THU-MAIC/OpenMAICPublic

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click

AI summary: Immersive, multi-agent interactive learning experience environment in a single click.

Stars
43.8K
+324 today
Forks
6.8K
Watchers
178
Open issues
178
Open PRs
30
Contributors
~126
Commits
871
Branches
359
Views (30d)
9

TypeScriptMITCreated Mar 11, 2026Last push 3d agoLatest release v1.4.2+615 stars this week+2.8K this month

Quick answers

What is OpenMAIC?
Immersive, multi-agent interactive learning experience environment in a single click.
What does OpenMAIC do?
OpenMAIC is a multi-agent interactive classroom environment designed to provide immersive learning experiences. It leverages large language models to simulate different personas, such as a teacher and diverse students, within a virtual classroom. Users can participate in these simulated environments to learn new subjects through interactive dialogue and role-play. The platform focuses on making the setup process as simple as a single click. It explores the educational applications of autonomous agents interacting dynamically with human users.
Who is OpenMAIC for?
Educators, AI researchers, and developers exploring the use of multi-agent systems in educational contexts. It provides a ready-to-use framework for creating immersive, conversational learning environments.
How popular is OpenMAIC on GitHub?
THU-MAIC/OpenMAIC has 43,830 stars and 6,750 forks on GitHub, and gained 615 stars in the last 7 days.
What license does OpenMAIC use?
THU-MAIC/OpenMAIC is released under the MIT license.

Star history

since Jul 28, 2026
020K40KJul 2026Sep 2026Oct 2026Nov 2026
43.8K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

4 recorded
  • Nov 10, 2026New release v1.4.2 (previously v1.3.0).
  • Oct 31, 2026New release v1.3.0 (previously v1.2.1).
  • Oct 22, 2026New release v1.2.1 (previously v1.1.3).
  • Oct 10, 2026New release v1.1.3 (previously v1.1.2).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-16: 0 commits2025-11-17: 0 commits2025-11-18: 0 commits2025-11-19: 0 commits2025-11-20: 0 commits2025-11-21: 0 commits2025-11-22: 0 commits2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 13 commits2026-03-13: 14 commits2026-03-14: 7 commits2026-03-15: 2 commits2026-03-16: 10 commits2026-03-17: 3 commits2026-03-18: 5 commits2026-03-19: 4 commits2026-03-20: 3 commits2026-03-21: 7 commits2026-03-22: 5 commits2026-03-23: 3 commits2026-03-24: 10 commits2026-03-25: 6 commits2026-03-26: 7 commits2026-03-27: 2 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 5 commits2026-03-31: 1 commit2026-04-01: 2 commits2026-04-02: 2 commits2026-04-03: 0 commits2026-04-04: 4 commits2026-04-05: 0 commits2026-04-06: 1 commit2026-04-07: 2 commits2026-04-08: 0 commits2026-04-09: 2 commits2026-04-10: 0 commits2026-04-11: 3 commits2026-04-12: 3 commits2026-04-13: 3 commits2026-04-14: 2 commits2026-04-15: 3 commits2026-04-16: 5 commits2026-04-17: 0 commits2026-04-18: 3 commits2026-04-19: 5 commits2026-04-20: 1 commit2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 3 commits2026-04-24: 1 commit2026-04-25: 3 commits2026-04-26: 4 commits2026-04-27: 2 commits2026-04-28: 2 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 4 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 1 commit2026-05-09: 2 commits2026-05-10: 2 commits2026-05-11: 1 commit2026-05-12: 1 commit2026-05-13: 3 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 2 commits2026-05-18: 1 commit2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 1 commit2026-05-22: 1 commit2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 1 commit2026-05-26: 0 commits2026-05-27: 3 commits2026-05-28: 0 commits2026-05-29: 2 commits2026-05-30: 1 commit2026-05-31: 4 commits2026-06-01: 3 commits2026-06-02: 4 commits2026-06-03: 1 commit2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 2 commits2026-06-07: 4 commits2026-06-08: 4 commits2026-06-09: 3 commits2026-06-10: 1 commit2026-06-11: 1 commit2026-06-12: 0 commits2026-06-13: 1 commit2026-06-14: 2 commits2026-06-15: 6 commits2026-06-16: 3 commits2026-06-17: 3 commits2026-06-18: 1 commit2026-06-19: 0 commits2026-06-20: 0 commits2026-06-21: 0 commits2026-06-22: 1 commit2026-06-23: 2 commits2026-06-24: 5 commits2026-06-25: 1 commit2026-06-26: 5 commits2026-06-27: 1 commit2026-06-28: 4 commits2026-06-29: 4 commits2026-06-30: 5 commits2026-07-01: 9 commits2026-07-02: 3 commits2026-07-03: 5 commits2026-07-04: 0 commits2026-07-05: 3 commits2026-07-06: 3 commits2026-07-07: 1 commit2026-07-08: 5 commits2026-07-09: 4 commits2026-07-10: 4 commits2026-07-11: 10 commits2026-07-12: 2 commits2026-07-13: 7 commits2026-07-14: 10 commits2026-07-15: 2 commits2026-07-16: 4 commits2026-07-17: 2 commits2026-07-18: 0 commits2026-07-19: 0 commits2026-07-20: 1 commit2026-07-21: 1 commit2026-07-22: 2 commits2026-07-23: 2 commits2026-07-24: 2 commits2026-07-25: 1 commit2026-07-26: 2 commits2026-07-27: 5 commits2026-07-28: 1 commit2026-07-29: 2 commits2026-07-30: 5 commits2026-07-31: 1 commit2026-08-01: 2 commits2026-08-02: 2 commits2026-08-03: 9 commits2026-08-04: 2 commits2026-08-05: 8 commits2026-08-06: 6 commits2026-08-07: 1 commit2026-08-08: 1 commit2026-08-09: 4 commits2026-08-10: 6 commits2026-08-11: 4 commits2026-08-12: 9 commits2026-08-13: 1 commit2026-08-14: 2 commits2026-08-15: 3 commits2026-08-16: 3 commits2026-08-17: 3 commits2026-08-18: 3 commits2026-08-19: 4 commits2026-08-20: 1 commit2026-08-21: 1 commit2026-08-22: 2 commits2026-08-23: 2 commits2026-08-24: 7 commits2026-08-25: 2 commits2026-08-26: 5 commits2026-08-27: 6 commits2026-08-28: 4 commits2026-08-29: 2 commits2026-08-30: 2 commits2026-08-31: 3 commits2026-09-01: 6 commits2026-09-02: 10 commits2026-09-03: 6 commits2026-09-04: 6 commits2026-09-05: 1 commit2026-09-06: 3 commits2026-09-07: 0 commits2026-09-08: 2 commits2026-09-09: 1 commit2026-09-10: 0 commits2026-09-11: 19 commits2026-09-12: 1 commit2026-09-13: 4 commits2026-09-14: 7 commits2026-09-15: 15 commits2026-09-16: 3 commits2026-09-17: 8 commits2026-09-18: 9 commits2026-09-19: 5 commits2026-09-20: 13 commits2026-09-21: 4 commits2026-09-22: 10 commits2026-09-23: 9 commits2026-09-24: 3 commits2026-09-25: 0 commits2026-09-26: 1 commit2026-09-27: 5 commits2026-09-28: 7 commits2026-09-29: 6 commits2026-09-30: 0 commits2026-10-01: 1 commit2026-10-02: 3 commits2026-10-03: 0 commits2026-10-04: 4 commits2026-10-05: 1 commit2026-10-06: 5 commits2026-10-07: 10 commits2026-10-08: 5 commits2026-10-09: 3 commits2026-10-10: 7 commits2026-10-11: 6 commits2026-10-12: 3 commits2026-10-13: 6 commits2026-10-14: 3 commits2026-10-15: 0 commits2026-10-16: 9 commits2026-10-17: 1 commit2026-10-18: 10 commits2026-10-19: 4 commits2026-10-20: 3 commits2026-10-21: 8 commits2026-10-22: 6 commits2026-10-23: 10 commits2026-10-24: 0 commits2026-10-25: 0 commits2026-10-26: 3 commits2026-10-27: 18 commits2026-10-28: 13 commits2026-10-29: 12 commits2026-10-30: 4 commits2026-10-31: 0 commits2026-11-01: 1 commit2026-11-02: 3 commits2026-11-03: 9 commits2026-11-04: 9 commits2026-11-05: 12 commits2026-11-06: 15 commits2026-11-07: 0 commits2026-11-08: 2 commits2026-11-09: 8 commits2026-11-10: 2 commits2026-11-11: 0 commits2026-11-12: 0 commits2026-11-13: 0 commits2026-11-14: 0 commits
852 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    43,830 stars

