LobsterAI

LobsterAI — All-Scenario Office Assistant Agent

A 24/7 all-scenario office assistant Agent that gets real work done — built by NetEase Youdao

The first open-source, desktop-grade Agent from a major Chinese tech company — publicly praised by OpenClaw's founder.

⬇️ Download  ·  💬 Community  ·  ⭐ Star History  ·  English · 中文

---

LobsterAI is an all-scenario office assistant Agent built by NetEase Youdao — the first open-source, desktop-grade Agent from a major Chinese tech company. It works around the clock to get real work done: data analysis, slide decks, video generation, document writing, web research, email, scheduled jobs, and more.

Unlike chat-only assistants, LobsterAI is desktop-grade. Through its Cowork mode it connects to your files, terminal, browser, and local projects — executing tools and running commands directly in your real working environment, with every sensitive action gated behind your approval. Spin up purpose-built Agents (stock research, content writing, lesson planning…), extend it with Expert Kits, Skills, and MCP servers, and reach it from your phone via WeChat, WeCom, DingTalk, Feishu, QQ, Telegram, Discord, and more — command your computer to work anytime, anywhere.

Why LobsterAI

• 🔓 Open source, secure & trustworthy — 100% open-source code with transparent capabilities; permissions, data, and execution flows are all auditable
• 🖥️ Desktop-grade Agent — Connects to your files, terminal, browser, and local projects, working directly inside your real environment instead of a sandboxed chat box
• 🧩 OpenClaw ecosystem — Built on the open-source OpenClaw Agent framework, with continuous access to new Skills, tools, MCP servers, and models
• 📱 Command your computer from your phone — Drive LobsterAI 24/7 through WeChat, WeCom, DingTalk, Feishu, QQ, Telegram, Discord, and more
• 🔒 Local data, controlled actions — Sessions, configuration, and memory stay on your device; every tool call is gated and logged

Capabilities

• All-scenario productivity — Data analysis, PPT creation, video generation, document writing, web search, email — covering the full range of daily work
• Custom Agents — Create purpose-built Agents (e.g. Stock Expert, Content Writer, Lesson Planner) each with its own identity, skills, and IM channels
• Expert Kits & Skills — 28 built-in skills plus installable Expert Kits; build your own with skill-creator and hot-load at runtime
• MCP support — Connect external tools and data sources through Model Context Protocol servers
• Scheduled tasks — Create recurring jobs by conversation or GUI — daily news digests, inbox cleanup, periodic reports, and more
• Persistent memory — Remembers your preferences and context across sessions via file-based memory; gets smarter the more you use it
• Local-first — Run tasks directly on your machine
• Cross-platform — macOS (Intel + Apple Silicon) and Windows desktop, plus mobile reach via IM
• Windows built-in Python runtime — Windows packages bundle a ready-to-use Python interpreter; skill dependencies install on demand

Real-World Scenarios

| Scenario | Example prompt | |----------|---------------| | Build a full system from scratch | "I run a small shop and still track stock and sales in Excel. Build me an inventory system: log purchases and sales, auto-calculate stock and profit, and let me open it locally." | | Edit files, process data, build pages | "Using the data in product-growth.xlsx, build me a visualization page." | | Daily scheduled news digest | "Every morning at 9, send me yesterday's AI news — especially OpenAI, Anthropic, Google and Chinese labs." | | Deep research & PPT generation | "Research the global AI Agent market landscape, and turn traffic-report.pdf into a report deck." | | Browser automation | "Open my ads dashboard every day, check whether spend, conversion, or cost-per-lead looks abnormal, and summarize the cause." | | Resume screening & doc review | "Turn the 50 resumes in this folder into a screening sheet, flag anyone missing the JD's hard requirements, then shortlist the best 10." | | Keeps learning | "From now on, keep every document you write for me clear, logical, and concise." — saved to long-term memory |

How It Works

Quick Start

Prerequisites

• Node.js >= 24 [!IMPORTANT]

> Cowork mode runs on the OpenClaw agent engine. The first launch must build the OpenClaw runtime, or Cowork sessions won't start. Use the electron:dev:openclaw command for the first run.

# First run: builds the OpenClaw runtime, then starts the app.
# Clones & builds OpenClaw on first run — this can take several minutes.
npm run electron:dev:openclaw

Once the runtime has been built, day-to-day development can use the faster command — it reuses the existing runtime and skips the OpenClaw build step:

npm run electron:dev

The Vite dev server runs at http://localhost:5175. By default the app connects to LobsterAI's production services, so no extra setup is needed to sign in and use it.

OpenClaw build options

The required OpenClaw version is pinned in package.json under openclaw.version, and its source is cloned/managed at ../openclaw (relative to this repo) by default.

