Learn to build AI agents locally without frameworks
Understand what happens under the hood before using production frameworks. Build real understanding of function calling, memory, and ReAct patterns.
Master the fundamentals of AI agents through hands-on examples
This tutorial teaches you to build AI agents from first principles using local LLMs and node-llama-cpp. By working through these examples, you'll understand deeply, then use frameworks wisely.
Follow these tutorials in order. Each example builds on the previous one, taking you from basic LLM interaction to advanced agent patterns.
Your first step: loading models, basic prompts, understanding tokens
Cloud-based models, API keys, message roles, statelessness
Transform general LLMs into specialized agents with system prompts
Teaching AI to think logically and solve complex problems
Process multiple requests simultaneously for better performance
Real-time responses and controlled output for better user experience
Transform LLMs from text generators into agents that can act
Transform agents from stateless responders into systems with context
Reasoning + Acting = Powerful problem-solving agents
"SQL for Reasoning" - Structured, executable plans
Learn to rebuild LangChain's core patterns with clear, educational code
Essential building blocks for understanding and building AI agents
Stateless processing, tokens, context windows, system prompts
Tools, tool definitions, agent decision-making, action-taking
ReAct, AoT, memory management, reasoning loops
Before you begin, make sure you have the following knowledge and resources ready
Don't worry if you're new to some concepts - we'll explain everything step by step!
Begin with Lesson 1 to understand basic LLM interaction, then progress through each tutorial to build your understanding step by step.
Start with Lesson 1