RRepoGEO

REPOGEO REPORT · LITE

McGill-NLP/webllama

Default branch main · commit 696a7c36 · scanned 5/27/2026, 4:27:05 AM

GitHub: 1,404 stars · 103 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 McGill-NLP/webllama, 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
  • hightopics#1
    Add specific topics to the repository

    Why:

    COPY-PASTE FIX
    llama-3, web-agents, llm-agents, web-browsing, conversational-ai, nlp, deep-learning
  • highreadme#2
    Reposition the 'About the project' opening to emphasize Llama-3 agents

    Why:

    CURRENT
    The goal of our project is to build effective human-centric agents for browsing the web.
    COPY-PASTE FIX
    WebLlama is a project dedicated to building powerful Llama-3 agents for human-centric web browsing, equipping users with intelligent assistants.
  • mediumreadme#3
    Clarify WebLlama's relationship with web automation tools in the Deployment section

    Why:

    CURRENT
    We want to make it easy to integrate Llama models with existing deployment platforms, including Playwright, Selenium, and Brows
    COPY-PASTE FIX
    WebLlama provides a framework for Llama-3 agents, designed to easily integrate with existing web automation platforms like Playwright and Selenium, rather than replacing them.

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 McGill-NLP/webllama
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Playwright
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Playwright · recommended 1×
  2. Python · recommended 1×
  3. LangChain · recommended 1×
  4. Puppeteer · recommended 1×
  5. Node.js · recommended 1×
  • CATEGORY QUERY
    How can I build an AI agent to autonomously browse websites and follow instructions?
    you: not recommended
    AI recommended (in order):
    1. Playwright
    2. Python
    3. LangChain
    4. Puppeteer
    5. Node.js
    6. LangChain.js
    7. Selenium WebDriver
    8. OpenAI's GPT-4
    9. Anthropic's Claude
    10. Google's Gemini
    11. AutoGPT
    12. BabyAGI
    13. BrowserGPT
    14. Agent-Browser
    15. GPT-4
    16. Claude 3 Opus
    17. Gemini 1.5 Pro

    AI recommended 17 alternatives but never named McGill-NLP/webllama. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for tools to create conversational AI assistants for web navigation tasks.
    you: not recommended
    AI recommended (in order):
    1. Voiceflow
    2. Rasa (RasaHQ/rasa)
    3. Dialogflow
    4. Botpress (botpress/botpress)
    5. Microsoft Bot Framework Composer (microsoft/BotFramework-Composer)
    6. Teneo

    AI recommended 6 alternatives but never named McGill-NLP/webllama. 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 McGill-NLP/webllama?
    pass
    AI named McGill-NLP/webllama explicitly

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

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

Subscribe to Pro for deep diagnoses

McGill-NLP/webllama — 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