LaunchedEditorial Listing

OpenMAIC

Tsinghua University (THU-MAIC) · OpenMAIC: Open-Source Multi-Agent Classroom That Turns Topics and Documents into Interactive Lessons

Open OpenMAIC

OpenMAIC is a free, MIT-licensed platform from Tsinghua University's THU-MAIC group that turns a topic or uploaded material into an interactive classroom: slides, quizzes, simulations, and project-based activities, taught by AI teachers and AI classmates who narrate, draw on a whiteboard, and discuss with you. It suits self-learners, educators, and course builders who want generated lessons they can host, edit, and export.

PricingFree
Setupmedium
Runs onSelf-hosted · Web · API
APIYes
Open sourceYes
DocsYes
CategoryResearch
Open SourceEducationAI TutorMulti-AgentCourse GenerationSelf-HostedDockerLocal ModelsVoiceAgent Skills

Best for

Self-learners, teachers, and course or training builders who want AI-generated, multi-agent interactive lessons from a topic or their own materials, and technical teams that want to host, modify, or embed that capability under an MIT license

Not ideal for

Schools that need a managed, supported service with user accounts, LMS integration, and published terms, people who only want quick cited answers or summaries from documents, teams that want serverless hosting such as Vercel, and anyone unwilling to run PostgreSQL and manage model API keys

Who it's for

Self-learners, educators, instructional designers, and developers who want to generate, host, or build on multi-agent interactive lessons

Capabilities

  • Generates a full lesson from a one-line topic or uploaded material through an outline stage and a scene stage; PDF and text work out of the box, while Word, PowerPoint, spreadsheet, image, audio, and video inputs depend on the document and media extractors you configure
  • Scene types: narrated slides with spotlight and laser-pointer effects, quizzes (single choice, multiple choice, short answer) with AI grading, HTML simulations, and project-based learning with roles, milestones, and deliverables
  • Deep Interactive Mode with 3D visualizations, simulations, knowledge games, mind maps, and in-browser programming, where the AI teacher can operate the interface to guide the learner
  • Multi-agent classroom: AI teachers and classmates lecture, start discussions, call on you, hold roundtable debates with different personas, and draw equations and diagrams on a shared whiteboard
  • Classroom chat on an agent loop (v1.1.0, the only chat mode since v1.2.1): point at a slide element, interactive component, or whiteboard drawing and ask about it, and the teacher can read the lesson, sample an experiment's live state, and search the web, with suggested replies
  • Pro agent workbench (v1.0.0): a chat agent that plans multi-lesson curricula, creates and reorders pages, edits narration, imports .pptx decks with layout preserved, and generates images, video, and narration audio
  • Durable, PostgreSQL-backed agent sessions that survive restarts and can be cancelled, resumed, and steered mid-run, plus 24 built-in teaching and slide-craft skills, per-owner custom skills, and course-level undo across manual edits and agent runs (v1.4.2)
  • Knowledge base (v1.3.0): uploads stay in the owner's library in folders until deleted, are parsed once and reused across conversations, and can be referenced with @ and read, searched (literal text search, no embeddings), and organized by the agent
  • PBL v3 (v1.4.0, experimental): runnable Python and Java projects with an in-browser IDE and terminal, AI teaching roles, milestone tests and quizzes, and a learning report, with progress saved between visits
  • Exports to editable PowerPoint (with charts and LaTeX formulas, and since v1.2.0 every scene, with interactive ones as linked placeholder slides), a single offline HTML file that plays the lesson, a classroom ZIP that plays offline on an intranet instance, and MP4 through an optional render service
  • Provider-neutral model configuration in openmaic.yml with a model per generation step, covering OpenAI, Azure OpenAI, Anthropic, Amazon Bedrock, Google Gemini, DeepSeek, Qwen, Kimi, MiniMax, Grok, OpenRouter, GLM, Doubao, and any OpenAI-compatible API
  • Local options: Ollama and Lemonade for LLMs, Lemonade for image, TTS, and speech recognition, FunASR for speech recognition, and self-hosted VoxCPM2 text-to-speech with voice cloning
  • OpenMAIC skill (SKILL.md) for OpenClaw, Codex, DeepSeek, WorkBuddy, and other agent workbenches, so classrooms can be generated from Feishu, Slack, Telegram, or an IDE
  • HTTP API for asynchronous, server-side classroom generation from a requirement and up to five previously uploaded materials
  • Web search through Tavily, Exa, Brave, SearXNG, Firecrawl, Kimi, DeepSeek, and other providers, plus an optional hosted page reader (v1.2.1)
  • Interface in 12 locales across 11 languages, including English, Simplified and Traditional Chinese, Japanese, Korean, Spanish, French, German, and Arabic

