Awesome AI Agents › Courses and Tutorials
AI Agents from Scratch is a teaching repository that explains how LLM agents work by constructing one agent incrementally rather than by demonstrating a framework. Every lesson adds a capability to the same Agent class, so the reader can follow the growth of a single artifact: lesson 01 covers a plain text-in/text-out model call, lesson 02 adds system prompts and role behaviour, lesson 03 introduces structured output through JSON contracts, lesson 04 adds routing decisions, lesson 05 adds external tools, lesson 06 assembles the observe-decide-act loop, lesson 07 adds short-term and long-term memory, lesson 08 treats planning as data instead of free-form reasoning, lesson 09 defines atomic actions for safe execution, lesson 10 introduces Atom of Thought dependency graphs, lesson 11 adds evaluations as regression tests over golden datasets, and lesson 12 adds runtime telemetry. The code is Python and runs entirely locally: the reader installs the requirements, places a GGUF model file in a models directory and runs a complete example script that demonstrates all twelve lessons together. The repository layout mirrors the curriculum, with separate modules for the agent class, memory, planner, state, tools, evaluations and telemetry, plus a lessons directory holding the written explanations and a diagrams folder. The stated philosophy is that agents are loops, state and constraints rather than personalities, and that nothing in the repository should feel like magic because every behaviour is visible in a file. The authors describe the audience explicitly: developers who can already code but find agent tooling opaque, people who want to avoid a heavier framework, learners who prefer local models, and educators looking for a clean mental model. It is not intended as a production starter kit or a fast demo.
https://github.com/pguso/agents-from-scratch
A comprehensive guide and resource hub for prompt engineering, context engineering, retrieval-augmented generation, and AI agents, offering tutorials, papers, tools, and courses to optimize the use of large language models.
Learn Claude Code is an educational project that teaches how to build modern AI coding agents like Claude Code through a progressive tutorial covering core concepts, planning, subagents, and skills mechanisms.
AI Engineering Hub is a comprehensive repository offering in-depth tutorials and practical resources on Large Language Models, Retrieval-Augmented Generation, and real-world AI agent applications for learners and practitioners.
The Hugging Face Agents Course is a comprehensive educational resource that teaches the fundamentals and advanced concepts of AI agents and large language models through structured units, practical frameworks, and community collaboration.
GenAI_Agents is a comprehensive repository offering tutorials, implementations, and community resources for building and advancing generative AI agents from basic to advanced levels.
This course provides a comprehensive project-based tutorial on Harness Engineering for building reliable AI coding agents, covering environment setup, state management, verification, and control.
An AI-powered tool that analyzes GitHub repositories and generates beginner-friendly tutorials with visualizations to simplify understanding complex codebases.
A comprehensive guide to prepare for machine learning and AI technical interviews at major tech companies, covering coding, ML fundamentals, system design, and behavioral aspects.