Home / Learn / OpenMAIC - AI Multi-Agent Classroom
Machine Learning

OpenMAIC - AI Multi-Agent Classroom

GitHubFree4 Clicks

OpenMAIC (Open Multi-Agent Interactive Classroom) is an open-source platform from Tsinghua University's MAIC research group that turns any topic or document into an interactive, AI-taught lesson with one click. Instead of static slides or plain text, it orchestrates a team of AI agents to generate a full lesson experience — slides, quizzes, interactive simulations, and project-based activities — complete with a virtual teacher, real-time whiteboard drawing, and text-to-speech narration.

Under the hood, OpenMAIC uses LangGraph for multi-agent orchestration on a Next.js/React frontend, and supports a wide range of LLM providers including OpenAI, Anthropic, Google Gemini, DeepSeek, and Qwen. It also includes an agent workbench for guided curriculum planning, optional local speech recognition and text-to-speech services, and the ability to export finished lessons as PowerPoint decks, interactive HTML pages, or offline packages.

This resource is best suited for educators, instructional designers, and developers who want to explore AI-driven curriculum generation and multi-agent teaching systems. It's also a useful reference for engineers interested in practical multi-agent orchestration patterns, since the codebase demonstrates how to coordinate several specialized AI agents around a shared learning workflow.

The project is free and open source under the MIT license, with support for 11 languages, making it accessible to a global audience of learners and builders.

↗ View source