  • Very active

    852 commits in 52 weeks

  • Community-driven

    ~126 contributors

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    48 trending appearances

What OpenMAIC does

OpenMAIC is a multi-agent interactive classroom environment designed to provide immersive learning experiences. It leverages large language models to simulate different personas, such as a teacher and diverse students, within a virtual classroom. Users can participate in these simulated environments to learn new subjects through interactive dialogue and role-play. The platform focuses on making the setup process as simple as a single click. It explores the educational applications of autonomous agents interacting dynamically with human users.

Educators, AI researchers, and developers exploring the use of multi-agent systems in educational contexts. It provides a ready-to-use framework for creating immersive, conversational learning environments.

  • Multi-agent simulation: Deploys multiple LLM-driven personas to act as teachers and students.
  • Immersive role-play: Allows users to interact directly with the simulated agents to learn concepts.
  • One-click deployment: Simplifies the complex setup of multi-agent systems into a single action.
  • Dynamic interaction: Facilitates real-time, unstructured conversations between agents and the user.
  • Educational focus: Specifically tailors the agent prompts and environment for teaching scenarios.

Where teams use it

Interactive learning

Participate in simulated classrooms to grasp complex topics through discussion rather than reading.

Agent research

Study how multiple language models interact with each other and human users in constrained environments.

Educational tool building

Use the framework as a foundation to build specialized tutoring systems.

Role-play training

Practice conversational or language skills by interacting with specific AI personas.

README

main branch

OpenMAIC Banner

Get an immersive, multi-agent learning experience in just one click

v1.0.0 User Guide (English)    v1.0.0 体验指南(中文)

Paper License: MIT Live Demo OpenClaw Integration Lemonade Local AI Stars
Discord   Feishu Community
Next.js React TypeScript Tailwind CSS

English | Simplified Chinese
Live Demo · Quick Start · Lemonade · FunASR · Features · Use Cases · OpenClaw

🗞️ News

  • 2026-11-10 — v1.5.0-rc.1: A brand-new home, redesigned end to end (release candidate) — the home page becomes the workbench: the course grows beside the conversation, My courses gets folders and pinning, and one full-screen classroom handles learning and editing. Off by default (NEXT_PUBLIC_WORKBENCH_ENABLED).
  • 2026-11-09 — v1.4.2: course-level undo for manual edits and agent runs; sandboxes open to every admitted owner.
  • 2026-11-05 — v1.4.1: edits and learner progress kept through background syncs; faster loading on slow connections.
  • 2026-11-04 — v1.4.0: PBL v3 — build a working project with an AI tutor, milestone by milestone. One-way upgrade.
  • 2026-11-02 — v1.3.1: DeepSeek Token Plan (one key for chat, web search and web fetch) and reliability fixes.
  • 2026-10-29 — v1.3.0: knowledge base — uploads kept, foldered and @-mentionable; one-way upgrade.
  • 2026-10-18 — v1.2.1: web research — Kimi, DeepSeek and Firecrawl search, and a hosted webFetch reader.
  • 2026-10-16 — v1.2.0: server-first is stable — generation survives closed tabs, models live in openmaic.yml, classroom export to PPTX and HTML.
Earlier releases
  • 2026-10-05 — v1.1.3: security — course documents served by /api/persistence carry only sanitized slide HTML (GHSA-6c52-8h4v-5xvg).
  • 2026-09-28 — v1.1.2: security — provider requests connect only to validated addresses and refuse redirects (GHSA-g87c-cm4q-cw5x).
  • 2026-09-27 — v1.1.1: security — hardened MinerU Cloud parsing (GHSA-cpjc-vgjh-c5jp).
  • 2026-09-24 — v1.1.0: agentic classroom chat (ask about any slide element, interactive, or whiteboard drawing); settings rebuilt around the course workflow; Token Plan connections.
  • 2026-09-15 — v1.0.3: security — access-code tokens expire, render-service network policy, pinned audio connections, Next.js RCE patch.
  • 2026-09-14 — v1.0.2: security — SSRF and DNS-rebinding fixes, classroom overwrite fix.
  • 2026-09-06 — v1.0.1: security and stability; tightens two defaults.
  • 2026-08-27 — v1.0.0: agent workbench, durable sessions, reusable skills, session materials, provider-neutral capabilities.
  • 2026-08-14 — v0.3.2: video export hardening, server-backed persistence and asset registry, @openmaic/generation, four new locales, FunASR.
  • 2026-07-21 — v0.3.1: one-click MP4 export, direct slide editing, smarter "Edit with AI", expanded document parsing.
  • 2026-06-28 — v0.3.0: PBL v2, "Edit with AI" editor agent, @openmaic/* SDKs on npm, relicensed to MIT.
  • 2026-06-02 — v0.2.2: MAIC Editor Pro Mode, editable outlines, offline classroom export.
  • 2026-04-26 — v0.2.1: VoxCPM2 TTS with voice cloning, per-model thinking config, course completion page.
  • 2026-04-20 — v0.2.0: Deep Interactive Mode — 3D, simulations, games, mind maps, online programming.
  • 2026-04-14 — v0.1.1: language inference, ACCESS_CODE, classroom ZIP export/import, Ollama.
  • 2026-03-26 — v0.1.0: discussion TTS, immersive mode, keyboard shortcuts.

Full history in the changelog.

📖 Overview

OpenMAIC (Open Multi-Agent Interactive Classroom) is an open-source AI platform that turns any topic or document into a rich, interactive classroom experience. Powered by multi-agent orchestration, it generates slides, quizzes, interactive simulations, and project-based learning activities — all delivered by AI teachers and AI classmates who can speak, draw on a whiteboard, and engage in real-time discussions with you. The built-in OpenMAIC Skill works with OpenClaw as well as agent workbenches such as Codex, DeepSeek, and WorkBuddy, so you can generate classrooms from messaging apps like Feishu, Slack, or Telegram, or right inside your IDE.

v1.0.1.-compressed.mp4

Highlights

  • One-click lesson generation — Describe a topic or attach your materials; the AI builds a full lesson in minutes
  • Multi-agent classroom — AI teachers and peers lecture, discuss, and interact with you in real time
  • Rich scene types — Slides, quizzes, interactive HTML simulations, and project-based learning (PBL)
  • Whiteboard & TTS — Agents draw diagrams, write formulas, and explain out loud
  • Export anywhere — A .pptx that keeps every scene, one offline .html file that plays the whole lesson, or a classroom ZIP to move it to another deployment
  • Agent workbench integration — The OpenMAIC Skill supports OpenClaw, Codex, DeepSeek, WorkBuddy, and more — generate classrooms from Feishu, Slack, Telegram, 20+ messaging apps, or your IDE

🚀 Quick Start

Prerequisites

  • Node.js >= 22.19
  • pnpm >= 10
  • PostgreSQL 16 — courses are stored on the server. For local development pnpm db:up starts one in Docker for you.

