REPOGEO REPORT · LITE

inference-labs-inc/JSTprove

Default branch main · commit 7c3cbbee · scanned 6/8/2026, 7:22:19 PM

GitHub: 970 stars · 14 forks

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 inference-labs-inc/JSTprove, 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 the README's opening to clarify JSTprove's purpose

Why:

CURRENT

```
  888888  .d8888b. 88888888888
    "88b d88P  Y88b    888
     888 Y88b.         888
     888  "Y888b.      888  88888b.  888d888 .d88b.  888  888  .d88b.
     888     "Y88b.    888  888 "88b 888P"  d88""88b 888  888 d8P  Y8b
     888       "888    888  888  888 888    888  888 Y88  88P 88888888
     88P Y88b  d88P    888  888 d88P 888    Y88..88P  Y8bd8P  Y8b.
     888  "Y8888P"     888  88888P"  888     "Y88P"    Y88P    "Y8888
   .d88P                    888
 .d88P"                     888
888P"                       888
```
# JSTprove: Community Edition

[](https://github.com/inference-labs-inc/JSTprove)
[](https://t.me/inference_labs)
[](https://x.com/inference_labs)
[](https://inferencelabs.com)
[](https://doi.org/10.48550/arXiv.2510.21024)

Zero-knowledge proofs of ML inference on **ONNX** models — powered by Polyhedra Network’s **Expander** (GKR/sum-check prover) and **Expander Compiler Collection (ECC)**.

COPY-PASTE FIX

# JSTprove: Community Edition

JSTprove is a framework for generating zero-knowledge proofs of machine learning inference on **ONNX** models. It is *not* a tool for JavaScript program verification. Powered by Polyhedra Network’s **Expander** (GKR/sum-check prover) and **Expander Compiler Collection (ECC)**, JSTprove enables fast, verifiable AI.

[](https://github.com/inference-labs-inc/JSTprove)
[](https://t.me/inference_labs)
[](https://x.com/inference_labs)
[](https://inferencelabs.com)
[](https://doi.org/10.48550/arXiv.2510.21024)

mediumtopics#2
Add more specific topics to improve category visibility
Why:
CURRENT
```
zkml
```
COPY-PASTE FIX
```
zkml, zero-knowledge-proofs, machine-learning, onnx, verifiable-ai, ai-inference, cryptography
```
lowhomepage#3
Add the project homepage to the About section
Why:
COPY-PASTE FIX
```
https://inferencelabs.com
```

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 inference-labs-inc/JSTprove

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

EZKL

Recommended in 2 of 2 queries

COMPETITOR LEADERBOARD

EZKL · recommended 2×
Orion · recommended 2×
ZKML by Modulus Labs · recommended 1×
RISC Zero · recommended 1×
SP1 Prover · recommended 1×

CATEGORY QUERY
How can I verify machine learning model inference using zero-knowledge proofs?
you: not recommended
AI recommended (in order):
1. EZKL
2. ZKML by Modulus Labs
3. Orion
4. RISC Zero
5. SP1 Prover
6. Halo2
7. Gnark
AI recommended 7 alternatives but never named inference-labs-inc/JSTprove. This is the gap to close.
Show full AI answer
CATEGORY QUERY
What tools exist for generating zero-knowledge proofs from ONNX neural network models?
you: not recommended
AI recommended (in order):
1. EZKL
2. Modulus Labs
3. Orion
4. Zator
5. halo2
6. arkworks
7. bellman
8. TensorFlow Privacy
9. PyTorch Privacy
AI recommended 9 alternatives but never named inference-labs-inc/JSTprove. 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 inference-labs-inc/JSTprove?
pass
AI named inference-labs-inc/JSTprove explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts inference-labs-inc/JSTprove in production, what risks or prerequisites should they evaluate first?
pass
AI named inference-labs-inc/JSTprove 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 inference-labs-inc/JSTprove solve, and who is the primary audience?
pass
AI named inference-labs-inc/JSTprove 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 inference-labs-inc/JSTprove. 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/inference-labs-inc/JSTprove.svg)](https://repogeo.com/en/r/inference-labs-inc/JSTprove)

HTML

<a href="https://repogeo.com/en/r/inference-labs-inc/JSTprove"><img src="https://repogeo.com/badge/inference-labs-inc/JSTprove.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

inference-labs-inc/JSTprove — 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