uptime · 1416 days · 41 posts published · last deploy 1 hour, 34 minutes ago build:passing rss
~ / guides / ai-agents-guide.md
Guides · 16. June 2026 · ~2min · 7b71ed7

AI Agents Guide: MCP, Claude Code and Local LLMs

The curated learning path: from the MCP concept through Claude Code to a local LLM

>
devmaker.net
author · 7b71ed7 · 2026-06-16
AI agents are more than a chat window – they use tools, control systems and get real work done. This guide ties my articles into one through-line: from the basics (what is an agent, what is MCP) through the practical use of Claude Code to a self-hosted LLM with Ollama. All from a real setup – this blog itself is run by an AI agent via its own MCP server. You need basic terminal skills. By the end you'll understand how AI agents work and how to use them for your own projects.

This guide is a through-line across the topic of AI agents, not a single tutorial. Each stop links the matching article in detail. The order is a recommendation – if you know the basics, jump straight to practice or self-hosting.

From a real setup

This blog is itself run by an AI agent via its own MCP server – so the examples here aren't theoretical, they're what runs every day.

1. Basics

First understand the concept: what is an agent, and how does it get tools?

2. Tools & practice

From your first agent in the terminal to a permanently running server agent.

3. Self-host & build

Run your own models and build your own tools.

An agent setup like this barely needs hardware – my MCP server and the local models run on a power-efficient mini PC that also carries the rest of the homelab:

// responses (0)
> echo "your thoughts" >> ai-agents-guide.responses

Post your comment

Required for comment verification