OpenMAIC — Multi Agent Interactive Classroom Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. OpenMAIC (Open Multi Agent Interactive Classroom) is a Next.js 16 / React 19 / TypeScript platform that converts any topic or document into a full interactive lesson. A multi agent pipeline (LangGraph 1.1) generates slides, quizzes, HTML simulations, and project based learning activities delivered by AI teachers and AI classmates with voice (TTS) and whiteboard support. Project Stack Layer Technology Framework Next.js 16 (App Router) UI React 19, Tailwind CSS 4 Agent orchestration LangGraph 1.1 Language TypeScript 5 Package manager pnpm = 10 Runtime Node.js = 20 Installation Environment Configuration Edit .env.local — at minimum one LLM provider key is required: Provider Config via YAML (alternative to env vars) Create server providers.yml in the project root: Running the App Docker Deployment Vercel Deployment One click deploy button is available in the README; it pre fills env var descriptions automatically. Lesson Generation Pipeline OpenMAIC uses a two stage pipeline: Stage Description Outline AI analyzes topic/document and produces a structured lesson outline Scenes Each outline item is expanded into a typed scene: slides , quiz , interactive , or pbl Scene Types Type Description slides AI teacher lectures with TTS narration, spotlight, laser pointer quiz Single/multiple choice or short answer with AI grading interactive HTML based simulation (physics, flowcharts, etc.) pbl Project Based Learning — choose a role, collaborate with agents API Usage — Generating a Classroom REST: Start Generation Job REST: Poll Job Status REST: Export Slides OpenClaw Integration OpenMAIC ships a skill for [OpenClaw](https://github.com/openclaw/openclaw), enabling classroom generation from Feishu, Slack, Discord, Telegram, etc. Install the Skill Configure OpenClaw Edit ~/.openclaw/openclaw.json : OpenClaw Skill Lifecycle Phase What Happens Clone Detect existing checkout or clone fresh Startup Choose pnpm dev , pnpm build && pnpm start , or Docker Provider Keys Guide user to edit .env.local Generation Submit async job, poll, return classroom link Custom Scene Development Pattern Scenes are typed React components. To add a new scene type: Multi Agent Interaction Modes Mode Trigger Description Classroom Discussion Automatic Agents proactively start discussions; user can jump in or get called on Roundtable Debate Scene config Multiple agent personas debate a topic with whiteboard illustrations Q&A User asks question AI teacher responds with slides, diagrams, or whiteboard drawings Whiteboard During any scene Agents draw equations, flowcharts, or concept diagrams in real time MinerU Advanced Document Parsing For complex PDFs with tables, formulas, or scanned images: Without MinerU, OpenMAIC falls back to standard PDF text extraction. Supported LLM Providers & Model Strings Export Formats Format Endpoint Notes PowerPoint .pptx GET /api/export/pptx?classroomId= Fully editable slides Interactive .html GET /api/export/html?classroomId= Self contained HTML page Common Patterns Generate a Classroom from a Document String Check Provider Health Troubleshooting Problem Solution No LLM provider configured Set at least one of OPENAI API KEY , ANTHROPIC API KEY , or GOOGLE API KEY in .env.local Generation hangs at outline stage Check API key quota; try switching to google:gemini 3 flash preview for higher rate limits TTS not working TTS requires a browser with Web Speech API support; check browser console for errors PDF parsing produces garbled text Enable MinerU by setting PDF MINERU BASE URL in .env.local Vercel timeout during generation Increase function timeout in vercel.json ; generation is async so the API should return a jobId immediately Docker build fails Ensure DOCKER BUILDKIT=1 and that .env.local exists before running docker compose up build OpenClaw skill not found Run clawhub install openmaic or manually copy skills/openmaic to ~/.openclaw/skills/ pnpm install fails on Node < 20 Upgrade Node.js to = 20 ( nvm use 20 ) Port 3000 already in use Set PORT=3001 in .env.local or run PORT=3001 pnpm dev Key File Structure

openmaic-classroom