RRepoGEO

REPOGEO REPORT · LITE

cvlab-columbia/viper

Default branch main · commit 09fe3465 · scanned 5/23/2026, 7:03:07 PM

GitHub: 1,713 stars · 130 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 cvlab-columbia/viper, 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 the README's first paragraph to clarify its function as a framework

    Why:

    CURRENT
    This is the code for the paper ViperGPT: Visual Inference via Python Execution for Reasoning by Dídac Surís*, Sachit Menon* and Carl Vondrick.
    COPY-PASTE FIX
    ViperGPT is a research framework that enables visual reasoning tasks by generating and executing Python code, as presented in our paper "ViperGPT: Visual Inference via Python Execution for Reasoning" by Dídac Surís*, Sachit Menon* and Carl Vondrick.
  • mediumlicense#2
    Add a 'License' section to the README to clarify the existing license

    Why:

    COPY-PASTE FIX
    ## License
This project is licensed under the terms detailed in the LICENSE file. Please refer to the LICENSE file for full terms and conditions.

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 cvlab-columbia/viper
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Code Interpreter
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Code Interpreter · recommended 2×
  2. CLIP · recommended 2×
  3. Azure OpenAI Service · recommended 2×
  4. OpenAI GPT-4 · recommended 1×
  5. YOLOv8 · recommended 1×
  • CATEGORY QUERY
    How to perform visual reasoning tasks by generating and executing Python code?
    you: not recommended
    AI recommended (in order):
    1. OpenAI GPT-4
    2. Code Interpreter
    3. YOLOv8
    4. Detectron2
    5. CLIP
    6. Pillow
    7. OpenCV
    8. Google Gemini
    9. Microsoft Azure AI Services
    10. Azure AI Vision
    11. Azure OpenAI Service
    12. Jupyter Notebook
    13. Flask
    14. Pandas
    15. Hugging Face Transformers
    16. BLIP-2
    17. LLaVA
    18. Llama 3
    19. Mixtral
    20. CodeLlama
    21. LangChain
    22. LlamaIndex
    23. Anthropic Claude

    AI recommended 23 alternatives but never named cvlab-columbia/viper. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Seeking a framework for visual inference using large language models and dynamic code execution.
    you: not recommended
    AI recommended (in order):
    1. LangChain (langchain-ai/langchain)
    2. OpenAI's GPT-4V
    3. Code Interpreter
    4. Google's Gemini Pro Vision
    5. LlamaIndex (run-llama/llama_index)
    6. Microsoft Semantic Kernel (microsoft/semantic-kernel)
    7. Azure OpenAI Service
    8. Hugging Face Transformers (huggingface/transformers)
    9. ViT
    10. DETR
    11. CLIP
    12. Llama 2
    13. Mistral
    14. Google Vertex AI
    15. Codey APIs

    AI recommended 15 alternatives but never named cvlab-columbia/viper. 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 cvlab-columbia/viper?
    pass
    AI named cvlab-columbia/viper explicitly

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

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

Subscribe to Pro for deep diagnoses

cvlab-columbia/viper — 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