RRepoGEO

REPOGEO REPORT · LITE

ZJU-REAL/ClawGUI

Default branch master · commit d05090c5 · scanned 5/25/2026, 8:22:07 PM

GitHub: 1,266 stars · 48 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 ZJU-REAL/ClawGUI, 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
    Clarify the project's core domain in the README's opening paragraph

    Why:

    CURRENT
    <b>A full-stack framework for GUI agents, covering online RL training, standardized evaluation, and deployment.</b>
    COPY-PASTE FIX
    <b>ClawGUI is a full-stack framework for AI agents that interact with graphical user interfaces (GUIs) on devices like mobile phones and computers. It covers online RL training, standardized evaluation, and deployment, and is *not* related to robotic claw control.</b>
  • highhomepage#2
    Add the missing homepage URL to the 'About' section

    Why:

    COPY-PASTE FIX
    https://zju-real.github.io/ClawGUI-Page/
  • mediumabout#3
    Refine the 'About' description for clarity and keyword density

    Why:

    CURRENT
    Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.
    COPY-PASTE FIX
    ClawGUI: A unified framework for AI agents interacting with graphical user interfaces (GUIs). Features online RL training, standardized benchmarks, and real-device deployment for GUI agents.

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 ZJU-REAL/ClawGUI
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Stable Baselines3
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Stable Baselines3 · recommended 2×
  2. OpenAI Gym · recommended 1×
  3. OpenCV · recommended 1×
  4. Pillow · recommended 1×
  5. Tesseract OCR · recommended 1×
  • CATEGORY QUERY
    How to build and deploy AI agents that interact with graphical user interfaces on real devices?
    you: not recommended
    AI recommended (in order):
    1. OpenAI Gym
    2. OpenCV
    3. Pillow
    4. Tesseract OCR
    5. Google Cloud Vision API
    6. Stable Baselines3
    7. Ray RLlib
    8. Appium
    9. Selenium WebDriver
    10. PyAutoGUI
    11. AutoIt
    12. AppleScript
    13. WinAppDriver
    14. UI Automation Framework
    15. PyTorch
    16. TensorFlow
    17. Microsoft Playwright
    18. SikuliX
    19. Azure Cognitive Services
    20. Amazon Rekognition
    21. YOLOv8
    22. Mask R-CNN

    AI recommended 22 alternatives but never named ZJU-REAL/ClawGUI. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What frameworks exist for online reinforcement learning and standardized evaluation of GUI-based AI agents?
    you: not recommended
    AI recommended (in order):
    1. MiniWoB++
    2. Playwright
    3. Selenium
    4. Gymnasium
    5. RLlib
    6. Stable Baselines3
    7. AutoGym

    AI recommended 7 alternatives but never named ZJU-REAL/ClawGUI. 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 ZJU-REAL/ClawGUI?
    pass
    AI named ZJU-REAL/ClawGUI explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts ZJU-REAL/ClawGUI in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ZJU-REAL/ClawGUI 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 ZJU-REAL/ClawGUI solve, and who is the primary audience?
    pass
    AI named ZJU-REAL/ClawGUI 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 ZJU-REAL/ClawGUI. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/ZJU-REAL/ClawGUI.svg)](https://repogeo.com/en/r/ZJU-REAL/ClawGUI)
HTML
<a href="https://repogeo.com/en/r/ZJU-REAL/ClawGUI"><img src="https://repogeo.com/badge/ZJU-REAL/ClawGUI.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ZJU-REAL/ClawGUI — 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