Agents Course Notebooks

Agents Course Notebooks

Collects the notebooks of the Hugging Face Agents Course, covering a dummy agent library, smolagents, LlamaIndex, LangGraph and two bonus units. For learners building AI agents hands-on.

Made by agents-course on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository holds the hands-on notebooks that go with the Hugging Face Agents Course. The index lists 16 entries, mostly Jupyter notebooks and one Python script, grouped by unit. They cover a dummy agent library, three agent frameworks and two bonus units.

Who it suits: It suits learners who follow the Agents Course and want the practice files, and developers who want to compare how smolagents, LlamaIndex and LangGraph build agents.

Industry | Who uses it | How they use it | Example
Education | Learners on the course | Open the notebook for each unit as they study | Work through the Code Agents notebook
Software | Developers choosing a framework | Read the same ideas in three frameworks | Compare the Tools notebooks for smolagents and LlamaIndex
Training | Teachers running a workshop | Use the units as class exercises | Assign the Mail Sorting notebook

People who want a ready-made agent product can skip it, since these are teaching notebooks.

Where to use it:

• A Jupyter-style notebook tool for the notebook files
• Python, for the Vision Web Browser script and for downloading the files
• Windows, macOS or Linux, where you can download the files with Python

Use case | Who | What they get back
Learn the basics | Beginners | A dummy agent library notebook in Unit 1
Try a framework | Developers | Notebooks for smolagents, LlamaIndex or LangGraph in Unit 2
Go further | Advanced learners | Bonus notebooks on tuning Gemma and on monitoring agents

How to set it up: You need these first:

• Python and the huggingface_hub package
• A tool that opens notebook files

1. Install the Hugging Face hub package.
2. Download the repository files to your computer.
3. Open the notebook for the unit you are on.

pip install -U huggingface_hub
hf download agents-course/notebooks

How to use it: Follow the course units in order and open the matching notebook from the index. The card text gives no run steps beyond the download, so follow the course pages for details.

Tool | What it does
Unit 1 | The Dummy Agent Library notebook
Unit 2.1 smolagents | Code Agents, Multi-agent, Retrieval Agents, Tool Calling Agents, Tools and Vision Agents notebooks, plus a Vision Web Browser script
Unit 2.2 LlamaIndex | Agents, Components, Tools and Workflows notebooks
Unit 2.3 LangGraph | Agent and Mail Sorting notebooks
Bonus Unit 1 | A notebook on Gemma SFT and thinking function calls
Bonus Unit 2 | A notebook on monitoring and evaluating agents

Example: A learner finishing Unit 2.3 opens the Mail Sorting notebook from the LangGraph group to practice building an agent that sorts mail. The notebook is the hands-on part of that unit.

For newcomers and experts: An agent is a program where a language model chooses actions and uses tools. A first small step is to open the Unit 1 notebook, which builds a dummy agent library, before trying a framework.

Unit 2 repeats the agent idea in three frameworks, so you can see what each one makes easy. The bonus units go further, with supervised fine-tuning of Gemma for function calling and with ways to monitor and evaluate agents.

Start with the Dummy Agent Library in Unit 1
Pick a framework in Unit 2
Build agents with tools in its notebooks
Try the bonus units on tuning and monitoring

Good to know:

• Contents: 16 entries across Unit 1, Unit 2.1 to 2.3 and two bonus units
• Format: notebook files, plus one Python script for the Vision Web Browser
• Course: the notebooks belong to the Hugging Face Agents Course
• License: apache-2.0
• Cost to run: none named, no API key or account in the card text
• Data it reaches: it downloads files from Hugging Face, and the card text names no other service or account

On Hugging Face, 13 November 2026

• Downloads in the last 30 days: 0
• Likes: 1,131
• License: apache-2.0

Links

• Model: https://huggingface.co/agents-course/notebooks
• Files: https://huggingface.co/agents-course/notebooks/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download agents-course/notebooks

Then follow the usage in its model card. Nothing in this kit runs by itself.