1. Clone & Install

git clone https://github.com/THU-MAIC/OpenMAIC.git
cd OpenMAIC
pnpm install

2. Configure

cp .env.example .env.local            # API keys and server options
cp openmaic.example.yml openmaic.yml  # which models the server uses

The copied example needs only OPENAI_API_KEY in .env.local (or change its provider to one you have a key for); everything else in it is commented out until you want it. openmaic.yml declares providers (accounts the server can call) and gives each slot (a use of AI: the outline, slide content, text to speech, web search, …) a model. Keys stay in .env.local and are referenced as ${VAR}:

providers:
  openai:
    preset: openai
    apiKey: ${OPENAI_API_KEY}      # OPENAI_API_KEY=sk-... in .env.local
  anthropic:
    preset: anthropic
    apiKey: ${ANTHROPIC_API_KEY}

slots:
  llm: openai:gpt-5.5              # the default chat model
  course.outline: anthropic:claude-sonnet-4-6
  video: null                      # turn a capability off

The slots you write are the server's defaults; users can change them, or connect services of their own, in the app's model settings unless you lock them or set allowUserKeys: false. The server validates the file at startup and names every mistake by its field (or, for broken YAML, its line).

To learn about Read
Slots, presets, fallbacks, lock, allowUserKeys, OPENMAIC_SECRET_KEY Configuration
Every provider preset and model ID Supported models
Upgrading: provider variables, server-providers.yml, DEFAULT_MODEL and MODEL_FALLBACK still work without openmaic.yml; MODEL_ROUTES must become slots Migrating from the legacy configuration
Which models users may pick: a provider whose key the server holds and that selects an upstream model offers only the models in its models list (*_MODELS), plus the slot, default and fallback models Model authorization

Providers: OpenAI, Azure OpenAI, Anthropic, Amazon Bedrock, Google Gemini, DeepSeek, Qwen, Kimi, MiniMax, Grok (xAI), OpenRouter, TokenDance, Doubao, Tencent Hunyuan/TokenHub, Xiaomi MiMo, GLM (Zhipu), Ollama, Lemonade and FunASR (local), and any OpenAI-compatible API.

Tip

Recommended setup: OpenMAIC is at its best with every modality turned on — generated illustrations, narration, video clips, web search, and web fetch. A token plan configures the capabilities it supports with one key (see the examples below). Choose a fast long-context model such as deepseek-v4.1-flash as the default.

More examples: token plans, Xiaomi MiMo and GLM, Amazon Bedrock

MiniMax token plan quick example (one key for chat, image, video, TTS and web search; tokendance works the same way):

providers:
  minimax:
    preset: minimax
    apiKey: ${MINIMAX_API_KEY}

slots:
  llm: minimax:MiniMax-M3
  image: minimax                   # a provider id alone: the plan's default model
  video: minimax
  tts: minimax
  webSearch: minimax

TokenDance quick example with a fast long-context default model:

providers:
  tokendance:
    preset: tokendance
    apiKey: ${TOKENDANCE_API_KEY}

slots:
  llm: tokendance:deepseek-v4.1-flash
  image: tokendance
  video: tokendance
  tts: tokendance
  webSearch: tokendance

Xiaomi MiMo Token Plan and GLM (Zhipu) quick example:

providers:
  mimo:
    preset: xiaomi
    apiKey: ${MIMO_API_KEY}
    baseUrl: https://token-plan-cn.xiaomimimo.com/v1
  glm:
    preset: glm
    apiKey: ${GLM_API_KEY}
    baseUrl: https://open.bigmodel.cn/api/paas/v4   # or https://api.z.ai/api/paas/v4

slots:
  llm: mimo:mimo-v2.5-pro
  course.content: glm:glm-5.1

Use https://token-plan-sgp.xiaomimimo.com/v1 or https://token-plan-ams.xiaomimimo.com/v1 for the Singapore or Europe Token Plan clusters.

Amazon Bedrock quick example:

providers:
  bedrock:
    preset: bedrock
    models: [us.anthropic.claude-sonnet-5, us.anthropic.claude-opus-4-8]

slots:
  llm: bedrock:us.anthropic.claude-sonnet-5

Bedrock uses AWS environment credentials or the AWS SDK credential provider chain, with the region from BEDROCK_REGION (for example BEDROCK_REGION=us-east-1 in .env.local). For temporary credentials, set AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and AWS_SESSION_TOKEN, or use an AWS profile / role available to the runtime.

3. Start the database

pnpm db:up

Then uncomment the local DATABASE_URL line in .env.local:

DATABASE_URL=postgres://openmaic:[email protected]:5432/openmaic

pnpm db:up starts a development PostgreSQL on 127.0.0.1:5432 (set OPENMAIC_DB_PORT for another port). It is its own Compose project, openmaic-dev-db, shared by every checkout on this machine, with its own container and volume, so it never touches the database of a docker compose up stack. pnpm db:down stops it and keeps the data. Any other PostgreSQL works too.

4. Run

pnpm dev

Open http://localhost:3000 and start learning! Without a DATABASE_URL the server refuses to start and tells you how to provide one (see Server-backed persistence).

5. Build for Production

pnpm build && DATABASE_URL=postgres://... pnpm start

Keep the server running as a long-running process (a process manager or a container): course generation runs inside it and continues after the browser leaves the page. See the Deployment guide for the required configuration and for upgrading from 1.1.x.

Docker Deployment

cp .env.example .env.local
# Edit .env.local with your API keys, then:
docker compose up --build

Open http://localhost:3000. The stack is two containers, the app and PostgreSQL. Courses, generated media and runtime sessions live in the named volumes openmaic-postgres and openmaic-data, which survive docker compose down and rebuilds; docker compose down -v deletes them. To configure models with openmaic.yml, create it from openmaic.example.yml and uncomment its mount in docker-compose.yml; otherwise connect a model service in the model settings once the app is running.

The Compose file is a personal installation: it runs in single-user mode (every browser sees one shared library) and listens on 127.0.0.1:3000 only. To serve other machines, protect it first:

  1. Set a long random ACCESS_CODE in .env.local (details). Without it, anyone who can reach the port owns, edits and can delete the whole library.

  2. Before the first start, set PERSISTENCE_POSTGRES_PASSWORD to a random value of letters and digits.

  3. Publish on the network address:

    OPENMAIC_PUBLISH_ADDRESS=0.0.0.0 docker compose up -d --build

OPENMAIC_PUBLISH_ADDRESS, OPENMAIC_PORT and PERSISTENCE_POSTGRES_PASSWORD come from your shell or a .env file next to docker-compose.yml, not from .env.local. Overriding the Compose defaults, rotating the database password and the full upgrade notes are in Hosting and identity.

Important

Upgrading a Compose deployment? PostgreSQL now always starts, the app is published on 127.0.0.1 only, and every visitor is the same single owner. If .env.local sets PERSISTENCE_SHARED_OWNER_ID, also set OWNER_SINGLE_USER=false, or the app refuses to start. Read Upgrading a Compose deployment first.

Slow-network / China build acceleration

Docker builds support two optional build arguments. Both are empty by default, so the standard command above keeps using the upstream Alpine and npm registries.

  • ALPINE_MIRROR is an Alpine mirror hostname without https://.
  • NPM_REGISTRY is a complete npm registry URL.

Use public mirror endpoints only. Do not embed usernames, passwords, or access tokens in these build arguments because Docker may record them in image metadata or build provenance.

