Skip to main content
FPEFPE

AI agents

on your machine.

Build your assistant with Claude Code, MCPs and sub-agents. It lives on your computer, knows you, and works for you.

Claude Code terminal

Before

  • You use Claude or ChatGPT in the browser and copy-paste answers all day
  • Every conversation starts from zero — it knows nothing about you or your project
  • "An agent that works for me?" — you have no idea how to build one
  • You know AI can do more but don't know where to start

After

  • Your own agents running locally, doing real tasks in your terminal
  • Agents that know you: CLAUDE.md, context and memory of your project
  • MCPs, skills and hooks that let your agent act way beyond chat
  • From casual user to the person everyone asks "how did you do that?"

Your own AI agents, running locally. From zero to power user.

The syllabus

What you'll master

What is an agent

Module 1

What is an agent

The difference between a chatbot and an agent. The READ → THINK → ACT loop, the tools (read, write, run commands) and why an agent acts instead of just answering.

Claude Code in your terminal

Module 2

Claude Code in your terminal

Install Claude Code, understand the CLI and watch it work: read your code, run commands, chain tasks. Your first agent running locally.

Give it context: CLAUDE.md

Module 3

Give it context: CLAUDE.md

Make your agent know you. CLAUDE.md, the filesystem, where sessions and memory live. The meta technique to have it define itself from your project.

Permissions & settings

Module 4

Permissions & settings

Control what it can and can't do. Permissions, modes, per-project memory and the settings to work from anywhere.

Connect the world: MCPs & skills

Module 5

Connect the world: MCPs & skills

Connect your agent to Notion, GitHub, the web... via MCP. Reusable skills. Your agent gains new capabilities without switching tools.

Automate it: hooks, cron & your final agent

Module 6

Automate it: hooks, cron & your final agent

Hooks that react to events, cron and claude -p for recurring tasks. You build your final agent that solves a real task with a single command.

How it works

1

Sign up free

Create your account and jump straight into the course. No card required.

2

Learn at your own pace

Short, to-the-point videos and guided, hands-on practice. Move forward whenever you can.

3

Walk away with your agent running

Your assistant living on your machine, knowing your context and working for you. Something you use every day, not theory.

Ready for your own local agents?

Sign up and start free. Jump into the course and build your first agent.

Sign up and try it free

No card required. Start in 1 minute.