Skip to main content
🎤 Luca Berton is speaking at Red Hat Summit & KubeCon EU 2026!Learn more →
intermediate

Agentic AI on Your Mac: Llama Stack, MCP and Agent Lifecycle

Build a local agent with Llama Stack and MCP, then deploy and update an agent on a Kubernetes cluster.

6 lessons23mUpdated November 2026

What you'll learn

  • Call a local model through the Responses API
  • Connect MCP tools and enforce an agent's permissions
  • Trace, update, and roll back a Kubernetes agent

Who this is for

  • • DevOps engineers deepening their expertise
  • • SREs building production-grade systems
  • • Backend developers expanding into infrastructure

Prerequisites

  • • An Apple Silicon Mac, Python, Ollama, and basic Kubernetes familiarity.

Course content

2 modules, 6 lessons, 23m of video

Module 1

3 lessons, 10 min
1

4 min

Llama Stack with the Ollama provider, on 127.0.0.1, answering OpenAI clients.

2
The Responses API

3 min

Tool calls, multi-turn state and streaming, with the same client code against any endpoint.

3
Tools from an MCP catalog

4 min

Two MCP servers registered in Llama Stack, tested in the MCP Inspector, called by the model.

Module 2

3 lessons, 13 min
4
Agents as Kubernetes resources

5 min

kagent on kind: deploy the agent, read its revision, survive a bad version, roll back.

5
Identity and policy for agents

4 min

One token per agent, a policy at the tool server, and an allow-list in each template.

6
Observe and update an agent

5 min

OpenTelemetry traces in Jaeger, a version two of the prompt, and a git revert.

Get started

Start Free Lesson

First lesson is always free — no signup required

This course includes

6 hands-on lessons
Intermediate level
23m total
Final assessment

Want all courses?

See Pro plan →

Your instructor

Luca Berton

Founder and CEO, Open Empower. About the author

More in AI Agents

All courses in this track