Step by step to your own agent.
From the first install to a productive setup. Every tutorial will get a video and cheat sheet over time.
Install Ollama and load your first model
Go from zero to a locally running LLM you can talk to via terminal and HTTP API in 15 minutes - no API key, no cloud.
Install Hermes 3 - a model that actually does tool-use
Pull Hermes 3 from NousResearch via Ollama and see why it's a better fit for building agents than a stock Llama.
Get an OpenRouter key and make your first call
Create an account, generate an API key, fire off your first call with curl and an SDK - and understand what's in the response.
Install Pi - your first agent in the terminal
Pi is a minimal terminal agent that gets surprisingly far with four tools (read, write, edit, bash) and one Markdown file (AGENTS.md). In this tutorial you'll install Pi, connect it to a local or free cloud model, and write your first custom skill.
How neural networks learn to read - the MNIST lab
Draw digits, train a real neural network live in your browser, and watch it learn to recognize handwriting from 784 pixels - from scratch, no server.
The Ant Lab - understand agents by building them
One simulation, four swappable brains. Each stage teaches one agent concept - from hardcode to an LLM with memory.
A Soul in a File - what belongs in a soul.md (and what doesn't)
Same world, different soul. Ask the same question to agents that differ only in their soul.md - none, minimal, rich, overloaded - and see the effect instantly.
Understanding RAG - step by step with real data
We build a Retrieval-Augmented Generation system from scratch. Real embeddings, a real vector database, and demos you can pause and pull apart whenever you want.
Kuno - the Mega-Agent
We build a complete, local multi-agent system on our own hardware, step by step. 15 chapters, each with a companion video, from an empty box to a talking mini-organisation.