With Docker Compose:

ALPINE_MIRROR=mirrors.tuna.tsinghua.edu.cn \
NPM_REGISTRY=https://registry.npmmirror.com \
docker compose up --build

For a direct image build:

docker build \
  --build-arg ALPINE_MIRROR=mirrors.tuna.tsinghua.edu.cn \
  --build-arg NPM_REGISTRY=https://registry.npmmirror.com \
  -t openmaic:local .

These arguments do not accelerate Docker Hub pulls, including the Dockerfile frontend and the node:22-alpine base image. Configure a Docker daemon registry mirror separately if those pulls are slow. The pnpm store cache is reused by the same BuildKit builder across builds, subject to normal cache garbage collection; the cache only improves performance and is not required for a correct build.

Vercel Deployment (up to 1.1.x)

Serverless deployment is supported up to OpenMAIC 1.1.x. From 1.2.0, course generation runs on the server in a process that outlives requests, so OpenMAIC needs a long-running Node.js process with PostgreSQL (the Docker deployment or pnpm start); Vercel and other serverless hosts are not supported, and the repository no longer ships a vercel.json. To deploy 1.1.x on Vercel:

  1. Fork this repository on GitHub, unchecking Copy the main branch only.
  2. In the fork, set the default branch to release/1.1.x (Settings → General → Default branch).
  3. In Vercel, Add New → Project and import the fork. Vercel builds its default branch; configure at least one LLM provider key as described in that branch's .env.example.

Such a deployment can move to a long-running host later without losing data: point the new host's DATABASE_URL at the database it used, if it used one, and serve it at the same address, since browsers keep their data per site; the courses visitors kept in their browsers are imported the first time each browser opens the upgraded app. See Upgrading from 1.1.x for every kind of deployment.

Server-backed persistence (PostgreSQL)

OpenMAIC keeps courses on the server. Course documents, folders, chat history, learner sessions and generated media live in PostgreSQL (media optionally in S3), served by the app itself at /api/persistence. The browser keeps only what belongs to the device, such as settings, playback position and caches; Settings → Clear Local Cache never touches the server.

  • DATABASE_URL is required. Without it the server prints the fix and exits with code 1. Compose sets it for you; for development, pnpm db:up starts a database.
  • Courses an older build kept in the browser are imported once per browser, automatically, the first time it opens the upgraded app. The browser copy is left untouched.
  • Invalid settings stop the server at startup with a one-line [boot] reason instead of a server that answers every request with 500.

Who owns a course. Every request resolves to an owner, and each owner has its own library. Pick one identity mode:

Mode Set Library
Single user (Compose default) OWNER_SINGLE_USER=true One library for everyone who can reach the server; guard it with ACCESS_CODE or loopback
Shared team PERSISTENCE_SHARED_OWNER_ID=<id> together with ACCESS_CODE One library for the team behind the access code
Anonymous (default without either) nothing One library per browser cookie; a second browser sees an empty one
Your own accounts owner auth methods registered in instrumentation.ts One library per signed-in account

Set the mode before the first start of 1.2.0: classrooms that 1.1.x saved as files are imported for the owner configured then. See Upgrading from 1.1.x for every kind of deployment.

Running OpenMAIC for other people, or embedding it in your own product? Hosting and identity covers:

Optional: ACCESS_CODE (Shared Deployments)

Protect a deployment with a site-level password in .env.local:

ACCESS_CODE=your-secret-code

Use a long random value, at least 16 characters from a random generator: it is the only secret guarding the deployment. Visitors then see a password prompt, and every API route is gated too. When it is unset (the default in .env.example), middleware.ts checks no credential and every route, the API included, is reachable: an unconfigured deployment is not gated, and there is no second enforcement point. The code is remembered for 7 days in a signed HTTP-only cookie; attempts are rate limited only behind a trusted proxy with TRUST_PROXY_HEADERS=true. See Configuration → ACCESS_CODE.

Optional: Agent workbench and runtime

The workbench, a course-building surface entered from the home page, is off by default. Turn on its build-time entry point and the server runtime; it uses the same PostgreSQL as the rest of the app:

NEXT_PUBLIC_WORKBENCH_ENABLED=true
OPENMAIC_AGENT_RUNTIME_ENABLED=true
DATABASE_URL=postgres://openmaic:openmaic-dev@postgres:5432/openmaic

The agent runs on the agent slot, which follows the default chat model unless assigned and needs a model with tool calling:

slots:
  llm: openai:gpt-5.5
  agent:
    model: openai:gpt-5.5
    api: openai-completions        # or openai-responses

The agent slot must not set thinking.effort. Its routes, the DEFAULT_MODEL caveat and runner tuning are in Hosting and identity.

Optional: Lemonade (Local AI Provider)

OpenMAIC supports Lemonade as a local, OpenAI-compatible provider for LLMs, image generation, TTS, and ASR. No API key is required.

Run Lemonade locally, then point OpenMAIC to it:

providers:
  lemonade:
    preset: lemonade
    baseUrl: http://localhost:13305/v1
  lemonade-tts:
    preset: lemonade-tts
    baseUrl: http://localhost:13305/v1
  lemonade-asr:
    preset: lemonade-asr
    baseUrl: http://localhost:13305/v1
  lemonade-image:
    preset: lemonade-image
    baseUrl: http://localhost:13305/v1

slots:
  llm: lemonade:Gemma-4-26B-A4B-it-GGUF
  tts: lemonade-tts
  asr: lemonade-asr
  image: lemonade-image

With the legacy variables, the same is LEMONADE_BASE_URL, TTS_LEMONADE_BASE_URL, ASR_LEMONADE_BASE_URL and IMAGE_LEMONADE_BASE_URL.

Optional: FunASR (Local Speech Recognition)

OpenMAIC can transcribe locally through FunASR's OpenAI-compatible server. The built-in provider supports SenseVoiceSmall, Paraformer, and Fun-ASR-Nano and requires no API key.

python -m pip install torch torchaudio
python -m pip install "funasr==1.4.0" fastapi uvicorn python-multipart
# Add vLLM for Fun-ASR-Nano on NVIDIA GPUs
python -m pip install vllm
funasr-server --device cuda --model fun-asr-nano

Point OpenMAIC at the server:

providers:
  funasr:
    preset: funasr-asr
    baseUrl: http://localhost:8000/v1

slots:
  asr: funasr

(Legacy variable: ASR_FUNASR_BASE_URL=http://localhost:8000/v1.)

Use funasr-server --device cpu --model sensevoice for a CPU-only setup. See the FunASR deployment guide for production options.

Optional: Local Audio and Video Extraction

OpenMAIC can extract timestamped transcripts and prepared video keyframes locally. Install the system ffmpeg package so both ffmpeg and ffprobe are executable on PATH, then assign the asr slot (for example FunASR, Lemonade, or OpenAI) as above. The application resolves the executables at extraction time; ffmpeg is not an npm dependency and is not required to start or use OpenMAIC.

If the executables are unavailable, the local extractor is skipped. A configured AliDocMind provider remains available as the cloud extraction path. When neither local ffmpeg extraction nor AliDocMind is available, audio/video materials are marked failed with an actionable setup message instead of hanging or completing with an empty transcript.

Optional: MP4 Video Export (Render Service)

The "Export Video" menu builds a self-contained Hyperframes project entirely in the browser. Turning that into an MP4 needs Chromium + FFmpeg on Node 22, so it runs in an isolated render-service container rather than the app.

It's opt-in. Start it with the video-export compose profile:

docker compose --profile video-export up --build

The app auto-detects the service via RENDER_SERVICE_URL (preset in docker-compose.yml) and enables one-click MP4 rendering. Without the profile — or when RENDER_SERVICE_URL is unset — export degrades to downloading the project ZIP for local CLI rendering. See render-service/README.md for standalone setup and tuning (RENDER_MAX_CONCURRENCY, etc.). When upgrading, upgrade the render-service together with the app or before it: render jobs are bound to their owner, and a mix of old and new versions fails closed.

