About Cortex
An open-source platform for deploying, scaling, and managing machine learning APIs and inference workloads on cloud infrastructure.
Key Features
- Declarative deployments — define and deploy model APIs and inference services via configuration.
- Autoscaling & multi-cloud support — support for scaling and running on multiple cloud providers.
- Developer-focused ergonomics — interfaces and tooling to bridge data science and production needs.
- Community-driven releases — open-source project with release notes and community docs.
Use Cases & Best For
Teams that want an open-source, declarative approach to serving ML APIs on cloud infrastructure.
Developers needing multi-cloud deployment and autoscaling for inference services.
About MLOps & Monitoring
Model operations and lifecycle management