huggingface/agents-course

This repository contains the Hugging Face Agents Course.

What it solves

The course fills a gap in practical education for building AI agents. It takes learners from the basics of agents and large language models to a final benchmarked assignment, so they can go from theory to building and evaluating real agents.

How it works

The course is divided into four main units, plus bonus units. Unit 1 introduces agents and LLMs, with a bonus on fine-tuning for function calling. Unit 2 covers three major frameworks: smolagents, LlamaIndex, and LangGraph, and includes a bonus on observability and evaluation. Unit 3 focuses on agentic RAG. Unit 4 is a final project where learners create, test, and certify their agent, with automated evaluation and a leaderboard. There is also a bonus unit on agents in games using Pokemon. Prerequisites are basic knowledge of Python and LLMs.

Who it's for

The course is for developers who have basic Python and LLM knowledge and want to learn how to build AI agents. It is free, available on the Hugging Face platform, and requires sign-up to access.

Highlights

  • Free and accessible online.
  • Covers multiple agent frameworks: smolagents, LangGraph, and LlamaIndex.
  • Includes bonus units on fine-tuning for function calling, and on observability and evaluation.
  • Final project with automated evaluation and a leaderboard.

Related

  • Project
    anywhere-labs/dsh-desktop

    DSH Desktop is a native Windows/macOS client that packages the DeepSeek Harness AI agent platform into an easy‑to‑install desktop app, offering a built‑in plugin market, remote mobile control, and configurable LAN access.

  • Project
    iOfficeAI/AionUi

    AionUi is a free, cross‑platform desktop app that turns LLM APIs into autonomous AI agents capable of reading/writing files, generating Office documents, browsing the web, and running scheduled tasks. It includes a built‑in agent engine, supports dozens of external CLI agents, offers a Team mode for coordinated multi‑agent work, and provides remote access via WebUI or chat‑platform bots.

  • Project
    OpenBMB/ChatDev

    ChatDev 2.0 (DevAll) is an open‑source, zero‑code platform that lets you design and run multi‑LLM‑agent workflows via a visual web console or a tiny Python SDK. Define agents and their connections in YAML, launch from the browser or code, and use built‑in templates for data viz, 3‑D generation, game dev, research, etc. The backend is FastAPI, the frontend Vue 3, and the project ships Docker/Makefile support, extensible Python tools, and research‑grade orchestrators (Puppeteer, MacNet).

  • Project
    agentscope-ai/agentscope

    A production-ready agent framework that provides an SDK and a FastAPI backend to build multi-tenant, multi-session agentic applications leveraging LLM reasoning and tool use.