RRepoGEO

REPOGEO REPORT · LITE

KellerJordan/Muon

Default branch master · commit 6399c658 · scanned 5/24/2026, 12:22:52 AM

GitHub: 2,613 stars · 120 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
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 KellerJordan/Muon, 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
    Reinforce domain and framework in README's opening

    Why:

    CURRENT
    # Muon: An optimizer for the hidden layers of neural networks
    COPY-PASTE FIX
    # Muon: A PyTorch Optimizer for Hidden Layers in Neural Networks
  • mediumhomepage#2
    Add a homepage URL to the repository

    Why:

    COPY-PASTE FIX
    https://www.lesswrong.com/posts/2p222222222222222/muon-an-optimizer-for-the-hidden-layers-of-neural-networks

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 KellerJordan/Muon
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Adam
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Adam · recommended 1×
  2. SGD with Momentum · recommended 1×
  3. RMSProp · recommended 1×
  4. Adagrad · recommended 1×
  5. Nesterov Accelerated Gradient · recommended 1×
  • CATEGORY QUERY
    How to improve neural network training performance by optimizing hidden layer weights?
    you: not recommended
    AI recommended (in order):
    1. Adam
    2. SGD with Momentum
    3. RMSProp
    4. Adagrad
    5. Nesterov Accelerated Gradient
    6. Nadam
    7. L-BFGS
    8. Cosine Annealing
    9. ReduceLROnPlateau
    10. OneCycleLR

    AI recommended 10 alternatives but never named KellerJordan/Muon. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking an advanced optimizer to accelerate convergence and stability for deep neural network hidden layers.
    you: not recommended
    AI recommended (in order):
    1. AdamW
    2. RAdam (Rectified Adam)
    3. Lookahead
    4. AdaBelief
    5. LAMB (Layer-wise Adaptive Moments for Batching)
    6. Lion (EvoLved Sign Momentum)

    AI recommended 6 alternatives but never named KellerJordan/Muon. 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 KellerJordan/Muon?
    pass
    AI named KellerJordan/Muon explicitly

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

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

Subscribe to Pro for deep diagnoses

KellerJordan/Muon — 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