RRepoGEO

REPOGEO REPORT · LITE

zkonduit/ezkl

Default branch main · commit e196b111 · scanned 5/26/2026, 2:52:01 AM

GitHub: 1,201 stars · 208 forks

AI VISIBILITY SCORE
87 /100
Healthy
Category recall
2 / 2
Avg rank #1.0 when recommended
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 zkonduit/ezkl, 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
  • highlicense#1
    Add a LICENSE file to the repository

    Why:

    CURRENT
    (no LICENSE file detected — the repo has no recognizable license)
    COPY-PASTE FIX
    Create a `LICENSE` file in the repository root with the chosen open-source license (e.g., MIT, Apache-2.0, GPL-3.0).
  • mediumreadme#2
    Strengthen the README's opening value proposition

    Why:

    CURRENT
    `ezkl` is a library and command-line tool for doing inference for deep learning models and other computational graphs in a zk-snark (ZKML).
    COPY-PASTE FIX
    After the 'Easy Zero-Knowledge Inference' tagline, add a sentence like: 'It provides a user-friendly, high-level toolchain for generating zero-knowledge proofs for *existing* ONNX-compatible machine learning models, enabling ML practitioners to leverage ZKP without deep cryptographic expertise.'
  • lowcomparison#3
    Add a 'Comparison with Alternatives' section to the README

    Why:

    COPY-PASTE FIX
    Add a new section to the README titled 'Comparison with Alternatives' or 'Why ezkl?' that outlines how `ezkl` differentiates itself from projects like ZKML by Modulus Labs, Orion, or Giza, particularly focusing on its ONNX compatibility and ease of use for ML practitioners.

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
2 / 2
100% of queries surface zkonduit/ezkl
Avg rank
#1.0
Lower is better. #1 = top recommendation.
Share of voice
13%
Of all named tools, what % are you?
Top rival
ZKML by Modulus Labs
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. ZKML by Modulus Labs · recommended 1×
  2. Orion by Ingonyama · recommended 1×
  3. ZK-GAN by Aleo · recommended 1×
  4. zk-SNARKs for Neural Networks (zk-NN) by Microsoft Research · recommended 1×
  5. Lattigo · recommended 1×
  • CATEGORY QUERY
    How to perform verifiable deep learning inference using zero-knowledge proofs for privacy?
    you: #1
    AI recommended (in order):
    1. EZKL ← you
    2. ZKML by Modulus Labs
    3. Orion by Ingonyama
    4. ZK-GAN by Aleo
    5. zk-SNARKs for Neural Networks (zk-NN) by Microsoft Research
    6. Lattigo
    7. OpenMined's PySyft
    Show full AI answer
  • CATEGORY QUERY
    What libraries allow running ONNX machine learning models inside a zero-knowledge snark?
    you: #1
    AI recommended (in order):
    1. ezkl ← you
    2. Modulus Labs
    3. Giza
    4. Orion
    5. Tensorflow Privacy
    6. Halo2
    7. PSE's ZK-SNARKs
    8. Cairo
    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 zkonduit/ezkl?
    pass
    AI named zkonduit/ezkl explicitly

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

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

Subscribe to Pro for deep diagnoses

zkonduit/ezkl — 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