cortexlabs/cortex
Production infrastructure for machine learning at scale
This infrastructure helps machine learning engineers and MLOps teams deploy, manage, and scale their machine learning models in a production environment. It takes trained models and configurations, then makes them available as real-time APIs, asynchronous processors, or batch jobs, handling the underlying scaling and resource management on AWS. This is for teams who need to move their ML models from development to a robust, scalable, and observable production system.
8,027 stars. No commits in the last 6 months.
Use this if you are an MLOps engineer or machine learning practitioner needing to deploy trained models reliably and scalably on AWS, whether for real-time predictions, asynchronous processing, or batch jobs.
Not ideal if you are looking for a platform that is actively maintained by its original authors or if you need to deploy machine learning models outside of AWS.
Stars
8,027
Forks
598
Language
Go
License
Apache-2.0
Category
Last pushed
Jun 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mlops/cortexlabs/cortex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.