Limitations

  • Self-hosting requires PostgreSQL 16 (the server refuses to start without DATABASE_URL), Node.js 22.19+ and pnpm 10+, or the bundled Docker Compose stack, on a long-running server: from v1.2.0, Vercel and other serverless hosts are not supported, and Vercel users must stay on the 1.1.x branch
  • Classroom chat and the Pro workbench need a model that supports tool calling
  • PBL v3 is experimental and stays off until you configure an E2B-compatible sandbox provider, durable checkpoint storage such as S3, and the agent runtime; it runs the bundled samples and imported packages, but cannot yet generate PBL v3 projects
  • Since v1.4.2, any owner a deployment admits, including anonymous visitors, can use its sandboxes, so a public instance without an access code can run up sandbox costs
  • You bring your own model provider keys or local models, and the project recommends enabling image, voice, video, and web search providers for the best lessons, which adds setup and per-use cost
  • No built-in user accounts: identity is an anonymous browser cookie, a single-user mode, or one shared team owner behind an access code, and real multi-user logins require writing your own authentication method
  • ACCESS_CODE is unset by default and the app is then fail-open, so a deployment reachable by others must be protected before it is exposed
  • Course reads are capability-by-id: anyone who can reach the server and knows a course id can read that course, though only its owner can change it
  • The Pro agent workbench is off by default and must be enabled with build and runtime flags plus a model that supports tool calling
  • On the hosted Live Demo at open.maic.chat, access codes require signing in and generation through the skill or API is capped at 10 per day; the web interface's quota and the demo's terms are not documented in the repository
  • Fast release pace: seven security releases between September and mid-October 2026 (v1.0.1 to v1.0.3, v1.1.1 to v1.1.4), and v1.2.0, v1.3.0, v1.3.1, and v1.4.0 carry breaking changes or one-way database migrations, so self-hosters need to follow upgrade notes and back up the database first
  • MP4 export needs a separate render-service container with Chromium and FFmpeg; without it, export falls back to a project ZIP for local rendering
  • No integration with learning management systems such as Moodle, Canvas, or Google Classroom is documented

Use cases

  • Turning a research paper or report PDF into a narrated lesson with a quiz and a class discussion
  • Learning a new skill from scratch, such as introductory Python, with in-browser coding exercises
  • Building a multi-lesson course with the Pro workbench from existing slides, documents, and lecture recordings
  • Creating interactive simulations or 3D visualizations to explain a physics or engineering concept
  • Generating a classroom from a chat message in Feishu, Slack, or Telegram through the OpenClaw skill
  • Exporting a generated lesson to PowerPoint or an offline classroom package for an intranet or air-gapped school network

Our take

OpenMAIC is an unusually complete open-source take on an AI-run classroom: it does not just answer questions about a document, it turns the material into a lesson with narration, a whiteboard, quizzes, simulations, and AI classmates, and since v1.1.0 the teacher can reason about what the learner is looking at. That makes it a different decision from Gemini Notebook. Choose Gemini Notebook to interrogate and summarize sources with citations; choose OpenMAIC when you want to be taught, or want to produce courses others will take. The catch is operational. Running it well means PostgreSQL, a stack of model and media keys, and care with access codes and identity, because it ships without user accounts and is fail-open until you set a code. Try the Live Demo first, then self-host only if you are ready to maintain a fast-moving project.

Who should use it

Self-learners who want an interactive lesson instead of a summary, teachers and trainers who want a first draft of a course from their own slides and documents, instructional designers prototyping interactive content, and developers or edtech teams who want an MIT-licensed base to host or embed.