Optional: MinerU (Advanced Document Parsing)

MinerU provides enhanced parsing for complex tables, formulas, and OCR. You can use the MinerU official API or self-host your own instance.

Declare it in openmaic.yml and assign the document slot to it: mineru-cloud for the official API, or mineru with the baseUrl of your own instance.

providers:
  mineru:
    preset: mineru-cloud
    apiKey: ${PDF_MINERU_CLOUD_API_KEY}

slots:
  document: mineru

Without openmaic.yml, the legacy variables PDF_MINERU_CLOUD_API_KEY or PDF_MINERU_BASE_URL in .env.local still work.

Optional: VoxCPM2 (Self-Hosted TTS with Voice Cloning)

VoxCPM2 is an open-source TTS model from OpenBMB with voice cloning. OpenMAIC ships an adapter; run VoxCPM on your own hardware and OpenMAIC will talk to it.

1. Run a VoxCPM backend. Three deployment styles, all behind the same OpenMAIC adapter. You pick which one with options.backend in openmaic.yml (step 2).

Backend Endpoint When to use
vLLM-Omni /v1/audio/speech OpenAI-compatible speech endpoint, ideal for GPU servers
Python API /tts/upload Official VoxCPM Python runtime via FastAPI
Nano-vLLM /generate Lightweight Nano-vLLM FastAPI deployment

See the VoxCPM repo for backend setup.

2. Point OpenMAIC at it. VoxCPM2 runs on your own network, so the deployment configures it in openmaic.yml (no API key required); workspaces cannot add it in Settings → Model Services:

providers:
  voxcpm:
    preset: voxcpm-tts
    baseUrl: http://localhost:8000/v1
    options:
      backend: vllm-omni          # vllm-omni (default) | python-api | nano-vllm

slots:
  tts: voxcpm

Voice registration works only on the vllm-omni backend; python-api and nano-vllm send the voice prompt with each request.

Without openmaic.yml, the legacy TTS_VOXCPM_BASE_URL=http://localhost:8000/v1 sets the endpoint but cannot choose a backend.

3. Manage voices. With VoxCPM2 assigned to the tts slot, open Settings → Model Services → Text-to-Speech → VoxCPM2 (the voice manager appears only when tts resolves to a voxcpm-tts provider). Three voice modes:

VoxCPM2 VoxCPM Voices section with Auto, Prompt and Clone modes

  • Auto Voice (default): OpenMAIC generates a voice prompt from each agent's persona at synthesis time. No setup required.
  • Prompt voice: describe the voice in natural language, e.g. "warm female teacher voice, calm and encouraging, mid-pitch".
  • Clone voice: upload a short reference audio clip or record one in the browser. The clip is stored in this browser (IndexedDB) and sent to your VoxCPM backend on each synthesis.

✨ Features

Agent Workbench (v1.0.0)

The workbench adds a conversational course-building agent to OpenMAIC. Its durable sessions can be resumed after a worker restart, accept follow-up instructions while running, and stream a replayable event history to the chat surface.

Where it is enabled, the workbench is the home page (/, also at /workspace). Its rail carries search, My courses, the knowledge base, the conversation and course lists, and an account menu with the language, theme, model settings and project links; beside it sit a chat pane and a classroom pane whose open courses stay in tabs. A classroom opens full screen with Learn | Edit, and a standalone classroom page opens in the workspace from its collapse button. Every entry remains gated by the public workbench flag plus the configured server runtime; with it off, the classic home page is unchanged.

The agent works through explicit, validated tools rather than editing opaque blobs:

Area Capabilities
Plan and organize Plan multi-lesson curricula; create courses and folders; rename and move courses
Build and edit Read/search the stage DSL; atomically patch one scene; generate, duplicate, insert, delete, and reorder pages; edit narration and deck structure
Use materials Upload files; extract documents, audio, and video; search extracted text; fetch trusted web URLs; reuse material media
Create media Generate images and videos through configured server providers; generate narration audio
Import and inspect Import .pptx slides with their layout preserved; render scene previews for visual inspection when available
Configure the classroom List available voices, set the agent roster, and clone/register a voice when a pluggable registration adapter is configured

Twenty-four built-in skills cover curriculum planning, deep research, interactive, lecture, workshop, vocational, and other teaching styles, slide/stage craft, PPTX import, editing, and style reuse. User-authored skills are stored per owner and can be created, read, and patched through the same runtime.

The server-backed workbench also exposes owner-scoped folder routes and a per-viewer stage metadata sidecar for ownership, publication, and generation-complete state. A stage ID acts as the capability for reading a non-deleted course, but stage mutations remain restricted to its owner. The material upload contract stores supported source bytes before lease-fenced document or media extraction records derived text and images; media extraction can select AliDocMind or the optional local ffmpeg/ffprobe provider.

Under the hood, agent sessions are database-backed with leases, heartbeats, crash resume, cancellation, and follow-up steering, and database-maintained revision counters keep per-stage and per-scene freshness monotonic so the workbench refetches only the scenes that changed. Server routes resolve LLM, media, ASR/TTS, and search configuration provider-neutrally: credentials never reach the browser, uniform <CAP>_<PREFIX>_ENABLED=false switches can force off any served capability, startup validation warns about bad model configuration, and unresolved model routes fail loudly instead of guessing a vendor.

Pluggable Storage

OpenMAIC stores course documents, learner runtime records and assets on the server, in PostgreSQL. The @openmaic/storage package defines swappable stores for those primitives — PostgreSQL-backed documents, learner runtime, assets, durable agent sessions, session materials, and user skills, plus browser implementations for embedders — and HTTP clients connect the browser to the embedded persistence endpoint, while the server asset layer can keep bytes in PostgreSQL or S3. Device-scoped KV values (settings, playback position) stay in the browser.

Deep Interactive Mode (New!)

Passive listening? ❌ Hands-on exploration! ✅

As Einstein said: "Play is the highest form of research."

While Standard Mode focuses on quickly generating classroom content, Deep Interactive Mode goes further — creating interactive, explorable, hands-on learning experiences. Students don't just watch knowledge; they adjust experiments, observe simulations, and actively explore how things work.

Five Types of Interactive UI

🌐 3D Visualization

Three-dimensional visual representations that make abstract structures more intuitive.

⚙️ Simulation

Process simulations and experimental environments for observing dynamic changes and outcomes.

🎮 Game

Knowledge-based mini-games that reinforce understanding and memory through interactive challenges.

🧭 Mind Map

Structured knowledge organization to help learners build an overall conceptual framework.

💻 Online Programming

In-browser coding and instant execution for learning by writing, testing, and iterating.

AI Teacher Guidance

The AI teacher can actively operate the UI to guide students — highlighting key areas, setting conditions, providing hints, and directing attention at the right moments.

Available on Any Device

All generated interactive UI is fully responsive — desktop, tablet, or mobile.

Desktop

Mobile

iPad

Need a More Complete and Professional UI Generation Experience?

If you are looking for a version with richer functionality, stronger interactivity, and deeper optimization for high-quality educational UI production, please visit MAIC-UI.

Lesson Generation

Describe what you want to learn or attach reference materials. PDF, Word, PowerPoint, spreadsheet, text, image, audio, and video inputs can enter the material pipeline; configured extractors turn supported sources into content for generation. OpenMAIC's classic two-stage pipeline handles the rest:

Stage What Happens
Outline AI analyzes your input and generates a structured lesson outline
Scenes Each outline item becomes a rich scene — slides, quizzes, interactive modules, or PBL activities

Classroom Components

🎓 Slides

AI teachers deliver lectures with voice narration, spotlight effects, and laser pointer animations — just like a real classroom.

