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.
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
4 min
Llama Stack with the Ollama provider, on 127.0.0.1, answering OpenAI clients.
3 min
Tool calls, multi-turn state and streaming, with the same client code against any endpoint.
4 min
Two MCP servers registered in Llama Stack, tested in the MCP Inspector, called by the model.
Module 2
3 lessons, 13 min
5 min
kagent on kind: deploy the agent, read its revision, survive a bad version, roll back.
4 min
One token per agent, a policy at the tool server, and an allow-list in each template.
5 min
OpenTelemetry traces in Jaeger, a version two of the prompt, and a git revert.
Get started
Start Free LessonFirst lesson is always free — no signup required
This course includes
Want all courses?
See Pro plan →Your instructor

Founder and CEO, Open Empower. About the author
More in AI Agents
All courses in this trackOpenClaw: Your First AI Agent
Deploy OpenClaw locally or on a small VPS, add real tools, create one reusable automation, and apply essential security guardrails. You'll leave with a working 'Ops Assistant' that generates a Daily Brief, creates an Action Queue, and does it all safely.
Beginner · 7 lessons · 1 h
Preview free lesson
Claude Code Masterclass: Ship Real Code with AI
Stop treating AI like a magic autocomplete and start using it like a sharp junior engineer who sits next to you — one you direct, review, and hold accountable. In 10 hands-on modules you'll master the Plan → Implement → Test → Review → Commit loop and use it to ship real, tested code with Claude Code: Best-of-N, honest test suites, safe git workflows, multimodal prompts, refactoring & docs, reusable skills, the GitHub MCP server, lifecycle hooks, and a production-readiness checklist. You stay the engineer of record — Claude proposes, you decide what ships.
Intermediate · 10 lessons · 5 h
Preview free lesson
MLflow on Kubernetes: ML at Scale
Build scalable MLOps with MLflow, KServe, Docker, and Kubernetes. Automate deployments, monitor models, and workflows. Learn to deploy ML models to Kubernetes at scale, implement CI/CD pipelines, track experiments, perform hyperparameter tuning, and build production-ready ML services.
Intermediate · 15 lessons · 1 h 28 min
Preview free lesson