RRepoGEO

REPOGEO REPORT · LITE

ashvardanian/NumKong

Default branch main · commit 48cbd21d · scanned 5/14/2026, 11:58:34 PM

GitHub: 1,810 stars · 119 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 ashvardanian/NumKong, 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
    Reposition README's opening to highlight overflow prevention

    Why:

    CURRENT
    Portable mixed-precision math, linear-algebra, & retrieval library with 2'000+ SIMD kernels for x86, Arm, RISC-V, LoongArch, Power, & WebAssembly...
    COPY-PASTE FIX
    NumKong is a portable mixed-precision math, linear-algebra, & retrieval library designed to prevent silent overflow in SIMD-accelerated operations. It offers 2'000+ kernels for x86, Arm, RISC-V, LoongArch, Power, & WebAssembly...
  • mediumtopics#2
    Add specific technical topics to improve categorization

    Why:

    CURRENT
    arm-neon, assembly, blas, cpp, golang, information-retrieval, javascript, matrix-multiplication, metrics, numpy, rust, scipy, simd, swift, tensor, vector-search
    COPY-PASTE FIX
    arm-neon, assembly, blas, cpp, golang, information-retrieval, javascript, matrix-multiplication, metrics, mixed-precision, numerical-stability, numpy, rust, scipy, simd, swift, tensor, vector-search, x86-simd, risc-v
  • lowreadme#3
    Enhance comparison section to emphasize unique advantages over generic BLAS

    Why:

    COPY-PASTE FIX
    Unlike traditional BLAS libraries that often operate in fixed precision, NumKong's mixed-precision approach actively prevents silent overflow, ensuring numerical stability across a wider range of inputs, as demonstrated by its superior error rates and performance in the table below.

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 ashvardanian/NumKong
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Intel MKL
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Intel MKL · recommended 1×
  2. OpenMathLib/OpenBLAS · recommended 1×
  3. eigenteam/eigen-git-mirror · recommended 1×
  4. numpy/numpy · recommended 1×
  5. CUDA · recommended 1×
  • CATEGORY QUERY
    How to prevent overflow in SIMD-accelerated dot products with mixed-precision numeric types?
    you: not recommended
    AI recommended (in order):
    1. Intel MKL
    2. OpenBLAS (OpenMathLib/OpenBLAS)
    3. Eigen (eigenteam/eigen-git-mirror)
    4. NumPy (numpy/numpy)
    5. CUDA

    AI recommended 5 alternatives but never named ashvardanian/NumKong. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a portable, high-performance linear algebra library with SIMD for multiple languages.
    you: not recommended
    AI recommended (in order):
    1. Intel oneAPI Math Kernel Library (oneMKL)
    2. OpenBLAS
    3. BLIS (Basic Linear Algebra Subprograms)
    4. Eigen
    5. Arm Performance Libraries
    6. cuBLAS
    7. rocBLAS

    AI recommended 7 alternatives but never named ashvardanian/NumKong. 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 ashvardanian/NumKong?
    pass
    AI named ashvardanian/NumKong explicitly

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

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

Subscribe to Pro for deep diagnoses

ashvardanian/NumKong — 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