epfml/disco

DISCO is a code-free and installation-free browser platform that allows any non-technical user to collaboratively train machine learning models without sharing any private data.

55
/ 100
Established

DISCO helps non-technical users collaborate on building machine learning models using their own private datasets. You provide your local data and a starting model, and DISCO aggregates secure model updates from all participants without sharing raw data, resulting in a collaboratively trained, high-performing model. This is ideal for researchers, healthcare professionals, or businesses needing to pool insights from sensitive data.

182 stars.

Use this if you need to train a machine learning model using data from multiple sources but cannot share the private data directly due to privacy, security, or regulatory concerns.

Not ideal if you are a developer looking for an SDK or library to integrate into an existing codebase, or if all your data resides in one location and does not require collaborative training.

data-privacy healthcare-analytics financial-modeling market-research collaborative-research
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

182

Forks

31

Language

TypeScript

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/epfml/disco"

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