RRepoGEO

REPOGEO REPORT · LITE

andrewkchan/yalm

Default branch main · commit 6cd1ef6e · scanned 6/8/2026, 11:38:22 AM

GitHub: 585 stars · 62 forks

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 andrewkchan/yalm, 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 the README's opening sentence to clarify project identity

    Why:

    CURRENT
    yalm (Yet Another Language Model) is an LLM inference implementation in C++/CUDA, using no libraries except to load and save frozen LLM weights.
    COPY-PASTE FIX
    yalm (Yet Another Language Model) is a **C++/CUDA LLM inference engine** with **zero external library dependencies** (beyond I/O), intended as an **educational exercise** in performance engineering and LLM inference implementation. It is *not* a programming language or compiler.
  • highlicense#2
    Add a LICENSE file to the repository

    Why:

    COPY-PASTE FIX
    Create a `LICENSE` file in the repository root with your chosen open-source license (e.g., MIT, Apache-2.0, GPL-3.0).
  • mediumhomepage#3
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    Set the repository's homepage URL to `https://andrewkchan.dev/posts/llm-inference-from-scratch/` (or the most relevant project page).

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 andrewkchan/yalm
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
ONNX Runtime
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. ONNX Runtime · recommended 2×
  2. NVIDIA TensorRT · recommended 1×
  3. OpenVINO · recommended 1×
  4. Apache TVM · recommended 1×
  5. CUDA · recommended 1×
  • CATEGORY QUERY
    How can I build a performant large language model inference engine using C++ and CUDA?
    you: not recommended
    AI recommended (in order):
    1. NVIDIA TensorRT
    2. OpenVINO
    3. ONNX Runtime
    4. Apache TVM
    5. CUDA
    6. cuBLAS
    7. cuDNN
    8. LibTorch

    AI recommended 8 alternatives but never named andrewkchan/yalm. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for C++/CUDA LLM inference implementations focusing on minimal dependencies and performance insights.
    you: not recommended
    AI recommended (in order):
    1. TensorRT-LLM
    2. llama.cpp
    3. ONNX Runtime
    4. DeepSpeed-MII
    5. FasterTransformer

    AI recommended 5 alternatives but never named andrewkchan/yalm. 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 andrewkchan/yalm?
    pass
    AI named andrewkchan/yalm explicitly

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

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

Subscribe to Pro for deep diagnoses

andrewkchan/yalm — 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