🧪 Quiz

Interactive quizzes (single / multiple choice, short answer) with real-time AI grading and feedback.

🔬 Interactive Simulation

HTML-based interactive experiments for visual, hands-on learning — physics simulators, flowcharts, and more.

🏗️ Project-Based Learning (PBL)

Choose a role and collaborate with AI agents on structured projects with milestones and deliverables.

Multi-Agent Interaction

  • Classroom Discussion — Agents proactively initiate discussions; you can jump in anytime or get called on
  • Roundtable Debate — Multiple agents with different personas discuss a topic, with whiteboard illustrations
  • Q&A Mode — Ask questions freely; the AI teacher responds with slides, diagrams, or whiteboard drawings
  • Whiteboard — AI agents draw on a shared whiteboard in real time — solving equations step by step, sketching flowcharts, or illustrating concepts visually.

Agent Workbench Integration

The OpenMAIC skill package (skills/openmaic/) uses the standard SKILL.md format and can be loaded by various agent workbenches — besides OpenClaw, this includes Codex, DeepSeek, WorkBuddy, and others. It is a guided SOP covering the live demo, local setup, classroom generation, and secondary development on top of the @openmaic/* SDK.

OpenClaw is a personal AI assistant that connects to the messaging platforms you already use (Feishu, Slack, Discord, Telegram, WhatsApp, etc.). With this integration, you can generate and view interactive classrooms directly from your chat app without ever touching a terminal.

Just tell your agent assistant what you want to learn — it handles everything else:

  • Hosted mode — Grab an access code from open.maic.chat, save it in your config, and generate classrooms instantly — no local setup required
  • Self-hosted mode — Clone, install dependencies, configure API keys, and start the server — the skill guides you through each step
  • Track progress — Poll the async generation job and send you the link when ready
  • Secondary development — Guide you through building on top of OpenMAIC: create your own app with the @openmaic/* SDK (see the extend docs inside the skill)

Every step asks for your confirmation first. No black-box automation.

Available on ClawHub — Install with one command:

clawhub install openmaic

Or, in other agent workbenches such as Codex, DeepSeek, or WorkBuddy, import the skills/openmaic/ folder from the repo (or its zipped archive) into the workbench to use it:

Configuration & details
Phase What the skill does
Clone Detect an existing checkout or ask before cloning/installing
Startup Choose between pnpm dev, pnpm build && pnpm start, or Docker
Provider Keys Recommend a provider path; you edit .env.local yourself
Generation Submit an async generation job and poll until it completes

Optional config in ~/.openclaw/openclaw.json:

{
  "skills": {
    "entries": {
      "openmaic": {
        "config": {
          // Hosted mode: paste your access code from open.maic.chat
          "accessCode": "sk-xxx",
          // Self-hosted mode: local repo path and URL
          "repoDir": "/path/to/OpenMAIC",
          "url": "http://localhost:3000"
        }
      }
    }
  }
}

Export

Format Description
PowerPoint (.pptx) Editable slides with images, charts, and LaTeX formulas. Interactive, quiz, and PBL scenes can stay in place as placeholder slides with an Open online button and a QR code
Resource Pack The PPTX plus each interactive scene as a self-contained web page
Offline HTML One file that plays the classroom without a network connection: narration with captions, spotlight and laser, slide video, quizzes and interactive scenes; with or without narration
Classroom ZIP Full classroom export (course structure + media) for backup or sharing

See Exporting a classroom for the options, the ZIP that classrooms over 400 MB are saved as, and opening an exported file on a phone.

Importing a classroom ZIP stores its embedded audio, images, video, and posters in the server asset pool before saving the course, so other browsers resolve those assets without the importing browser's cache. A ZIP is also a way to move a course between deployments: export it from one and import it on the other.

Offline / intranet classrooms: When you export a classroom (.maic.zip) or a Resource Pack, OpenMAIC inlines the external assets referenced by interactive scenes (KaTeX, Three.js incl. three/addons, Tailwind CDN, Google Fonts, images) into the exported HTML as data: URIs. The exported course then plays fully offline after import into an air-gapped/intranet instance — no public CDN is contacted at playback time. Assets that can't be fetched at export time (e.g. CORS-restricted image hosts) are reported and left as URLs. Classrooms exported before this feature still reference CDNs and must be re-exported to gain offline support.

And More

  • Text-to-Speech — Multiple voice providers with customizable voices
  • Speech Recognition — Talk to your AI teacher using your microphone
  • Web Search — Agents search the web for up-to-date information during class
  • Provider controls — Server-side capability discovery, model resolution, force-off switches, and fail-loud routing keep deployments explicit
  • Course freshness — Database-triggered per-scene revision counters, freshness events, and targeted scene fetches keep workbench views synchronized
  • i18n — Interface supports 12 locales across 11 languages: Simplified Chinese, Traditional Chinese, English, Japanese, Korean, Russian, Arabic, Portuguese (Brazil), Spanish (Mexico), French, Vietnamese, and German
  • Dark Mode — Easy on the eyes for late-night study sessions

💡 Use Cases

"Teach me Python from scratch in 30 min"

"How to play the board game Avalon"

"Analyze the stock prices of Zhipu and MiniMax"

"Break down the latest DeepSeek paper"


🤝 Contributing

We welcome contributions from the community! Whether it's bug reports, feature ideas, or pull requests — every bit helps.

Project Structure

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

28 total
  1. 1.5.0-rc.1 is the first release candidate for 1.5.0: **a brand-new home, redesigned end to end.** With the workbench enabled, the home page is the workbench. A request shows a live preview beside the conversation from the moment it is sent, and the preview becomes the course once its first page is saved. A rail without a top bar holds **My courses** (folders, pinning, thumbnails), the knowledge base and a chat list that shows what is running, waiting for an answer or failed. One full-screen classroom handles both learning and editing, and the agent settles one style per course and briefs each slide's design apart from its content. The workbench stays off by default (`NEXT_PUBLIC_WORKBENCH_ENABLED`), and without it the classic home page is unchanged. Some classroom changes apply to every deployment: interactive pages fill the classroom pane and shrink to fit instead of scrolling, a course ends on a closing card instead of an extra completion page, and the dock under the stage can be resized and folded. Read **Breaking Changes** before upgrading: the workbench flag is renamed, and deployments that run the agent runtime get a one-way schema migration. ### Breaking Changes - **`NEXT_

  2. 1.4.2 is a regular patch release. Its main addition is **course-level undo**: one undo/redo line per course that covers manual edits, page add/delete/reorder, narration, titles and agent runs, with buttons in the workbench header and Cmd/Ctrl+Z. It also stops a Director from retrying a failing child agent without end (the 1.4.0 known issue [#2122](https://github.com/THU-MAIC/OpenMAIC/issues/2122)), keeps Pro edits from leaving an interactive page empty, lets `ALLOW_LOCAL_NETWORKS` cover TUN/fake-ip proxies, and carries a batch of PBL v3 fixes plus Java application previews. There are no schema or migration changes over 1.4.1. Read **Behavior Changes** before upgrading: sandboxes are no longer limited to one role, and `ASSET_COLLECTION_GRACE_MS` must stay at 45 minutes or more. ### Behavior Changes - Sandbox: once a deployment enables sandboxes, any owner it admits may use them, including anonymous and shared-team owners; the `sandbox:use` role and the single-user requirement are gone, and `SANDBOX_FORBIDDEN` is no longer returned. Model calls were never gated by identity either. Each owner still reaches only its own sandboxes, files, previews and checkpoints. **On an anonymous p

