RRepoGEO

REPOGEO REPORT · LITE

samuel-vitorino/lm.rs

Default branch main · commit 74665ab5 · scanned 5/14/2026, 7:03:42 AM

GitHub: 1,034 stars · 43 forks

AI VISIBILITY SCORE
28 /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
2 / 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 samuel-vitorino/lm.rs, 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
    Reposition the README's introductory text to emphasize functional capability

    Why:

    CURRENT
    Inspired by Karpathy's llama2.c and llm.c I decided to create the most minimal code (not so minimal atm) that can perform full inference on Language Models on the CPU without ML libraries. Previously only Google's Gemma 2 models were supported, but I decided to add support for the new Llama 3.2 models, and more recently the option to use images with PHI-3.5.
    COPY-PASTE FIX
    Inspired by Karpathy's `llama2.c` and `llm.c`, `lm.rs` provides a minimal, self-contained Rust implementation for full LLM inference on the CPU, without external ML libraries. It supports models like Gemma 2, Llama 3.2, and PHI-3.5 (including multimodal vision). While designed for clarity and direct CPU execution, it's actively being optimized for performance, with recent updates boosting batch processing for image encoding.
  • hightopics#2
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    llm, inference, rust, cpu, multimodal, language-models, machine-learning, edge-ai, phi-3-5, llama-3

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 samuel-vitorino/lm.rs
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
huggingface/candle
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. huggingface/candle · recommended 2×
  2. sonos/tract · recommended 2×
  3. huggingface/llm · recommended 1×
  4. huggingface/rust-bert · recommended 1×
  5. pykeio/ort · recommended 1×
  • CATEGORY QUERY
    Looking for a lightweight Rust library to perform local LLM inference without GPU.
    you: not recommended
    AI recommended (in order):
    1. llm crate (huggingface/llm)
    2. candle (huggingface/candle)
    3. rust-bert (huggingface/rust-bert)
    4. tract (sonos/tract)
    5. ort (pykeio/ort)

    AI recommended 5 alternatives but never named samuel-vitorino/lm.rs. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a Rust solution for multimodal LLM inference on edge devices.
    you: not recommended
    AI recommended (in order):
    1. ONNX Runtime
    2. OpenVINO
    3. Apache TVM
    4. candle (huggingface/candle)
    5. tract (sonos/tract)

    AI recommended 5 alternatives but never named samuel-vitorino/lm.rs. 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 samuel-vitorino/lm.rs?
    pass
    AI did not name samuel-vitorino/lm.rs — likely talking about a different project

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

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

Subscribe to Pro for deep diagnoses

samuel-vitorino/lm.rs — 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