Hugging Face AI Agents Course

Hugging Face’s open course explains agents and develops practical work across several frameworks, including smolagents, LlamaIndex, and LangGraph. It combines concepts with project activity and includes an agentic retrieval unit. The published final project provides a more concrete goal than simply completing a set of introductory videos.

What you will learn

• Explain the components of a tool-using agent
• Compare agent frameworks
• Explore retrieval in agent workflows
• Build and evaluate a final agent project

Who this suits

Useful for a learner with basic Python and an understanding of language models. The free format makes it a useful way to test your interest in agent engineering before purchasing a broader course.

Before you enroll

Account, model, and execution requirements depend on the activities you choose. Hosted inference and optional compute may have limits or charges. Work through exercises and inspect failure cases rather than assuming a framework demonstration transfers directly to an unattended application.

The learning material is free. The provider offers a certification route tied to its activities and final project; check current submission and assessment instructions.

Put it into practice

Implement an agent over a small verifiable document collection. Record its tool calls and evaluate questions the documents cannot answer before extending its capabilities.

Source and review

This overview is based on the provider's published information, checked on 11 October 2026. It is an editorial assessment, not a claim that we completed the resource. Time filters are approximate study ranges; projects and exercises can take longer.

View the curriculum and current access options at Hugging Face.

How YellowCourse describes and checks learning resources.