RRepoGEO

REPOGEO REPORT · LITE

ngxson/smolvlm-realtime-webcam

Default branch main · commit 37b62fc3 · scanned 6/22/2026, 11:08:41 AM

GitHub: 5,559 stars · 898 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 ngxson/smolvlm-realtime-webcam, 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 README's opening paragraph to highlight client-side, real-time VLM

    Why:

    CURRENT
    # SmolVLM real-time camera demo

This repository is a simple demo for how to use llama.cpp server with SmolVLM 500M to get real-time object detection
    COPY-PASTE FIX
    # SmolVLM Real-time Webcam Demo: Client-Side Vision-Language Model in Your Browser

This repository showcases a unique real-time object detection and visual understanding demo, running a SmolVLM 500M model via `llama.cpp` server for entirely client-side webcam analysis directly in a web browser. It's designed for developers and researchers exploring lightweight, local VLM applications without needing a backend server or cloud API.
  • mediumreadme#2
    Clarify the project's license in the README

    Why:

    COPY-PASTE FIX
    ## License

This project includes a LICENSE file. Please refer to it for specific terms and conditions. It is not a standard SPDX template and may contain custom or compound licensing terms.

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 ngxson/smolvlm-realtime-webcam
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
OpenCV
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. OpenCV · recommended 1×
  2. ultralytics/ultralytics · recommended 1×
  3. MediaPipe (Google) · recommended 1×
  4. PyTorch · recommended 1×
  5. torchvision · recommended 1×
  • CATEGORY QUERY
    How to implement real-time object detection from a webcam using a local vision model?
    you: not recommended
    AI recommended (in order):
    1. OpenCV
    2. YOLOv8 (Ultralytics) (ultralytics/ultralytics)
    3. MediaPipe (Google)
    4. PyTorch
    5. torchvision
    6. TensorFlow
    7. TensorFlow Lite
    8. Darknet

    AI recommended 8 alternatives but never named ngxson/smolvlm-realtime-webcam. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are options for integrating a lightweight visual language model with a web frontend for live video?
    you: not recommended
    AI recommended (in order):
    1. TensorFlow.js
    2. MediaPipe
    3. ONNX Runtime Web
    4. WebNN API
    5. OpenCV.js
    6. WebAssembly (Wasm)

    AI recommended 6 alternatives but never named ngxson/smolvlm-realtime-webcam. 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 ngxson/smolvlm-realtime-webcam?
    pass
    AI named ngxson/smolvlm-realtime-webcam explicitly

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

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

Subscribe to Pro for deep diagnoses

ngxson/smolvlm-realtime-webcam — 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