Who should skip it

Schools and companies that need a supported product with user accounts, LMS integration, and published terms, people who just want cited answers from their documents, and anyone who does not want to operate PostgreSQL or manage provider API keys.

Strengths

  • Produces a taught, interactive class with multiple agents rather than static notes or summaries
  • Wide range of scene types: narrated slides, graded quizzes, simulations, games, 3D visualizations, and project-based learning
  • MIT licensed with npm SDK packages, so it can be hosted, modified, and embedded commercially
  • Provider-neutral, with a model per generation step and local options for LLM, voice, and speech recognition
  • Agent workbench builds and revises whole courses from your own materials and slides
  • Exports to editable PowerPoint, interactive HTML, offline classroom packages, and MP4

Weaknesses

  • Self-hosting needs PostgreSQL, Node.js, and several provider keys for the full experience
  • No built-in user accounts or LMS integration
  • Insecure if exposed without setting an access code, and courses are readable by anyone with their id
  • The hosted Live Demo is capped, and its pricing and terms are not documented in the repository
  • Rapid release pace with frequent security fixes, breaking changes, and one-way database migrations
  • No serverless or Vercel hosting from v1.2.0, and PBL v3 needs a separate sandbox provider

OpenMAIC pricing

Open Source

Free

  • MIT license, commercial use permitted
  • Self-host with Docker Compose or from source on a long-running server with PostgreSQL (Vercel only up to 1.1.x)
  • Bring your own model, media, and search provider keys, or run local models

Free tier limits: The software has no paid tier. The hosted Live Demo at open.maic.chat limits generation through the skill or API to 10 per day (with an access code you get by signing in); its web interface has a separate quota that is not documented in the repository.

Note: Self-hosted costs come from the model, image, video, voice, and search providers you configure, or only your hardware if you use local providers such as Ollama, Lemonade, and FunASR. PBL v3 adds the cost of the sandbox provider and checkpoint storage you configure. The repository documents no pricing or paid plan for the hosted Live Demo, and open.maic.chat links no pricing or terms page. The bundled mathml2omml package is LGPL-3.0-or-later rather than MIT. Verified on the OpenMAIC repository (README and release notes through v1.4.2) and open.maic.chat on 2026-11-09.

Technical specs

Modalities

Text, Documents (PDF, Word, PowerPoint, spreadsheets), Image, Audio, Video, Voice (TTS and speech recognition)

API pricing

Free self-hosted HTTP API; model, media, and search usage is billed by the providers you configure

Available models

OpenAI, Azure OpenAI, Anthropic (Claude), Amazon Bedrock, Google Gemini, DeepSeek, Qwen, Kimi, MiniMax, Grok, OpenRouter, GLM, Doubao, Tencent Hunyuan, Xiaomi MiMo, SiliconFlowAny OpenAI-compatible chat APILocal LLMs through Ollama or LemonadeToken Plan presets (MiniMax, TokenDance, Volcengine Ark, Kimi Coding Plan, and since v1.3.1 DeepSeek) that cover several capabilities with one key

Where OpenMAIC excels

Learning a dense paper as a class instead of reading it alone

Upload the PDF and OpenMAIC outlines it into scenes, has an AI teacher walk through it with narration and whiteboard drawings, and lets AI classmates raise questions, with a quiz to check understanding.

A first draft of a training course from existing materials

The Pro workbench agent plans a multi-lesson curriculum from uploaded documents, slides, and recordings, imports existing .pptx decks, and revises pages on request, and the result exports to editable PowerPoint.

Hands-on STEM explanations

Deep Interactive Mode generates simulations, 3D visualizations, and coding exercises, and since v1.1.0 the teacher can read the live state of an experiment when the learner asks about it.

Classrooms for offline or intranet networks

Exported classroom packages inline the scripts, fonts, and images that interactive scenes use, so a course can play on an air-gapped OpenMAIC instance without reaching a public CDN.

