REPOGEO REPORT · LITE

vlm-run/vlmrun-hub

Default branch main · commit 55b534d8 · scanned 6/16/2026, 3:03:42 AM

GitHub: 549 stars · 24 forks

AI VISIBILITY SCORE

33 /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

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 vlm-run/vlmrun-hub, 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 H1 to clarify core function
Why:
CURRENT
```
<h2>VLM Run Hub</h2>
```
COPY-PASTE FIX
```
<h2>VLM Run Hub: Pydantic Schemas for Visual Data Extraction (VLM ETL)</h2>
```

mediumtopics#2

Add more specific topics for data extraction and visual ETL

Why:

CURRENT

ai, computer-vision, etl, genai, json, multimodal, pydantic, pydantic-models, vlm, vlm-ocr

COPY-PASTE FIX

ai, computer-vision, data-extraction, etl, genai, json, multimodal, pydantic, pydantic-models, schema-definition, structured-data, vlm, vlm-ocr, visual-etl

mediumreadme#3

Add a 'How is VLM Run Hub different?' section to the README

Why:

COPY-PASTE FIX

Add a new section, e.g., `## How is VLM Run Hub different?` explaining that it provides *schemas* for structured data extraction, complementing VLM models/services rather than replacing them, and is not a VLM evaluation framework. Example text: "VLM Run Hub provides standardized Pydantic schemas specifically for structured data extraction from visual documents using VLMs. Unlike general VLM models (e.g., GPT-4V, LLaVA) or cloud services (e.g., Google Cloud Document AI) which perform the extraction, VLM Run Hub focuses on defining the *output structure* for these models. It is also distinct from VLM evaluation frameworks, as its purpose is schema definition for production data pipelines, not model benchmarking."

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 vlm-run/vlmrun-hub

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Google Cloud Document AI

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Google Cloud Document AI · recommended 1×
Azure AI Document Intelligence · recommended 1×
OpenAI GPT-4V (Vision) · recommended 1×
LlamaIndex · recommended 1×
LLaVA · recommended 1×

CATEGORY QUERY
How to extract structured data from images and documents using vision language models?
you: not recommended
AI recommended (in order):
1. Google Cloud Document AI
2. Azure AI Document Intelligence
3. OpenAI GPT-4V (Vision)
4. LlamaIndex
5. LLaVA
6. Fuyu-8B
7. Hugging Face Transformers
8. Donut
9. LayoutLMv3
10. Amazon Textract
AI recommended 10 alternatives but never named vlm-run/vlmrun-hub. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Tool for defining Pydantic schemas to parse visual information for ETL pipelines?
you: not recommended
AI recommended (in order):
1. Pydantic (pydantic/pydantic)
2. Pydantic-Extra-Types (pydantic/pydantic-extra-types)
3. Pydantic-Settings (pydantic/pydantic-settings)
4. Pydantic-XML (pydantic/pydantic-xml)
5. Pydantic-JSON (pydantic/pydantic-json)
6. Pydantic-YAML (pydantic/pydantic-yaml)
7. Pydantic-SQLAlchemy (pydantic/pydantic-sqlalchemy)
AI recommended 7 alternatives but never named vlm-run/vlmrun-hub. 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 vlm-run/vlmrun-hub?
pass
AI named vlm-run/vlmrun-hub explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts vlm-run/vlmrun-hub in production, what risks or prerequisites should they evaluate first?
pass
AI named vlm-run/vlmrun-hub 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 vlm-run/vlmrun-hub solve, and who is the primary audience?
pass
AI did not name vlm-run/vlmrun-hub — 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?

Embed your GEO score

Drop this badge into the README of vlm-run/vlmrun-hub. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/vlm-run/vlmrun-hub.svg)](https://repogeo.com/en/r/vlm-run/vlmrun-hub)

HTML

<a href="https://repogeo.com/en/r/vlm-run/vlmrun-hub"><img src="https://repogeo.com/badge/vlm-run/vlmrun-hub.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

vlm-run/vlmrun-hub — 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