RRepoGEO

REPOGEO REPORT · LITE

keyvank/femtoGPT

Default branch main · commit 3976c47f · scanned 6/3/2026, 3:03:07 PM

GitHub: 934 stars · 68 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 keyvank/femtoGPT, 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
    Emphasize educational, from-scratch purpose in README's opening

    Why:

    CURRENT
    femtoGPT is a pure Rust implementation of a minimal Generative Pretrained Transformer.
    COPY-PASTE FIX
    femtoGPT is a pure Rust, from-scratch implementation of a minimal Generative Pretrained Transformer, designed for deep learning enthusiasts and students to understand LLMs at a fundamental level.
  • mediumtopics#2
    Add specific topics to highlight educational and architectural focus

    Why:

    CURRENT
    from-scratch, gpt, gpu, hacktoberfest, llm, machine-learning, neural-network, opencl, rust
    COPY-PASTE FIX
    from-scratch, gpt, gpu, hacktoberfest, llm, machine-learning, neural-network, opencl, rust, educational, learning, nanoGPT, transformer-architecture
  • lowreadme#3
    Add a 'Comparison' section to the README

    Why:

    COPY-PASTE FIX
    ## Comparison

femtoGPT aims to be an even more streamlined and accessible educational reference than projects like Andrej Karpathy's nanoGPT, focusing on extreme code simplicity, readability, and hackability. Unlike general-purpose deep learning frameworks (e.g., Burn, Candle), femtoGPT is not designed for production-scale applications but rather for fundamental understanding of the GPT architecture from scratch.

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 keyvank/femtoGPT
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
llm
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. llm · recommended 1×
  2. Burn · recommended 1×
  3. tch-rs · recommended 1×
  4. candle · recommended 1×
  5. dfdx · recommended 1×
  • CATEGORY QUERY
    Seeking a pure Rust implementation of a minimal GPT for deep learning and experimentation.
    you: not recommended
    AI recommended (in order):
    1. llm

    AI recommended 1 alternative but never named keyvank/femtoGPT. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How can I train and infer small transformer models on CPU and GPU using Rust?
    you: not recommended
    AI recommended (in order):
    1. Burn
    2. tch-rs
    3. candle
    4. dfdx
    5. ort

    AI recommended 5 alternatives but never named keyvank/femtoGPT. 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 keyvank/femtoGPT?
    pass
    AI named keyvank/femtoGPT explicitly

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

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

Subscribe to Pro for deep diagnoses

keyvank/femtoGPT — 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