OpenMAIC vs. competitors

OpenMAIC vs. Gemini Notebook (formerly NotebookLM)

Gemini Notebook (formerly NotebookLM) is Google's hosted research assistant that answers only from the sources you add, with citations, and generates study aids such as audio and video overviews, flashcards, quizzes, mind maps, and slide decks. OpenMAIC also starts from your material or a topic, but its output is a taught lesson: AI teachers and classmates narrate slides, run quizzes and simulations, draw on a whiteboard, and discuss with you, and you can host, modify, and export it. Pick Gemini Notebook for cited research and quick study aids with no setup, and OpenMAIC for an interactive, multi-agent class or for building courses on infrastructure you control.

Frequently asked questions

What is OpenMAIC?

OpenMAIC (Open Multi-Agent Interactive Classroom) is an open-source platform from Tsinghua University's THU-MAIC group that turns a topic or uploaded documents into an interactive lesson. Multiple AI agents act as teachers and classmates, delivering narrated slides, quizzes, simulations, and project-based activities, drawing on a whiteboard, and discussing the material with you.

Is OpenMAIC free and open source?

Yes. OpenMAIC is released under the MIT license, which permits commercial use, after moving from AGPL-3.0 in v0.3.0. The software is free; if you self-host, you pay only for the model, media, and search providers you connect, or nothing beyond your hardware with local providers.

Can I try OpenMAIC without installing it?

Yes. The OpenMAIC team hosts a Live Demo at open.maic.chat. After signing in, you can generate an access code in your account settings to use it from the OpenMAIC skill or API, where generation is limited to 10 per day. The repository does not document pricing or terms for the demo.

What do I need to self-host OpenMAIC?

Node.js 22.19 or newer, pnpm 10 or newer, a PostgreSQL 16 database, and at least one LLM provider key with a model that supports tool calling, or the bundled Docker Compose stack, which runs the app and PostgreSQL on 127.0.0.1 by default. Since v1.2.0 it needs a long-running server; Vercel and other serverless hosts are only supported on the 1.1.x branch. Set a long random ACCESS_CODE before exposing it to other machines, enable the Pro agent workbench with its flags if you want it, and configure an E2B-compatible sandbox and S3-compatible storage only if you want PBL v3.

Can OpenMAIC run with local models?

Yes. It supports Ollama and Lemonade for local LLMs, Lemonade for local image generation, text-to-speech, and speech recognition, FunASR for local speech recognition, and a self-hosted VoxCPM2 text-to-speech backend with voice cloning. Lesson quality then depends on the local models you choose.

Does OpenMAIC work with OpenClaw?

Yes. OpenMAIC ships a SKILL.md skill that installs in OpenClaw with clawhub install openmaic and can be imported into Codex, DeepSeek, WorkBuddy, and other agent workbenches. It walks you through using the Live Demo or a local install, submits generation jobs, and sends you the classroom link, asking for confirmation before state-changing steps.

OpenMAIC vs Gemini Notebook: what is the difference?

Gemini Notebook (formerly NotebookLM) answers questions about your sources with citations and turns them into study aids such as audio and video overviews, flashcards, quizzes, and mind maps. OpenMAIC turns a topic or your materials into a full interactive lesson delivered by multiple AI agents, with simulations, project-based activities, and a whiteboard, and it is open source and self-hostable.

Integrations & fit

OpenClawCodexOpenAIAzure OpenAIAnthropicAmazon BedrockGoogle GeminiDeepSeekQwenKimiMiniMaxGrokOpenRouterGLMDoubaoOllamaLemonadeFunASRVoxCPM2ElevenLabsMinerUTavilyExaBrave SearchSearXNGFirecrawlComfyUIPostgreSQLAmazon S3DockerE2BPowerPoint
Good fit forSolo / individual, Startup / small team
Pricing modelFree· No cost to start
See pricing on OpenMAIC →