  3. 1.4.1 is a regular patch release with no upgrade conditions over 1.4.0. Most of it stops edits and learner progress from being lost when a background sync crosses a save, makes courses open quickly again on slow connections, and fixes PBL v3 sandbox cleanup and tutoring. Upgrading from 1.3.x carries the conditions of [1.4.0](https://github.com/THU-MAIC/OpenMAIC/blob/main/CHANGELOG.md#140---2026-11-04), and the 1.4.0 **Known issues** still apply. ### Bug Fixes - PBL: a background course sync no longer empties a PBL v2 project on screen. It used to take the stored design template as it was, and the next whole-document save then recorded the empty state, so the learner's submissions and progress were gone after a reload. [#2184](https://github.com/THU-MAIC/OpenMAIC/pull/2184) - Workbench: a background course sync no longer overwrites a scene edit that has not finished saving, so the edit no longer reverts on screen and the older copy is no longer saved over it. The scene is read again as soon as the save finishes. [#2168](https://github.com/THU-MAIC/OpenMAIC/pull/2168) - Workbench: on a connection Chromium rates 3G or slower, a course no longer takes close to a minute to open and Ed

  4. 1.4.0 is about project-based learning: **PBL v3** is a new way into vibe coding where learners build the project and come away understanding how it works. Concepts become hands-on tasks that the learner gets running, an AI tutor works through requirements, design and implementation with them, each milestone gives feedback and the finished project a personal learning report, and work and progress are kept for the next visit. PBL v3 runs on a new shared sandbox and stays off until a sandbox provider is configured; no new setting is required otherwise. The upgrade is one-way; read **Breaking Changes** before upgrading. ### Breaking Changes - **The upgrade is one-way: stop every 1.3.x instance first, and plan rollback as a database restore.** `@openmaic/storage` 0.39.2 adds asset migration v4 (retained document assets). A 1.4.0 instance applies it when persistence starts: on the first request or, at the latest, on its first schema check about 30 s after boot. [#1979](https://github.com/THU-MAIC/OpenMAIC/pull/1979) [#2151](https://github.com/THU-MAIC/OpenMAIC/pull/2151) - Once v4 is applied, an older release refuses to start against the database (`SchemaVersionAheadError`). Roll bac

  5. 1.3.1 is a regular patch release. DeepSeek joins the Token Plan one-key setup, and most of the rest is reliability: asset uploads no longer hold database connections across slow object stores, requests stop waiting forever for a connection, and edits made just before leaving a page are kept. It has one upgrade condition and one new known issue; read **Breaking Changes** and **Known issues** before upgrading. ### Breaking Changes - **Stop every 1.3.0 instance before 1.3.1 accepts writes, and plan rollback as a database restore.** `@openmaic/storage` 0.39 adds asset migration v3. [#2092](https://github.com/THU-MAIC/OpenMAIC/pull/2092) - Do not run a mixed-version rolling deployment. An old collector does not read the new stage pins, so while both versions run it can delete bytes a new write has just uploaded, and if its own transaction then rolls back, that write can commit an entry naming missing bytes. - Once v3 is applied, a 0.38 instance refuses to start against the database because the schema is newer than it knows. Roll back by restoring the previous database state, not by restarting the old version. - A host that provisions `ASSET_PG_SCHEMA` through its own migrations

Code frequency

additions and deletions
+177.2K-177.2KWeek of 2026-03-08: +177,155 linesWeek of 2026-03-08: -45,960 linesWeek of 2026-03-15: +3,536 linesWeek of 2026-03-15: -596 linesWeek of 2026-03-22: +7,777 linesWeek of 2026-03-22: -1,976 linesWeek of 2026-03-29: +4,601 linesWeek of 2026-03-29: -3,034 linesWeek of 2026-04-05: +2,490 linesWeek of 2026-04-05: -125 linesWeek of 2026-04-12: +9,584 linesWeek of 2026-04-12: -1,378 linesWeek of 2026-04-19: +14,741 linesWeek of 2026-04-19: -7,069 linesWeek of 2026-04-26: +5,490 linesWeek of 2026-04-26: -1,899 linesWeek of 2026-05-03: +4,298 linesWeek of 2026-05-03: -225 linesWeek of 2026-05-10: +4,033 linesWeek of 2026-05-10: -445 linesWeek of 2026-05-17: +1,141 linesWeek of 2026-05-17: -594 linesWeek of 2026-05-24: +3,323 linesWeek of 2026-05-24: -240 linesWeek of 2026-05-31: +22,350 linesWeek of 2026-05-31: -3,272 linesWeek of 2026-06-07: +52,401 linesWeek of 2026-06-07: -1,523 linesWeek of 2026-06-14: +6,564 linesWeek of 2026-06-14: -4,279 linesWeek of 2026-06-21: +98,769 linesWeek of 2026-06-21: -42,003 linesWeek of 2026-06-28: +14,206 linesWeek of 2026-06-28: -1,795 linesWeek of 2026-07-05: +26,431 linesWeek of 2026-07-05: -1,616 linesWeek of 2026-07-12: +48,001 linesWeek of 2026-07-12: -2,835 linesWeek of 2026-07-19: +18,657 linesWeek of 2026-07-19: -1,493 linesWeek of 2026-07-26: +27,577 linesWeek of 2026-07-26: -3,268 linesWeek of 2026-08-02: +46,262 linesWeek of 2026-08-02: -11,606 linesWeek of 2026-08-09: +80,957 linesWeek of 2026-08-09: -24,167 linesWeek of 2026-08-16: +17,880 linesWeek of 2026-08-16: -3,069 linesWeek of 2026-08-23: +148,356 linesWeek of 2026-08-23: -33,939 linesWeek of 2026-08-30: +17,192 linesWeek of 2026-08-30: -2,932 linesWeek of 2026-09-06: +22,389 linesWeek of 2026-09-06: -878 linesWeek of 2026-09-13: +37,650 linesWeek of 2026-09-13: -3,786 linesWeek of 2026-09-20: +23,480 linesWeek of 2026-09-20: -3,700 linesWeek of 2026-09-27: +86,753 linesWeek of 2026-09-27: -37,877 linesWeek of 2026-10-04: +79,412 linesWeek of 2026-10-04: -27,205 linesWeek of 2026-10-11: +16,640 linesWeek of 2026-10-11: -7,406 linesWeek of 2026-10-18: +59,120 linesWeek of 2026-10-18: -4,751 linesWeek of 2026-10-25: +32,511 linesWeek of 2026-10-25: -4,140 linesWeek of 2026-11-01: +109,574 linesWeek of 2026-11-01: -4,810 linesWeek of 2026-11-08: +39,058 linesWeek of 2026-11-08: -14,936 linesMar 8, 2026Nov 8, 2026
+1.4M lines added, -310.8K removed over the last year.

