pro
3. pyautogui
4. AutoGPT
5. BabyAGI
6. Microsoft's AutoGen
7. Microsoft's VALL-E X
8. Google's ScreenAI
9. Pix2Struct
10. Selenium
11. Playwright
12. Puppeteer
13. OpenCV
14. Tesseract
15. YOLO
16. DETR
17. GPT-4
AI recommended 17 alternatives but never named niuzaisheng/ScreenAgent. This is the gap to close.
Show full AI answer

Objective checks

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

Metadata completeness
pass
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 niuzaisheng/ScreenAgent?
pass
AI named niuzaisheng/ScreenAgent explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts niuzaisheng/ScreenAgent in production, what risks or prerequisites should they evaluate first?
pass
AI named niuzaisheng/ScreenAgent 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 niuzaisheng/ScreenAgent solve, and who is the primary audience?
pass
AI named niuzaisheng/ScreenAgent 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 niuzaisheng/ScreenAgent. 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/niuzaisheng/ScreenAgent.svg)](https://repogeo.com/en/r/niuzaisheng/ScreenAgent)

HTML

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

Pro

Subscribe to Pro for deep diagnoses

niuzaisheng/ScreenAgent — 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