AI Skill Hub 强烈推荐:龙虾AI 是一款优质的MCP工具。已获得 5.3k 颗 GitHub Star,AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的MCP工具解决方案,这是一个值得深入了解的选择。
龙虾AI 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
龙虾AI 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/netease-youdao/LobsterAI
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--ai": {
"command": "npx",
"args": ["-y", "lobsterai"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 龙虾AI 执行以下任务... Claude: [自动调用 龙虾AI MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__ai": {
"command": "npx",
"args": ["-y", "lobsterai"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效

<p align="center"> <a href="https://github.com/netease-youdao/LobsterAI/stargazers"><img src="https://badgen.net/github/stars/netease-youdao/LobsterAI?label=%E2%98%85" alt="GitHub stars" /></a> <a href="LICENSE"><img src="https://badgen.net/github/license/netease-youdao/LobsterAI" alt="License" /></a> <a href="https://x.com/LobsterAIYoudao"><img src="https://img.shields.io/badge/-000000?logo=x&logoColor=white" alt="Follow LobsterAI on X" /></a> <a href="https://shared.ydstatic.com/market/souti/fihserChatWeb/online/2.0.7/dist/assets/wechat_group-B34qRm1G.png"><img src="https://img.shields.io/badge/-000000?logo=wechat&logoColor=white" alt="Follow LobsterAI on X" /></a> <br> <img src="https://img.shields.io/badge/macOS%20%7C%20Windows-4493F8?style=flat-square" alt="Supported platforms: macOS and Windows" /> <img src="https://img.shields.io/badge/Electron-40-47848F?style=flat-square&logo=electron&logoColor=white" alt="Electron 40" /> <img src="https://img.shields.io/badge/React-18-61DAFB?style=flat-square&logo=react&logoColor=black" alt="React 18" /> </p>
<p align="center"> English · <a href="README_zh.md">中文</a> </p>
<p align="center"> <strong>All-scenario office assistant Agent.</strong><br/> The first open-source desktop-grade Agent among major Chinese tech companies, built by NetEase Youdao. </p>
<p align="center"> <a href="#features"><strong>Features</strong></a> · <a href="#developing"><strong>Developing</strong></a> · <a href="#community--support"><strong>Community</strong></a> </p>
<p align="center"> <img src="docs/res/mainpage_en.png" alt="main page" /> </p>
LobsterAI is a desktop Agent that can operate in your real working environment: local files, terminal commands, browser workflows, documents, spreadsheets, slides, IM channels, scheduled jobs, and project workspaces.
Cowork is the LobsterAI product/session layer. OpenClaw is the runtime and gateway underneath it. That split lets LobsterAI keep local persistence, permissions, UI state, artifacts, agents, memory, and IM bindings in the desktop app while using OpenClaw for agent execution.
npm run compile:electron
npm run openclaw:runtime:host
OPENCLAW_FORCE_BUILD=1 npm run electron:dev:openclaw
npm run dsh:runtime:host
npm run dsh:e2e
<details>
<summary>Publish a runtime archive (per platform)</summary>
Each target must be built on a matching machine: native dependencies install for the host, so a cross-architecture build produces an archive that packs cleanly and only fails on users' machines. The build refuses to run on a mismatched host.
| Target | Build on |
| --- | --- |
| `mac-arm64` | Apple Silicon mac |
| `mac-x64` | Intel mac |
| `win-x64` | Windows 10 1803+ (ships `tar.exe`) |
Run these on that machine, substituting the target:
bash
npm run dsh:runtime:mac-arm64
npm run dist:mac # macOS, host architecture npm run dist:mac:x64 npm run dist:mac:arm64 npm run dist:mac:universal npm run dist:win # Windows x64 npm run dist:linux
`vendor/` does not need to be deleted between builds. The OpenClaw runtime under `vendor/openclaw-runtime/<target>` is cached by pinned version and patch hash and is rebuilt automatically when either changes. Set `OPENCLAW_FORCE_BUILD=1` to rebuild it after changing the build scripts themselves, and `OPENCLAW_FORCE_PLUGIN_INSTALL=1` to re-download the bundled plugins. Optional plugins (POPO, NIM) are skipped with a warning when their registry is unreachable, so check the build log before shipping.
