A 21-lesson Microsoft course teaching developers the fundamentals of building generative AI applications with Python and TypeScript.
microsoft/generative-ai-with-javascript
A Microsoft-led beginner course teaching Generative AI with JavaScript through a time-travel story and a companion character chat app.
- Stars
- 1,292
- Forks
- 851
- Open issues
- 16
- Last commit
- 4 days ago
What is it?
This is a beginner course for JavaScript developers who want to add Generative AI features to their apps. It is organized as eight written lessons covering LLM fundamentals, building a first AI app, prompt engineering, structured output, retrieval augmented generation (RAG), tool/function calling, and the Model Context Protocol (MCP), including building an MCP server and improving an MCP client with an LLM.
The course is framed as a time-travel adventure in which learners chat with historical figures such as Leonardo da Vinci and Ada Lovelace. A companion app in the repository lets users interact with these characters, and each lesson includes an assignment, a quiz, and solutions.
The repository can be run in GitHub Codespaces or locally on Node.js LTS. Model configuration uses Microsoft Foundry, with a chat model deployed and its endpoint and API key set in a root `.env` file.
Key features
- 01Eight lessons covering LLM basics through MCP client development.
- 02Companion app for chatting with historical characters powered by generative AI.
- 03Each lesson includes an assignment, a quiz, and solutions.
- 04Runs in GitHub Codespaces or locally with Node.js LTS.
- 05Audio tags on lesson content for listening as well as reading.
Use cases
- A JavaScript developer new to LLMs who wants a guided, hands-on introduction.
- Learning RAG, tool calling, or MCP with runnable JavaScript examples.
- Instructors who want a structured course with assignments and quizzes.
Quick start
- 1
Fork the repository on GitHub
- 2
Create a Codespace from your fork's Code button, then follow the course setup guide
- 3
Or run the code locally with Node.js LTS, following the setup guide's local app option
Things to know
- Running the examples requires a Microsoft Foundry project with a deployed chat model and an API key.
- The companion app's historical characters are fictional AI-generated content and do not represent real views.
In collections
Topics
FAQ
- What is generative-ai-with-javascript?
- A Microsoft-led beginner course teaching Generative AI with JavaScript through a time-travel story and a companion character chat app. This is a beginner course for JavaScript developers who want to add Generative AI features to their apps. It is organized as eight written lessons covering LLM fundamentals, building a first AI app, prompt engineering, structured output, retrieval augmented generation (RAG), tool/function calling, and the Model Context Protocol (MCP), including building an MCP server and improving an MCP client with an LLM.
- Is generative-ai-with-javascript free to use? What license does it have?
- generative-ai-with-javascript is open source under the MIT license. Check the license terms before using it in commercial products.
- Is generative-ai-with-javascript still maintained?
- Actively maintained. The last commit to generative-ai-with-javascript was on Nov 2, 2026.
- What can I use generative-ai-with-javascript for?
- A JavaScript developer new to LLMs who wants a guided, hands-on introduction. Learning RAG, tool calling, or MCP with runnable JavaScript examples. Instructors who want a structured course with assignments and quizzes.
- How do I install generative-ai-with-javascript?
- Fork the repository on GitHub Create a Codespace from your fork's Code button, then follow the course setup guide Or run the code locally with Node.js LTS, following the setup guide's local app option
- Where can I get generative-ai-with-javascript?
- The source code and installation instructions are on GitHub: https://github.com/microsoft/generative-ai-with-javascript
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A collection of 90+ hands-on tutorial projects covering LLMs, RAG pipelines, and AI agents, organized by difficulty level.
Compresses tool outputs, logs, files and RAG chunks before they reach an LLM, as a library, proxy or MCP server.
A project-based course teaching how to build the environment, state, verification, and control mechanisms that make AI coding agents reliable.
A collection of 22 prompt engineering techniques, each explained in a hands-on Jupyter Notebook tutorial for working with LLMs.
A free, open-source Chinese AI course and collection of practical skills covering Claude Code, Codex, OpenClaw, Hermes, prompt engineering, and image, voice and music AI tools.