RRepoGEO

REPOGEO REPORT · LITE

karpathy/build-nanogpt

Default branch master · commit 6104ab1b · scanned 5/24/2026, 10:07:54 PM

GitHub: 5,028 stars · 812 forks

AI VISIBILITY SCORE
23 /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
2 / 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/build-nanogpt, 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
  • highlicense#1
    Add a LICENSE file to the repository

    Why:

    COPY-PASTE FIX
    Add a LICENSE file to the repository root, choosing an appropriate open-source license (e.g., MIT, Apache-2.0) that reflects your intentions for reuse.
  • mediumreadme#2
    Reposition the README's opening sentence to emphasize its educational guide nature

    Why:

    CURRENT
    This repo holds the from-scratch reproduction of nanoGPT.
    COPY-PASTE FIX
    This repository is a step-by-step educational guide and code reproduction for building nanoGPT from scratch, accompanied by a video lecture.

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/build-nanogpt
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
keras-team/keras
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. keras-team/keras · recommended 2×
  2. PyTorch · recommended 1×
  3. PyTorch Lightning · recommended 1×
  4. Hugging Face Transformers · recommended 1×
  5. TensorFlow · recommended 1×
  • CATEGORY QUERY
    How can I learn to build a foundational large language model from scratch?
    you: not recommended
    AI recommended (in order):
    1. PyTorch
    2. PyTorch Lightning
    3. Hugging Face Transformers
    4. TensorFlow
    5. Keras
    6. JAX
    7. Flax
    8. Haiku
    9. DeepSpeed
    10. Megatron-LM
    11. SentencePiece
    12. Hugging Face Tokenizers

    AI recommended 12 alternatives but never named karpathy/build-nanogpt. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a guide to implement transformer architecture for a basic generative text model.
    you: not recommended
    AI recommended (in order):
    1. Hugging Face Transformers (huggingface/transformers)
    2. PyTorch (pytorch/pytorch)
    3. TensorFlow (tensorflow/tensorflow)
    4. Keras (keras-team/keras)
    5. JAX (google/jax)
    6. Flax (google/flax)
    7. Haiku (deepmind/dm-haiku)
    8. Keras (keras-team/keras)

    AI recommended 8 alternatives but never named karpathy/build-nanogpt. 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/build-nanogpt?
    pass
    AI named karpathy/build-nanogpt 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/build-nanogpt in production, what risks or prerequisites should they evaluate first?
    pass
    AI named karpathy/build-nanogpt 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/build-nanogpt solve, and who is the primary audience?
    pass
    AI did not name karpathy/build-nanogpt — likely talking about a different project

    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/build-nanogpt. 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/build-nanogpt.svg)](https://repogeo.com/en/r/karpathy/build-nanogpt)
HTML
<a href="https://repogeo.com/en/r/karpathy/build-nanogpt"><img src="https://repogeo.com/badge/karpathy/build-nanogpt.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

karpathy/build-nanogpt — 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