Install an AI SRE Agent in Kubernetes with AURA and Helm

AURA does not have to live on your laptop. Install it into the cluster with Helm and it is still there the next time something breaks.

Learn more about AURA → https://www.mezmo.com/aura
Get started today → https://github.com/mezmo/aura
Get deployment help → https://www.mezmo.com/contact

AURA is a fully open source AI agent built specifically for SRE work. Rather than one general assistant, you configure workers: separate agent roles, each scoped to a job like inspecting the cluster.

Diagnosing a cluster problem today means you, a terminal, and a dashboard. Running AURA as a long-lived in-cluster instance, rather than a standalone binary on a laptop, is what makes long-term memory, centralized configuration, and the possibility of automated investigations available at all.

Mezmo forward deployed engineer Jeff installs AURA and the Kubernetes MCP server with helm into a cluster standing in for production, trimming the quickstart example values to one MCP server and one worker that inspects the cluster. The MCP server runs read-only, enforced through both RBAC and a startup flag, and ingress is off since AURA runs on the same cluster, so the agent can read the cluster without being able to change it and nothing is exposed beyond it.

0:00 Why run AURA as a long-lived instance

0:34 The demo cluster and the Helm approach

0:58 The AURA Helm chart and the quickstart example values

1:31 Trimming the values file to one MCP server and one worker

1:58 Cloning the repo and running helm install

2:51 Installing the Kubernetes MCP server in read-only mode

4:07 Verifying both rollouts

4:38 Connecting to AURA and running a smoke test

5:21 Next steps: GitOps, and what the next video covers

#AISREAgent #Kubernetes #SRE