"The Skynet Funding Bill is passed. The system goes on-line August 4th, 1997. Human decisions are removed from strategic defense. Skynet begins to learn at a geometric rate.", you might remember this quote from the Terminator 2 movie. And while we all thought that this is just a movie, it turns out that we are not that far away from this scenario. Ok, maybe not building an AI that will destroy humanity, but using an AI that will help us to interact with Kubernetes clusters. This talk will show you how LocalAI, an open-source project and an alternative to OpenAI, can help us "Skynet" our Kubernetes clusters by running LLMs models locally. This ensures that no confidential data is sent to the cloud maintaining a compliant and secure environment in highly regulated environments. An example architecture will be discussed, covering the delivery via GitOps and enabling use cases, such as k8sgpt and node-red.