explaingit

thu-maic/openmaic

17,512TypeScriptAudience · generalComplexity · 3/5Setup · moderate

TLDR

OpenMAIC turns any topic or document into an interactive AI classroom, with slides, quizzes, simulations, and AI teachers that lecture and discuss in real time, connecting to many LLM providers and supporting self-hosting.

Mindmap

mindmap
  root((OpenMAIC))
    What it does
      AI classroom generator
      Multi-agent lessons
    Output
      Slides pptx
      Interactive HTML
      Mind maps
      Simulations
    LLM Providers
      OpenAI
      Anthropic
      Gemini
      Ollama
    Tech
      Next.js
      LangGraph
      TypeScript
    Audience
      Learners
      Educators
Click or tap to explore — scroll the page freely

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

Things people build with this

USE CASE 1

Turn a research paper or textbook chapter into an interactive AI lesson with quizzes and simulations without writing any code.

USE CASE 2

Spin up an AI classroom on a custom topic for a course you are teaching, then export it as an editable slide deck.

USE CASE 3

Trigger lesson generation from Slack or Discord by asking an AI chatbot to create a classroom on a topic on demand.

Tech stack

TypeScriptNext.jsReactTailwind CSSLangGraphNode.jspnpm

Getting it running

Difficulty · moderate Time to first run · 30min

Requires at least one LLM provider API key (e.g. OpenAI or Anthropic) and pnpm to install dependencies.

In plain English

OpenMAIC, short for Open Multi-Agent Interactive Classroom, is an open-source AI platform that turns a topic or document into an interactive lesson. You describe what you want to learn or upload your own material, and the system generates a classroom, slides, quizzes, interactive simulations, and project-based activities, delivered through AI "teachers" and AI "classmates" that can speak, draw on a whiteboard, and discuss the material in real time. It is built around multi-agent orchestration, meaning several AI roles cooperate behind the scenes: one might lecture, another might play a peer asking questions, another might run a simulation. Beyond passive slides, a Deep Interactive Mode adds 3D visualization, simulations, games, mind maps, and inline programming. Generated lessons can be exported as editable .pptx slide decks or interactive .html pages. Through an optional integration called OpenClaw, you can trigger classroom generation from chat apps like Feishu, Slack, Discord, and Telegram by asking an AI assistant. You would use OpenMAIC if you want to learn a subject more interactively than from a static document, or if you teach and want to spin up an AI lesson around your own materials. A hosted version is at open.maic.chat, and you can also self-host. The project is a web app built with Next.js, React, TypeScript, and Tailwind CSS, with LangGraph powering the multi-agent flow. It runs on Node.js and pnpm. It connects to many LLM providers, including OpenAI, Anthropic, Google Gemini, DeepSeek, Qwen, Grok, OpenRouter, Ollama, and any OpenAI-compatible API, and you bring at least one provider's key. The full README is longer than what was provided.

Copy-paste prompts

Prompt 1
I uploaded a PDF on machine learning basics to OpenMAIC. Generate a classroom with a lecture, two quiz questions, and a short simulation for a non-technical audience.
Prompt 2
Using OpenMAIC with the OpenAI provider, create an interactive classroom on the topic 'How blockchain works' and export it as a .pptx slide deck.
Prompt 3
How do I self-host OpenMAIC locally with the Ollama LLM provider? Walk me through the pnpm setup steps.
Prompt 4
Configure OpenMAIC's OpenClaw integration to let my Slack workspace trigger new lessons by messaging an AI assistant with a topic.
Open on GitHub → Explain another repo

← thu-maic on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.