Alternatives to consider

About OpenMAIC

OpenMAIC (Open Multi-Agent Interactive Classroom) is a Next.js web application from Tsinghua University's THU-MAIC group, whose research appears in the group's JCST 2026 paper "From MOOC to MAIC". You describe what you want to learn, or attach PDFs, Word, PowerPoint, spreadsheet, image, audio, or video files, and a two-stage pipeline writes a lesson outline and then turns each item into a scene: narrated slides, quizzes with AI grading, HTML simulations, or a project-based learning (PBL) activity where you take a role alongside AI agents. Deep Interactive Mode adds 3D visualizations, simulations, games, mind maps, and in-browser programming. During playback, a cast of AI agents lectures with voice, uses a spotlight and laser pointer, draws on a shared whiteboard, starts discussions, and runs roundtable debates; the classroom chat runs on an agent loop (always since v1.2.1, which requires a model with tool calling) that can read the lesson, check the live state of an experiment, and search the web before answering. Version 1.0.0 added a Pro agent workbench for course builders: a chat agent that plans multi-lesson curricula, builds and revises pages from your materials, imports .pptx decks, and generates images, video, and narration, with durable server-backed sessions you can cancel, resume, and steer, and a library of 24 built-in teaching skills. Since v1.2.0 the app is server-first: generation runs on the server and survives closed tabs, and courses, media, and provider settings are stored in PostgreSQL rather than the browser. v1.3.0 added a knowledge base that keeps every upload in the owner's library, parsed once and searchable by the agent, and v1.4.0 added PBL v3, runnable Python and Java projects with an IDE, a terminal, and an AI tutor, which needs an experimental E2B-compatible sandbox. Lessons export to editable PowerPoint, a single offline HTML file, a classroom ZIP, or MP4. A SKILL.md package lets OpenClaw, Codex, and other agent workbenches generate classrooms from chat. What sets it apart from document tools such as Gemini Notebook is that it produces a taught, multi-agent class rather than answers, summaries, and study aids, and that you can host and modify all of it. The tradeoffs: self-hosting means running PostgreSQL on a long-running server (Vercel and other serverless hosts are unsupported from v1.2.0) and bringing your own model keys (or local models), the best results need image, voice, video, and search providers configured, there are no built-in user accounts, and the hosted Live Demo is capped, with no pricing or terms documented in the repository.

Updates from OpenMAIC

New Featurev1.4.0: PBL v3 runnable projects

Project-based learning v3 lets learners build and run Python or Java projects with an AI tutor, an IDE, a terminal, milestone tests, and a learning report. It runs on a new experimental shared sandbox and stays off until a sandbox provider is configured; generating PBL v3 projects is not available yet. v1.4.2 (2026-11-09) added course-level undo and opened sandboxes to every admitted owner.

New Featurev1.3.0: knowledge base

Every upload now stays in its owner's knowledge base until deleted, organized in folders and parsed once for every conversation, and the agent can read, search, and organize it. The Pro workbench gained a preview before the first page exists and Learn and Edit tabs. The upgrade is one-way.

Milestonev1.2.0: server-first, with classroom export

Generation moved to the server and survives closed tabs and restarts, courses and settings are stored in PostgreSQL, and models are configured once in openmaic.yml with optional locks. New exports: a PowerPoint that keeps every scene and a single offline HTML file. Vercel and other serverless hosts are no longer supported.

Updatev1.1.2 security release

Server-side requests to caller-supplied provider URLs now connect only to validated addresses and refuse redirects, and error responses no longer echo provider responses. It followed v1.1.1, which hardened MinerU Cloud document parsing.

New Featurev1.1.0: classroom chat on an agent loop

Classroom chat moved to an agent loop by default, so learners can ask about a specific slide element, interactive component, or whiteboard drawing, and the teacher can read the lesson, check an experiment's live state, and search the web. Settings were rebuilt with a model choice per generation step and Token Plan connections.

Launchv1.0.0: agent workbench for building courses

OpenMAIC 1.0 added a Pro workbench where a chat agent plans curricula and builds and revises pages from uploaded materials, with durable server-backed sessions, 20 built-in skills at launch, provider-neutral server configuration, and pluggable storage.

Milestonev0.3.0: relicensed to MIT

Version 0.3.0 moved the project from AGPL-3.0 to the MIT license and added Project-Based Learning v2, an Edit with AI editor agent, and the @openmaic/* SDK packages on npm.

Are you the founder? Claim this listing →