RRepoGEO

REPOGEO REPORT · LITE

reworkd/tarsier

Default branch main · commit cc0888b1 · scanned 6/23/2026, 4:37:12 PM

GitHub: 1,764 stars · 124 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
40 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
2 pass · 0 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 reworkd/tarsier, 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 README's opening statement to clarify LLM-web interaction focus

    Why:

    CURRENT
    If you've tried using an LLM to automate web interactions, you've probably run into questions like:
    COPY-PASTE FIX
    Tarsier is a Python library providing vision utilities to enable large language models (LLMs) to visually understand and interact with web pages, transforming complex web content into actionable insights for AI agents.
  • hightopics#2
    Add more specific LLM-web interaction topics

    Why:

    CURRENT
    gpt4v, llms, ocr, playwright, pypi-package, python, selenium, webscraping
    COPY-PASTE FIX
    gpt4v, llms, ocr, playwright, pypi-package, python, selenium, webscraping, llm-agents, web-automation-llm, browser-llm-interface, ai-web-perception
  • mediumcomparison#3
    Add a 'Comparison to Alternatives' section

    Why:

    COPY-PASTE FIX
    ## Comparison to Alternatives

Unlike general web automation libraries like Playwright or Selenium, Tarsier is specifically designed to provide a structured, LLM-friendly interface for web browser interaction. While those tools offer low-level control, Tarsier abstracts away the complexities of visual perception and element mapping, delivering a concise, actionable format tailored for AI agents to understand and act upon web pages.

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 reworkd/tarsier
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Playwright
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Playwright · recommended 2×
  2. requests · recommended 2×
  3. OpenAI GPT-4V · recommended 1×
  4. Gemini 1.5 Pro · recommended 1×
  5. Claude 3 Opus · recommended 1×
  • CATEGORY QUERY
    How to enable large language models to visually understand and interact with web pages?
    you: not recommended
    AI recommended (in order):
    1. Playwright
    2. OpenAI GPT-4V
    3. Gemini 1.5 Pro
    4. Claude 3 Opus
    5. Puppeteer
    6. LLaVA (Large Language and Vision Assistant)
    7. Selenium WebDriver
    8. YOLO
    9. DETR
    10. GPT-3.5
    11. Llama 2
    12. Mistral
    13. Auto-GPT
    14. Adept AI's ACT-1
    15. LangChain
    16. requests
    17. BeautifulSoup

    AI recommended 17 alternatives but never named reworkd/tarsier. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Python library for giving LLMs perception of web page elements using browser automation?
    you: not recommended
    AI recommended (in order):
    1. Playwright
    2. Selenium
    3. Pyppeteer
    4. Beautiful Soup
    5. requests
    6. httpx
    7. Scrapy

    AI recommended 7 alternatives but never named reworkd/tarsier. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    pass

  • 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 reworkd/tarsier?
    pass
    AI named reworkd/tarsier explicitly

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

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

Subscribe to Pro for deep diagnoses

reworkd/tarsier — 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