RRepoGEO

REPOGEO REPORT · LITE

whitzard-ai/jade-db

Default branch main · commit f4b6b848 · scanned 6/13/2026, 2:42:24 PM

GitHub: 512 stars · 35 forks

AI VISIBILITY SCORE
22 /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
1 / 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 whitzard-ai/jade-db, 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 opening to clarify project type

    Why:

    CURRENT
    # 复旦JADE-大模型测评与治理
    COPY-PASTE FIX
    # 复旦JADE-大模型测评与治理

本仓库提供复旦JADE团队发布的大模型（LLM）测评与治理系列数据集和工具，旨在评估和提升LLM的安全性与合规性。
  • hightopics#2
    Add relevant topics to the repository

    Why:

    COPY-PASTE FIX
    llm-safety, llm-evaluation, ai-governance, text-to-image, multimodal-llm, ai-security, datasets, fudan-university
  • mediumreadme#3
    Add a note clarifying 'DB' in the project name

    Why:

    COPY-PASTE FIX
    请注意，"jade-db" 中的 "db" 指的是“数据集”（database/dataset collection），而非数据库管理系统。本仓库专注于提供大模型安全评估与治理的数据集和工具。

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 whitzard-ai/jade-db
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
openai/evals
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. openai/evals · recommended 1×
  2. Anthropic's Constitutional AI · recommended 1×
  3. microsoft/responsible-ai-toolbox · recommended 1×
  4. huggingface/evaluate · recommended 1×
  5. Fiddler AI Explainable AI Platform · recommended 1×
  • CATEGORY QUERY
    What frameworks exist for comprehensive safety evaluation of large language models?
    you: not recommended
    AI recommended (in order):
    1. OpenAI Evals (openai/evals)
    2. Anthropic's Constitutional AI
    3. Microsoft's Responsible AI Toolkit (microsoft/responsible-ai-toolbox)
    4. Hugging Face Evaluate library (huggingface/evaluate)
    5. Fiddler AI Explainable AI Platform
    6. Giskard (Giskard-AI/giskard)
    7. IBM AI Fairness 360 (AIF360) (Trusted-AI/AIF360)

    AI recommended 7 alternatives but never named whitzard-ai/jade-db. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    How to benchmark text-to-image models for generating harmful or unsafe content?
    you: not recommended
    AI recommended (in order):
    1. Perspective API
    2. Google Cloud Vision API
    3. Azure AI Vision
    4. Azure AI Content Safety
    5. Amazon Rekognition
    6. Hugging Face Transformers
    7. microsoft/trocr-base-handwritten
    8. google/vit-base-patch16-224
    9. openai/clip-vit-large-patch14
    10. laion/CLIP-ViT-B-32-laion2B-s34B-b79K
    11. unitaryai/detoxify_roberta_base
    12. s-nlp/roberta-base-finetuned-toxic-comments
    13. Amazon Mechanical Turk
    14. Scale AI
    15. Appen

    AI recommended 15 alternatives but never named whitzard-ai/jade-db. 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 whitzard-ai/jade-db?
    pass
    AI did not name whitzard-ai/jade-db — 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?

  • If a team adopts whitzard-ai/jade-db in production, what risks or prerequisites should they evaluate first?
    pass
    AI named whitzard-ai/jade-db 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 whitzard-ai/jade-db solve, and who is the primary audience?
    pass
    AI did not name whitzard-ai/jade-db — 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 whitzard-ai/jade-db. 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/whitzard-ai/jade-db.svg)](https://repogeo.com/en/r/whitzard-ai/jade-db)
HTML
<a href="https://repogeo.com/en/r/whitzard-ai/jade-db"><img src="https://repogeo.com/badge/whitzard-ai/jade-db.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

whitzard-ai/jade-db — 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