Deploy Now

SaaS Alternative

Coursera Kahoot Duolingo Khan Academy Udemy

Categories

Education AI Agents E-Learning Multi-Agent Systems Interactive Learning EdTech Course Creation

Stars

23,492

Forks

4,448

Watchers

124

Developer links

Last Updated: 08-30-2026
Share on X

OpenMAIC

Developed by Tsinghua University researchers and validated across more than 700 students, OpenMAIC converts raw prompts, PDFs, Office documents, audio, and video into complete, multi-agent virtual learning environments. The platform leverages Next.js, LangGraph state machines, and a pluggable `@openmaic/storage` layer to orchestrate autonomous AI professors and student avatars that lecture, debate at roundtables, answer inquiries, and illustrate complex equations on a real-time SVG whiteboard. Its Pro Agent Workbench features durable PostgreSQL-backed sessions, twenty specialized curriculum-building skills, and granular JSON Patch slide editing with full `.pptx` import fidelity. OpenMAIC supports rich scene modalities including automated quiz grading, Project-Based Learning milestones, and Deep Interactive Mode offering in-browser code execution, interactive mind maps, and Three.js 3D physics simulations. Built-in audio pipelines connect with VoxCPM2 for zero-shot voice cloning, Azure STT, and FunASR for speech recognition, alongside a dedicated Chromium-FFmpeg rendering microservice for one-click MP4 video exports. Flexible model routing interfaces seamlessly with OpenAI, Anthropic Claude, Google Gemini, Amazon Bedrock, DeepSeek, and local Ollama or Lemonade instances, while OpenClaw integration enables direct classroom generation from Slack, Discord, Feishu, and Telegram. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. MIT licensed.

OpenMAIC
OpenMAIC
OpenMAIC
OpenMAIC
OpenMAIC
OpenMAIC
OpenMAIC
OpenMAIC

Benefits

  • Autonomous Multi-Agent Classroom Collaboration
  • Orchestrates coordinated AI teachers and student personas via LangGraph state machines, delivering interactive lectures, roundtable discussions, real-time SVG whiteboard derivations, and contextual Q&A assistance during learning sessions.
  • Multi-Modal Deep Interactive Learning
  • Engages students beyond static slides through WebGL Three.js simulations, interactive physics sandboxes, in-browser code execution environments, structured concept mind maps, and collaborative Project-Based Learning milestones.
  • Pro Workbench with Durable Sessions
  • Empowers educators to plan multi-lesson curricula using twenty built-in agent skills, durable PostgreSQL session leases, granular JSON Patch slide adjustments, and direct PowerPoint presentation imports.
  • Provider-Agnostic AI and Media Ecosystem
  • Connects with OpenAI, Claude, Gemini, Bedrock, DeepSeek, or local Ollama instances alongside VoxCPM2 voice cloning, FunASR speech recognition, and Chromium-FFmpeg MP4 video exports.

Features

  • LangGraph Multi-Agent Orchestration
  • Coordinates specialized teacher and peer agent personas with synchronized speech, laser pointer cues, and SVG whiteboard drawing actions.
  • Deep Interactive Mode
  • Renders responsive Three.js 3D visualizations, interactive physics simulations, online code execution environments, and structured hierarchical mind maps.
  • Pro Agent Workbench
  • Provides durable PostgreSQL-backed session management, twenty domain-specific curriculum skills, session materials extraction, and editable PPTX slide imports.
  • Voice Cloning and Speech
  • Integrates VoxCPM2 for zero-shot neural voice cloning, Azure STT, and FunASR speech recognition for interactive voice conversations.
  • Comprehensive Export Capabilities
  • Exports fully editable PowerPoint presentations, self-contained interactive HTML bundles, offline classroom ZIP archives, and Chromium-FFmpeg MP4 videos.
  • OpenClaw Chat Integration
  • Generates tailored educational classrooms directly through conversational messaging platforms including Feishu, Slack, Discord, and Telegram.