# Use a custom OpenClaw source path
OPENCLAW_SRC=/path/to/openclaw npm run electron:dev:openclaw

# Force a rebuild even when the pinned version hasn't changed
OPENCLAW_FORCE_BUILD=1 npm run electron:dev:openclaw

# Skip the automatic version checkout (e.g. when developing OpenClaw locally)
OPENCLAW_SKIP_ENSURE=1 npm run electron:dev:openclaw

Production Build

# TypeScript compilation + Vite bundle
npm run build

# ESLint check
npm run lint

Packaging & Distribution

Build commands, channel packages, manual runtime build & Windows Python bundling

Uses electron-builder to produce platform-specific installers. Output goes to release/.

# macOS (.dmg)
npm run dist:mac

# macOS - Intel only
npm run dist:mac:x64

# macOS - Apple Silicon only
npm run dist:mac:arm64

# macOS - Universal (both architectures)
npm run dist:mac:universal

# Windows (.exe NSIS installer)
npm run dist:win

# Linux (.AppImage & .deb)
npm run dist:linux

Build channel-specific packages by setting KEYFROM:

# macOS - Intel only
KEYFROM=xxx npm run dist:mac:x64

# macOS - Apple Silicon only
KEYFROM=xxx npm run dist:mac:arm64

# Windows (.exe NSIS installer)
npx cross-env KEYFROM=xxx npm run dist:win

Desktop packaging (macOS / Windows / Linux) bundles a prebuilt OpenClaw runtime under Resources/cfmind. The pinned OpenClaw version (package.json → openclaw.version) is automatically fetched and built during packaging — no manual setup needed. The build is cached: if the runtime for the pinned version already exists locally, the build step is skipped automatically.

You can also build OpenClaw runtime manually:

# Build runtime for current host platform (auto-detect mac/win/linux + arch)
npm run openclaw:runtime:host

# Build explicit targets
npm run openclaw:runtime:mac-arm64
npm run openclaw:runtime:mac-x64
npm run openclaw:runtime:win-x64
npm run openclaw:runtime:linux-x64

Override OpenClaw source path with an environment variable when needed:

OPENCLAW_SRC=/path/to/openclaw npm run dist:win

Windows builds bundle a portable Python runtime under resources/python-win (included as installer resource python-win), so end users do not need to install Python manually. The bundled runtime is interpreter-focused and does not preinstall LobsterAI skill Python packages; those can be installed at runtime on demand. By default, packaging downloads the official Python embeddable runtime from python.org if no prebuilt archive is provided. For offline/non-network builds, provide a prebuilt runtime archive explicitly.

Offline/runtime source options for packaging:

• LOBSTERAI_PORTABLE_PYTHON_ARCHIVE: Local prebuilt runtime archive path (recommended for offline CI/CD)
• LOBSTERAI_PORTABLE_PYTHON_URL: Download URL for the prebuilt runtime archive
• LOBSTERAI_WINDOWS_EMBED_PYTHON_VERSION / LOBSTERAI_WINDOWS_EMBED_PYTHON_URL / LOBSTERAI_WINDOWS_GET_PIP_URL: Optional overrides for Windows-host bootstrap sources

Architecture

LobsterAI uses Electron's strict process isolation. All cross-process communication goes through IPC.

Process Model

Main Process (src/main/main.ts):

• Window lifecycle management
• SQLite persistence
• OpenClaw agent engine (primary) + CoworkEngineRouter dispatch layer
• IM Gateways — WeChat, WeCom, DingTalk, Feishu, QQ, Telegram, Discord, POPO remote access
• 40+ IPC channel handlers
• Security: context isolation enabled, node integration disabled, sandbox enabled

Preload Script (src/main/preload.ts):

• Exposes window.electron API via contextBridge
• Includes cowork namespace for session management and stream events

Renderer Process (src/renderer/):

• React 18 + Redux Toolkit + Tailwind CSS
• All UI and business logic
• Communicates with main process exclusively through IPC