Commits per week

last 52 weeks
510Week of 2025-11-16: 0 commitsWeek of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 34 commitsWeek of 2026-03-15: 34 commitsWeek of 2026-03-22: 33 commitsWeek of 2026-03-29: 14 commitsWeek of 2026-04-05: 8 commitsWeek of 2026-04-12: 19 commitsWeek of 2026-04-19: 13 commitsWeek of 2026-04-26: 8 commitsWeek of 2026-05-03: 7 commitsWeek of 2026-05-10: 7 commitsWeek of 2026-05-17: 5 commitsWeek of 2026-05-24: 7 commitsWeek of 2026-05-31: 14 commitsWeek of 2026-06-07: 14 commitsWeek of 2026-06-14: 15 commitsWeek of 2026-06-21: 15 commitsWeek of 2026-06-28: 30 commitsWeek of 2026-07-05: 30 commitsWeek of 2026-07-12: 27 commitsWeek of 2026-07-19: 9 commitsWeek of 2026-07-26: 18 commitsWeek of 2026-08-02: 29 commitsWeek of 2026-08-09: 29 commitsWeek of 2026-08-16: 17 commitsWeek of 2026-08-23: 28 commitsWeek of 2026-08-30: 34 commitsWeek of 2026-09-06: 26 commitsWeek of 2026-09-13: 51 commitsWeek of 2026-09-20: 40 commitsWeek of 2026-09-27: 22 commitsWeek of 2026-10-04: 35 commitsWeek of 2026-10-11: 28 commitsWeek of 2026-10-18: 41 commitsWeek of 2026-10-25: 50 commitsWeek of 2026-11-01: 49 commitsWeek of 2026-11-08: 12 commitsNov 16, 2025Nov 8, 2026
852 commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 8 commitsSun 1:00 — 2 commitsSun 2:00 — 1 commitsSun 3:00 — 2 commitsSun 4:00 — 1 commitsSun 5:00 — 1 commitsSun 6:00 — 2 commitsSun 7:00 — 1 commitsSun 8:00 — 0 commitsSun 9:00 — 3 commitsSun 10:00 — 1 commitsSun 11:00 — 3 commitsSun 12:00 — 2 commitsSun 13:00 — 1 commitsSun 14:00 — 6 commitsSun 15:00 — 11 commitsSun 16:00 — 11 commitsSun 17:00 — 4 commitsSun 18:00 — 4 commitsSun 19:00 — 4 commitsSun 20:00 — 3 commitsSun 21:00 — 14 commitsSun 22:00 — 10 commitsSun 23:00 — 11 commitsMon 0:00 — 2 commitsMon 1:00 — 3 commitsMon 2:00 — 4 commitsMon 3:00 — 2 commitsMon 4:00 — 3 commitsMon 5:00 — 1 commitsMon 6:00 — 1 commitsMon 7:00 — 3 commitsMon 8:00 — 1 commitsMon 9:00 — 2 commitsMon 10:00 — 0 commitsMon 11:00 — 9 commitsMon 12:00 — 8 commitsMon 13:00 — 3 commitsMon 14:00 — 8 commitsMon 15:00 — 11 commitsMon 16:00 — 15 commitsMon 17:00 — 13 commitsMon 18:00 — 8 commitsMon 19:00 — 6 commitsMon 20:00 — 4 commitsMon 21:00 — 6 commitsMon 22:00 — 5 commitsMon 23:00 — 16 commitsTue 0:00 — 3 commitsTue 1:00 — 0 commitsTue 2:00 — 1 commitsTue 3:00 — 1 commitsTue 4:00 — 0 commitsTue 5:00 — 4 commitsTue 6:00 — 0 commitsTue 7:00 — 1 commitsTue 8:00 — 1 commitsTue 9:00 — 4 commitsTue 10:00 — 4 commitsTue 11:00 — 11 commitsTue 12:00 — 10 commitsTue 13:00 — 13 commitsTue 14:00 — 6 commitsTue 15:00 — 17 commitsTue 16:00 — 15 commitsTue 17:00 — 14 commitsTue 18:00 — 6 commitsTue 19:00 — 6 commitsTue 20:00 — 8 commitsTue 21:00 — 7 commitsTue 22:00 — 6 commitsTue 23:00 — 7 commitsWed 0:00 — 3 commitsWed 1:00 — 2 commitsWed 2:00 — 4 commitsWed 3:00 — 2 commitsWed 4:00 — 1 commitsWed 5:00 — 3 commitsWed 6:00 — 6 commitsWed 7:00 — 3 commitsWed 8:00 — 0 commitsWed 9:00 — 4 commitsWed 10:00 — 6 commitsWed 11:00 — 11 commitsWed 12:00 — 8 commitsWed 13:00 — 10 commitsWed 14:00 — 10 commitsWed 15:00 — 14 commitsWed 16:00 — 7 commitsWed 17:00 — 7 commitsWed 18:00 — 10 commitsWed 19:00 — 2 commitsWed 20:00 — 8 commitsWed 21:00 — 7 commitsWed 22:00 — 7 commitsWed 23:00 — 9 commitsThu 0:00 — 3 commitsThu 1:00 — 5 commitsThu 2:00 — 4 commitsThu 3:00 — 1 commitsThu 4:00 — 0 commitsThu 5:00 — 2 commitsThu 6:00 — 2 commitsThu 7:00 — 2 commitsThu 8:00 — 3 commitsThu 9:00 — 3 commitsThu 10:00 — 2 commitsThu 11:00 — 6 commitsThu 12:00 — 10 commitsThu 13:00 — 4 commitsThu 14:00 — 6 commitsThu 15:00 — 5 commitsThu 16:00 — 12 commitsThu 17:00 — 9 commitsThu 18:00 — 8 commitsThu 19:00 — 7 commitsThu 20:00 — 7 commitsThu 21:00 — 4 commitsThu 22:00 — 12 commitsThu 23:00 — 8 commitsFri 0:00 — 3 commitsFri 1:00 — 0 commitsFri 2:00 — 3 commitsFri 3:00 — 5 commitsFri 4:00 — 2 commitsFri 5:00 — 6 commitsFri 6:00 — 0 commitsFri 7:00 — 1 commitsFri 8:00 — 1 commitsFri 9:00 — 1 commitsFri 10:00 — 3 commitsFri 11:00 — 16 commitsFri 12:00 — 8 commitsFri 13:00 — 3 commitsFri 14:00 — 12 commitsFri 15:00 — 8 commitsFri 16:00 — 13 commitsFri 17:00 — 6 commitsFri 18:00 — 11 commitsFri 19:00 — 8 commitsFri 20:00 — 7 commitsFri 21:00 — 4 commitsFri 22:00 — 5 commitsFri 23:00 — 3 commitsSat 0:00 — 6 commitsSat 1:00 — 4 commitsSat 2:00 — 0 commitsSat 3:00 — 1 commitsSat 4:00 — 0 commitsSat 5:00 — 2 commitsSat 6:00 — 0 commitsSat 7:00 — 0 commitsSat 8:00 — 3 commitsSat 9:00 — 0 commitsSat 10:00 — 1 commitsSat 11:00 — 4 commitsSat 12:00 — 4 commitsSat 13:00 — 11 commitsSat 14:00 — 9 commitsSat 15:00 — 5 commitsSat 16:00 — 1 commitsSat 17:00 — 4 commitsSat 18:00 — 4 commitsSat 19:00 — 3 commitsSat 20:00 — 3 commitsSat 21:00 — 3 commitsSat 22:00 — 5 commitsSat 23:00 — 3 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Nov 1, 2026daily#7+115
Oct 31, 2026daily#7+115
Oct 3, 2026monthly#17+11,062
Oct 2, 2026monthly#17+11,062
Oct 1, 2026monthly#14+13,868
Sep 30, 2026monthly#11+18,126
Sep 29, 2026monthly#7+18,422
Sep 28, 2026monthly#10+18,484
Sep 27, 2026monthly#4+18,374
Sep 26, 2026monthly#4+18,282
Sep 25, 2026monthly#4+18,202
Sep 24, 2026monthly#4+18,072
Sep 23, 2026monthly#4+17,895
Sep 22, 2026monthly#2+17,721
Sep 21, 2026monthly#3+17,511
  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • anomalyco/opencode

    The open source coding agent.

    228.3K stars · TypeScript

  • n8n-io/n8n

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

    211.6K stars · TypeScript

  • firecrawl/firecrawl

    Knowledge infrastructure to make your agents smarter. Search, scrape and access 550+ data providers through one API.

    205.3K stars · TypeScript