RRepoGEO

REPOGEO REPORT · LITE

karpathy/reader3

Default branch master · commit 64960f99 · scanned 5/22/2026, 6:33:08 AM

GitHub: 3,645 stars · 459 forks

Scan history for this repo

Score trend below includes all ready runs (older left, newer right; scroll horizontally if needed). The table is collapsed by default—expand for newest-first rows, 10 per page.

Score trend (left → right: older → newer)

2 ready scans. Expand the table below for newest-first rows (10 per page, paginated).

AI VISIBILITY SCORE
30 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 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 karpathy/reader3, 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

2 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 emphasize LLM integration

    Why:

    CURRENT
    A lightweight, self-hosted EPUB reader that lets you read through EPUB books one chapter at a time. This makes it very easy to copy paste the contents of a chapter to an LLM, to read along.
    COPY-PASTE FIX
    A lightweight, self-hosted EPUB reader designed for seamless interaction with Large Language Models (LLMs), allowing you to easily read books chapter-by-chapter and copy-paste content for AI analysis or collaborative reading.
  • mediumlicense#2
    Add an MIT LICENSE file to the repository root

    Why:

    COPY-PASTE FIX
    Create a file named `LICENSE` in the repository root with the standard MIT License text.

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 karpathy/reader3
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Calibre
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Calibre · recommended 2×
  2. futurepress/epub.js · recommended 2×
  3. abetlen/llama-cpp-python · recommended 1×
  4. ollama/ollama · recommended 1×
  5. aerkalov/epub_parser · recommended 1×
  • CATEGORY QUERY
    How to easily integrate an EPUB book reader with a local LLM for collaborative reading?
    you: not recommended
    AI recommended (in order):
    1. Calibre
    2. llama-cpp-python (abetlen/llama-cpp-python)
    3. ollama (ollama/ollama)
    4. epub_parser (aerkalov/epub_parser)
    5. lxml
    6. Flask (pallets/flask)
    7. Django (django/django)
    8. FastAPI (tiangolo/fastapi)
    9. Electron (electron/electron)
    10. epub.js (futurepress/epub.js)
    11. readium-js (readium/readium-js)
    12. Node.js (nodejs/node)
    13. Jupyter Notebook/Lab
    14. ipywidgets (jupyter-widgets/ipywidgets)
    15. JupyterHub (jupyterhub/jupyterhub)
    16. Streamlit (streamlit/streamlit)
    17. Gradio (gradio-app/gradio)
    18. React (facebook/react)
    19. Vue (vuejs/core)
    20. Angular (angular/angular)
    21. Express (expressjs/express)
    22. NestJS (nestjs/nest)
    23. Socket.IO (socketio/socket.io)
    24. PostgreSQL
    25. MongoDB (mongodb/mongo)
    26. Redis (redis/redis)

    AI recommended 26 alternatives but never named karpathy/reader3. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a simple self-hosted EPUB viewer to extract chapter text for AI analysis.
    you: not recommended
    AI recommended (in order):
    1. Calibre
    2. EPUB.js (futurepress/epub.js)
    3. Readium Web (readium/readium-js-viewer)
    4. Sigil (Sigil-Ebook/Sigil)
    5. Pandoc (jgm/pandoc)

    AI recommended 5 alternatives but never named karpathy/reader3. This is the gap to close.

    Show full AI answer

Objective checks

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

  • Metadata completeness
    fail

    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 karpathy/reader3?
    pass
    AI named karpathy/reader3 explicitly

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

  • If a team adopts karpathy/reader3 in production, what risks or prerequisites should they evaluate first?
    pass
    AI named karpathy/reader3 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 karpathy/reader3 solve, and who is the primary audience?
    pass
    AI named karpathy/reader3 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 karpathy/reader3. 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/karpathy/reader3.svg)](https://repogeo.com/en/r/karpathy/reader3)
HTML
<a href="https://repogeo.com/en/r/karpathy/reader3"><img src="https://repogeo.com/badge/karpathy/reader3.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

karpathy/reader3 — 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