RRepoGEO

REPOGEO REPORT · LITE

andrewnguonly/Lumos

Default branch main · commit 69ff12ed · scanned 5/16/2026, 2:52:17 PM

GitHub: 1,513 stars · 111 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 andrewnguonly/Lumos, 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
    Strengthen README's opening to clarify core purpose as a web co-pilot

    Why:

    CURRENT
    A RAG LLM co-pilot for browsing the web, powered by local LLMs.
    COPY-PASTE FIX
    Lumos is a powerful Chrome extension that functions as a RAG LLM co-pilot for browsing the web. It leverages local LLMs, like those powered by Ollama, to provide instant summarization of web content, answer questions about articles or forums, and assist with research directly in your browser, all without remote server dependencies.
  • mediumhomepage#2
    Add a homepage URL to the repository metadata

    Why:

    COPY-PASTE FIX
    Add a link to a dedicated project landing page, documentation, or a more detailed wiki page (e.g., `https://wiki.mutable.ai/andrewnguonly/Lumos` if that's the intended primary source).
  • mediumtopics#3
    Expand repository topics to include specific use cases and application type

    Why:

    CURRENT
    chrome-extension, langchain, langchain-js, llm, ollama, react, typescript, webpack
    COPY-PASTE FIX
    chrome-extension, langchain, langchain-js, llm, ollama, react, typescript, webpack, web-copilot, browser-ai, web-summarization, local-llm-agent, rag-chatbot

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 andrewnguonly/Lumos
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Plasmo
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Plasmo · recommended 1×
  2. Web Extension Boilerplate · recommended 1×
  3. WebLLM · recommended 1×
  4. Transformers.js · recommended 1×
  5. ONNX Runtime Web · recommended 1×
  • CATEGORY QUERY
    How can I create a browser extension for web summarization using local language models?
    you: not recommended
    AI recommended (in order):
    1. Plasmo
    2. Web Extension Boilerplate
    3. WebLLM
    4. Transformers.js
    5. ONNX Runtime Web

    AI recommended 5 alternatives but never named andrewnguonly/Lumos. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What are good tools for a private AI co-pilot to query web pages locally?
    you: not recommended
    AI recommended (in order):
    1. LocalAI
    2. Ollama
    3. Llama.cpp
    4. llama-cpp-python
    5. Haystack
    6. LangChain
    7. Playwright
    8. Beautiful Soup

    AI recommended 8 alternatives but never named andrewnguonly/Lumos. 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 andrewnguonly/Lumos?
    pass
    AI named andrewnguonly/Lumos explicitly

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

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

Subscribe to Pro for deep diagnoses

andrewnguonly/Lumos — 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