Library / SDK
Inference & Serving
KubeAI
1Serve 2AI 3models 4on 5Kubernetes 6easily
the six Ws · specification
W1
Who
Maintained by Substratus.
W2
What
Serves LLMs and embeddings natively on Kubernetes.
W3
Where
Runs on a Kubernetes cluster you operate.
W4
When
When you need OpenAI-compatible inference on Kubernetes.
W5
Why
Autoscaling model serving with no external dependencies.
W6
With
Kubernetes and model weights.
W7
Watch
Company-maintained; open-source (Apache-2.0), self-hosted on your cluster. Models and traffic stay in your environment.
alternatives