Directory Structure

View the full source tree

src/
├── main/                           # Electron main process
│   ├── main.ts                     # Entry point, IPC handlers
│   ├── preload.ts                  # Security bridge
│   ├── sqliteStore.ts              # SQLite storage
│   ├── coworkStore.ts              # Session/message CRUD
│   ├── skillManager.ts             # Skill management
│   ├── im/                         # IM gateways (WeChat/WeCom/DingTalk/Feishu/QQ/Telegram/Discord/POPO)
│   └── libs/
│       ├── agentEngine/
│       │   ├── coworkEngineRouter.ts    # Dispatch layer (routes sessions to the active engine)
│       │   ├── openclawRuntimeAdapter.ts # Primary OpenClaw gateway adapter
│       │   └── claudeRuntimeAdapter.ts  # Legacy built-in adapter (deprecated)
│       ├── coworkRunner.ts          # Legacy built-in executor (deprecated)
│       ├── openclawEngineManager.ts # OpenClaw runtime lifecycle (install/start/status)
│       ├── openclawConfigSync.ts    # Syncs cowork config → OpenClaw config files
│       └── coworkMemoryExtractor.ts # Memory extraction
│
├── renderer/                        # React frontend
│   ├── App.tsx                     # Root component
│   ├── types/                      # TypeScript definitions
│   ├── store/slices/               # Redux state slices
│   ├── services/                   # Business logic (API/IPC/i18n)
│   └── components/
│       ├── cowork/                 # Cowork UI components
│       ├── artifacts/              # Artifact renderers
│       ├── skills/                 # Skill management UI
│       ├── im/                     # IM integration UI
│       └── Settings.tsx            # Settings panel
│
SKILLs/                              # Skill definitions
├── skills.config.json              # Skill enable/disable and ordering
├── web-search/                     # Web search
├── docx/                           # Word document generation
├── xlsx/                           # Excel spreadsheets
├── pptx/                           # PowerPoint presentations
├── pdf/                            # PDF processing
├── remotion/                       # Video generation
├── playwright/                     # Web automation
└── ...                             # More skills

Cowork System

Cowork is the core feature of LobsterAI — an AI working session system powered by OpenClaw as the primary agent engine. Designed for productivity scenarios, it can autonomously complete complex tasks like data analysis, document generation, and information retrieval.

Execution modes, stream events & permission control

Execution Modes

| Mode | Description | |------|-------------| | auto | Automatically selects based on context | | local | Direct local execution, full speed |

Stream Events

Cowork uses IPC events for real-time bidirectional communication:

• message — New message added to the session
• messageUpdate — Incremental streaming content update
• permissionRequest — Tool execution requires user approval
• complete — Session execution finished
• error — Execution error occurred

Permission Control

All tool invocations involving file system access, terminal commands, or network requests require explicit user approval in the CoworkPermissionModal. Both single-use and session-level approvals are supported.

Skills System

LobsterAI ships with a rich set of built-in skills covering productivity, creative, investment research, and automation scenarios, configured via SKILLs/skills.config.json. Below are some typical examples:

View the full skill list

| Skill | Function | Typical Use Case | |-------|----------|-----------------| | web-search | Web search | Information retrieval, research | | docx | Word document generation | Reports, proposals | | xlsx | Excel spreadsheet generation | Data analysis, dashboards | | pptx | PowerPoint creation | Presentations, business reviews | | pdf | PDF processing | Document parsing, format conversion | | remotion | Video generation (Remotion) | Promo videos, data visualization animations | | seedance | AI video generation (Seedance) | Text-to-video, image-to-video | | seedream | AI image generation (Seedream) | Text-to-image, image editing and fusion | | playwright | Web automation | Browser tasks, automated testing | | canvas-design | Canvas drawing and design | Posters, chart design | | frontend-design | Frontend UI design | Prototyping, page design | | develop-web-game | Web game development | Quick game prototypes | | stock-analyzer | Stock deep analysis | A-share research, valuation and financials | | stock-announcements | Stock announcement retrieval | Listed company filings, disclosure lookup | | stock-explorer | Stock information explorer | Basic stock info, market overview | | content-planner | Content planning | Topic strategy, content calendar creation | | article-writer | Article writing | Multi-style long-form content, social media posts | | daily-trending | Daily trending | Hot topic aggregation, trend tracking | | films-search | Film/TV resource search | Movie and series cloud-drive download links | | music-search | Music resource search | Song and album cloud-drive download links | | technology-news-search | Tech news search | Programming, AI, and IT industry updates (disabled by default) | | weather | Weather queries | Weather information | | local-tools | Local system tools | File management, system operations | | imap-smtp-email | Email send/receive | Email processing, auto-replies | | create-plan | Plan authoring | Project planning, task breakdown | | youdaonote | Youdao Note | Note management, to-dos, web clipping | | skill-vetter | Skill security audit | Safety check before installing third-party skills | | skill-creator | Custom skill creation | Extend new capabilities |

Custom skills can be created via skill-creator and hot-loaded at runtime.

Scheduled Tasks

LobsterAI supports scheduled tasks that let the Agent automatically execute recurring work on a set schedule.

How to Create

• Conversational — Tell the Agent in natural language (e.g., "collect tech news for me every morning at 9 AM"), and it will create the scheduled task automatically
• GUI — Add tasks manually in the Scheduled Tasks management panel with a visual interface for configuring timing and task content

Typical Scenarios

| Scenario | Example | |----------|---------| | News Collection | Automatically gather industry news and generate a summary every morning | | Inbox Cleanup | Periodically check your inbox, categorize emails, and summarize important ones | | Data Reports | Generate a weekly busi

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: netease-youdao
• Source: netease-youdao/LobsterAI
• License: MIT
• Homepage: https://lobsterai.youdao.com

Install and usage instructions live in the source repository linked above.