RRepoGEO

REPOGEO REPORT · LITE

HazyResearch/ThunderKittens

Default branch main · commit 02e9acbd · scanned 6/28/2026, 7:02:57 AM

GitHub: 3,488 stars · 300 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 HazyResearch/ThunderKittens, 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
  • hightopics#1
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    cuda, deep-learning, gpu, kernels, optimization, pytorch, flashattention, ai-inference, ai-training
  • highhomepage#2
    Add a homepage URL to the repository

    Why:

    COPY-PASTE FIX
    [Insert official project homepage URL here]
  • mediumreadme#3
    Refine README opening to clarify competitive positioning

    Why:

    CURRENT
    # ThunderKittens

<div align="center" >
    <br/>
    <em>ThunderKittens: Tile primitives for speedy kernels</em><br/><br/>
</div>

**ThunderKittens** is a framework to make it easy to write fast deep learning kernels in CUDA.
    COPY-PASTE FIX
    # ThunderKittens

<div align="center" >
    <br/>
    <em>ThunderKittens: Tile primitives for speedy kernels for deep learning acceleration</em><br/><br/>
</div>

**ThunderKittens** is a high-performance framework for writing fast deep learning kernels in CUDA, offering a simpler and more extensible alternative to low-level CUDA programming or other kernel DSLs like Triton for NVIDIA GPUs.

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 HazyResearch/ThunderKittens
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
openai/triton
Recommended in 3 of 2 queries
COMPETITOR LEADERBOARD
  1. openai/triton · recommended 3×
  2. apache/tvm · recommended 2×
  3. NVIDIA CUDA · recommended 1×
  4. cuDNN · recommended 1×
  5. cuBLAS · recommended 1×
  • CATEGORY QUERY
    How to achieve maximum speed for deep learning kernels on graphics processing units?
    you: not recommended
    AI recommended (in order):
    1. NVIDIA CUDA
    2. cuDNN
    3. cuBLAS
    4. Triton (openai/triton)
    5. OpenAI Triton (openai/triton)
    6. TensorRT
    7. ROCm (ROCm-Developer-Tools/ROCm)
    8. MIOpen (ROCmSoftwarePlatform/MIOpen)
    9. rocBLAS (ROCmSoftwarePlatform/rocBLAS)
    10. Apache TVM (apache/tvm)
    11. JAX (google/jax)
    12. XLA

    AI recommended 12 alternatives but never named HazyResearch/ThunderKittens. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools simplify writing custom, highly optimized GPU compute kernels for AI applications?
    you: not recommended
    AI recommended (in order):
    1. CUDA C++
    2. OpenCL
    3. HIP (ROCm/HIP)
    4. SYCL
    5. Apache TVM (apache/tvm)
    6. OpenAI Triton (openai/triton)

    AI recommended 6 alternatives but never named HazyResearch/ThunderKittens. 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 HazyResearch/ThunderKittens?
    pass
    AI named HazyResearch/ThunderKittens explicitly

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

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

Subscribe to Pro for deep diagnoses

HazyResearch/ThunderKittens — 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