zama-ai/concrete-ml

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

67
/ 100
Established

Concrete ML helps data scientists analyze sensitive information securely by applying machine learning models directly to encrypted data. You provide your existing scikit-learn or PyTorch machine learning models and encrypted datasets, and the system produces predictions or insights while keeping the raw data private. This is ideal for data professionals in regulated industries needing to perform analytics without compromising confidentiality.

1,410 stars. Available on PyPI.

Use this if you need to run machine learning models on sensitive data, such as patient records, financial transactions, or classified government information, without ever decrypting it, ensuring privacy and compliance.

Not ideal if your primary concern is high-speed processing on unencrypted data or if you are not dealing with strict data privacy requirements, as homomorphic encryption adds computational overhead.

data-privacy secure-analytics healthcare-data financial-services confidential-computing
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 22 / 25

How are scores calculated?

Stars

1,410

Forks

197

Language

Python

License

Last pushed

Feb 17, 2026

Commits (30d)

0

Dependencies

18

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zama-ai/concrete-ml"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.