explaingit

zyfup/fh_maic

Analysis updated 2026-05-18

43TypeScriptAudience · developerComplexity · 4/5Setup · moderate

TLDR

An AI classroom platform that turns a topic or uploaded materials into an interactive lesson delivered by multiple cooperating AI agents.

Mindmap

mindmap
  root((Fanghu MAIC))
    What it does
      Generates lessons
      Multi agent classroom
      Interactive slides
    Tech stack
      TypeScript
      Next.js
      LangGraph
    Use cases
      Build AI lessons
      Deliver interactive classes
    Audience
      Developers
        Educators

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

What do people build with it?

USE CASE 1

Generate an interactive AI led lesson from a topic or uploaded materials

USE CASE 2

Run a multi agent classroom with a teacher, classmates, and a director agent

USE CASE 3

Export a completed lesson as a PowerPoint, HTML page, or ZIP archive

What is it built with?

TypeScriptNext.jsLangGraph

How does it compare?

zyfup/fh_maicflaviojmendes/dinamosjavlonbek1233/amaliy-ish1
Stars434343
LanguageTypeScriptTypeScriptTypeScript
Setup difficultymoderatemoderateeasy
Complexity4/53/52/5
Audiencedeveloperdevelopervibe coder

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · moderate Time to first run · 1h+

Requires an API key for at least one supported AI provider.

In plain English

Fanghu MAIC is an AI-powered classroom platform where you give it a topic or upload materials and it generates a fully interactive lesson for you. Instead of a single AI answering questions, it uses multiple AI agents working together: one plays the role of the teacher, others play classmates, and a director agent coordinates who speaks and what happens next using a state machine called LangGraph. The classroom experience includes canvas-based slides with animations, a laser pointer, whiteboard drawing, and real-time voice through text-to-speech and speech-to-recognition. You can also trigger deeper interactive elements such as 3D visualizations, simulations, games, mind maps, and an online coding environment during the lesson. When you have a question, the AI teacher can respond by updating the slides or the whiteboard in real time. Once a lesson is complete you can export it as a PowerPoint file, an interactive HTML page, or a classroom ZIP archive. The platform supports multiple spoken and written languages in its interface, including Chinese, English, Japanese, and Russian. On the technical side it is built with Next.js and TypeScript. It connects to a wide range of AI providers including OpenAI, Anthropic, Google Gemini, DeepSeek, MiniMax, GLM, and Ollama, as well as any OpenAI-compatible API, so you can point it at whichever model you have access to. You would use this if you are building or delivering AI-assisted education and want a rich classroom experience that goes well beyond a simple question-and-answer chat.

Copy-paste prompts

Prompt 1
Help me set up fh_maic and connect it to my OpenAI or Anthropic API key
Prompt 2
Show me how the director agent coordinates the teacher and classmate agents using LangGraph
Prompt 3
Help me export a generated lesson as an interactive HTML page

Frequently asked questions

What is fh_maic?

An AI classroom platform that turns a topic or uploaded materials into an interactive lesson delivered by multiple cooperating AI agents.

What language is fh_maic written in?

Mainly TypeScript. The stack also includes TypeScript, Next.js, LangGraph.

How hard is fh_maic to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is fh_maic for?

Mainly developer.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Verify against the repo before relying on details.