RRepoGEO

REPOGEO REPORT · LITE

code-kern-ai/refinery

Default branch main · commit 7972dc98 · scanned 5/27/2026, 1:06:48 AM

GitHub: 1,471 stars · 73 forks

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 code-kern-ai/refinery, 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 highlight data-centric AI platform and active learning

    Why:

    CURRENT
    The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.
    COPY-PASTE FIX
    Refinery is an open-source, data-centric AI platform for natural language processing, enabling data scientists to scale, assess, and maintain training data. It provides an integrated approach with first-class active learning and weak supervision mechanisms to efficiently curate, label, and improve NLP datasets, treating training data like a software artifact.
  • mediumtopics#2
    Add more specific data-centric AI and platform-related topics

    Why:

    CURRENT
    active-learning, annotations, artificial-intelligence, data-centric-ai, data-labeling, data-science, deep-learning, human-in-the-loop, labeling, labeling-tool, machine-learning, natural-language-processing, neural-search, nlp, python, spacy, supervised-learning, text-annotation, text-classification, transformers
    COPY-PASTE FIX
    active-learning, annotations, artificial-intelligence, data-centric-ai, data-labeling, data-science, deep-learning, human-in-the-loop, labeling, labeling-tool, machine-learning, natural-language-processing, neural-search, nlp, python, spacy, supervised-learning, text-annotation, text-classification, transformers, weak-supervision, data-curation, nlp-platform, mlops-data
  • lowabout#3
    Refine description to emphasize "platform" and "integrated" aspects

    Why:

    CURRENT
    The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.
    COPY-PASTE FIX
    An open-source data-centric AI platform for natural language processing, enabling data scientists to scale, assess, and maintain training data. Treat training data like a software artifact.

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 code-kern-ai/refinery
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Prodigy
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Prodigy · recommended 2×
  2. argilla-io/argilla · recommended 1×
  3. snorkel-team/snorkel · recommended 1×
  4. heartexlabs/label-studio · recommended 1×
  5. cleanlab/cleanlab · recommended 1×
  • CATEGORY QUERY
    How to effectively manage and improve natural language processing training datasets for machine learning?
    you: not recommended
    AI recommended (in order):
    1. Argilla (argilla-io/argilla)
    2. Snorkel (snorkel-team/snorkel)
    3. Prodigy
    4. Label Studio (heartexlabs/label-studio)
    5. Cleanlab (cleanlab/cleanlab)
    6. Weights & Biases (W&B)
    7. Data Version Control (DVC) (iterative/dvc)

    AI recommended 7 alternatives but never named code-kern-ai/refinery. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What open-source tools facilitate data labeling and active learning for NLP model development?
    you: not recommended
    AI recommended (in order):
    1. Prodigy
    2. Argilla
    3. Doccano
    4. LightTag
    5. Label Studio
    6. ActiveLoop
    7. Sklearn-active-learning

    AI recommended 7 alternatives but never named code-kern-ai/refinery. 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 code-kern-ai/refinery?
    pass
    AI named code-kern-ai/refinery explicitly

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

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

Subscribe to Pro for deep diagnoses

code-kern-ai/refinery — 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