RRepoGEO

REPOGEO REPORT · LITE

mayocream/koharu

Default branch main · commit 271c43e0 · scanned 5/24/2026, 7:27:05 PM

GitHub: 4,460 stars · 239 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 mayocream/koharu, 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 unique identity in the README's opening

    Why:

    CURRENT
    <h1 align="center">Koharu</h1>

<p align="center">ML-powered manga translator, written in <b>Rust</b>.</p>
    COPY-PASTE FIX
    <h1 align="center">Koharu: ML-powered Manga Translator</h1>

<p align="center">The definitive <b>Rust</b>-based, local-first desktop application for automating manga translation.</p>
  • highabout#2
    Enhance the repository description for clarity and uniqueness

    Why:

    CURRENT
    ML-powered manga translator, written in Rust.
    COPY-PASTE FIX
    Koharu is a local-first, ML-powered desktop application for automating manga translation, built entirely in Rust with Tauri.
  • mediumreadme#3
    Integrate user-centric keywords into the README's introductory section

    Why:

    CURRENT
    Koharu introduces a local-first workflow for manga translation, utilizing the power of ML to automate the process. It combines the capabilities of object detection, OCR, inpainting, and LLMs to create a seamless translation experience.
    COPY-PASTE FIX
    Koharu introduces a local-first workflow for **AI-powered manga translation**, utilizing the power of ML to automate the process. It combines the capabilities of **automatic text detection**, **OCR for manga dialogue**, **inpainting for text removal**, and **LLMs for translation** to create a seamless **desktop translation experience**.

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 mayocream/koharu
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
OpenCV
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. OpenCV · recommended 2×
  2. Hugging Face Transformers · recommended 2×
  3. PaddleOCR · recommended 2×
  4. Manga Translator · recommended 1×
  5. Google Cloud Vision API · recommended 1×
  • CATEGORY QUERY
    How to automate manga translation using machine learning and computer vision?
    you: not recommended
    AI recommended (in order):
    1. Manga Translator
    2. Google Cloud Vision API
    3. Google Translate API
    4. OpenCV
    5. Tesseract OCR
    6. MarianMT
    7. Hugging Face Transformers
    8. DeepL API
    9. PaddleOCR
    10. NLLB-200
    11. LaMa
    12. GLIDE
    13. Adobe Photoshop
    14. Pillow (PIL)
    15. ImageMagick

    AI recommended 15 alternatives but never named mayocream/koharu. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a Rust-based desktop application for AI-powered image text translation.
    you: not recommended
    AI recommended (in order):
    1. Tauri
    2. Tesseract
    3. tesseract-sys
    4. tesseract-rs
    5. rust-bert
    6. candle
    7. Slint
    8. egui
    9. Druid
    10. Python
    11. C++
    12. pyo3
    13. OpenCV
    14. PaddleOCR
    15. EasyOCR
    16. Hugging Face Transformers
    17. PyTorch
    18. TensorFlow
    19. tract

    AI recommended 19 alternatives but never named mayocream/koharu. 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 mayocream/koharu?
    pass
    AI named mayocream/koharu explicitly

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

  • If a team adopts mayocream/koharu in production, what risks or prerequisites should they evaluate first?
    pass
    AI named mayocream/koharu 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 mayocream/koharu solve, and who is the primary audience?
    pass
    AI named mayocream/koharu 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 mayocream/koharu. 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/mayocream/koharu.svg)](https://repogeo.com/en/r/mayocream/koharu)
HTML
<a href="https://repogeo.com/en/r/mayocream/koharu"><img src="https://repogeo.com/badge/mayocream/koharu.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

mayocream/koharu — 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