gizatechxyz/LuminAIR
A zkML framework for ensuring the integrity of computational graphs using Circle STARK proofs
LuminAIR helps you prove that a complex machine learning calculation, like one used in financial models or medical diagnostics, ran exactly as it was supposed to. It takes your computational graph (the step-by-step logic of your ML model) and produces a cryptographic proof. This proof can then be quickly checked by others to confirm the calculation's integrity without needing to rerun the entire process. This is for developers building verifiable AI applications where trust and accuracy are critical.
No commits in the last 6 months.
Use this if you are a developer building machine learning applications where demonstrating the integrity and trustworthiness of computations is paramount, such as in regulated industries or decentralized systems.
Not ideal if you are solely looking for a general-purpose machine learning framework without the need for cryptographic verification of computational integrity.
Stars
55
Forks
24
Language
Rust
License
—
Category
Last pushed
Sep 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gizatechxyz/LuminAIR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ICME-Lab/jolt-atlas
Fast zkVM born at a16z Crypto substantially adapted by ICME Labs (NovaNet) for verifiable...
socathie/circomlib-ml
Circom Circuits Library for Machine Learning
mithril-security/blindai
Confidential AI deployment with secure enclaves :lock:
SpeyTech/certifiable-inference
Deterministic, bit-perfect AI inference for safety-critical systems
guruvamsi-policharla/zkpot
A prototype implementation of zero-knowledge proofs of training introduced in eprint:2023/1345