The `dist:*` scripts also run these steps for you:
- `openclaw:runtime:<target>`: build, patch, bundle, and prune the OpenClaw runtime, shipped under `Resources/cfmind`.
- Windows only, `verify:installer-patches`: re-applies `patches/app-builder-lib+*.patch` to `node_modules` and runs the installer contract tests. It fails when `node_modules` still carries an older version of the patch, for example after `git pull` without reinstalling; run `npm ci` and retry. Never ship an installer from a tree where it fails.
- Windows only, `setup:python-runtime`: prepares a portable Python under `resources/python-win`, so end users do not need to install Python. cfmind, `SKILLs`, and python-win are shipped as a single `win-resources.tar` and extracted after install.
Windows channel and web-installer builds wrap the same `dist:win` chain:
bash
npm run dist:win:channel -- --keyfrom <channel> [--silent]
npm run dist:win:web -- --keyfrom <channel> [--silent] [--pkg-base-url <cdn-dir> | --pkg-url <package-url>] ```
Offline or private-source packaging can use:
LOBSTERAI_PORTABLE_PYTHON_ARCHIVELOBSTERAI_PORTABLE_PYTHON_URLLOBSTERAI_WINDOWS_EMBED_PYTHON_VERSIONLOBSTERAI_WINDOWS_EMBED_PYTHON_URLLOBSTERAI_WINDOWS_GET_PIP_URLLOBSTERAI_PORTABLE_GIT_ARCHIVELOBSTERAI_PORTABLE_GIT_URL</details>
Create custom Agents with their own identity, model choice, skills, working directory, enabled state, and IM bindings. Keep the Main Agent for general work and use specialized Agents for repeatable roles.
LobsterAI 是由网易有道打造的全能型个人助手 Agent。它作为一个 24/7 全天候在线的智能助手,旨在通过强大的自动化能力帮助用户高效完成各类任务,是您工作流中的智能核心。
LobsterAI 集成了全方位的生产力工具,涵盖数据分析、PPT 制作、视频生成、文档撰写及网页搜索等功能。它支持在本地环境或 OpenClaw Sandbox 沙箱环境中执行任务,并内置了 Office ��档生成、Playwright 自动化、Remotion 视频生成等多种核心 Skills,实现从搜索到执行的闭环。
在开始使用前,请确保您的开发环境已安装 Node.js(版本需满足 >= 24 且 < 25)以及 npm 包管理器。请根据项目要求配置好相应的运行环境。
项目基于 Electron 开发。首次运行时,系统会自动克隆并构建 OpenClaw 核心组件,请耐心等待。开发者可以通过 `npm run electron:dev:openclaw` 命令启动开发模式。如果需要指定 OpenClaw 源码路径或强制重新构建,可以通过设置 `OPENCLAW_SRC` 或 `OPENCLAW_FORCE_BUILD=1` 环境变量进行灵活控制。
本项目遵循严格的 TypeScript 开发规范,采用函数式组件与 Hooks 模式。代码风格要求使用 2 空格缩进、单引号及分号,并优先使用 Tailwind CSS。提交 Commit 信息时需遵循 `type: short imperative summary` 格式(例如 `feat: add artifact toolbar`),以保持版本历史的清晰与规范。
应用级别的配置通过 SQLite 的 `kv` 表进行存储,用户可以直接在 Settings 面板中进行编辑。针对 Cowork 会话,您可以自定义 Working Directory(Agent 操作的根目录)、System Prompt(定制 Agent 行为)以及 Execution Mode(支持 `auto` 或 `local` 模式)。
LobsterAI 支持通过 IM 平台进行移动端远程控制。通过 OpenClaw gateway 接入微信等协议,您可以随时随地通过手机发送指令,远程触发桌面端的 Agent 执行任务,实现跨设备的智能协同。此外,项目内置了基于 Vitest 的测试工作流,开发者可以通过 `npm test` 对特定模块进行自动化测试。
高质量的开源MCP工具,功能强大
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
总体来看,龙虾AI 是一款质量优秀的MCP工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | LobsterAI |
| 原始描述 | 开源MCP工具:Open-source, desktop-grade AI agent that gets real work done — data analysis, sl。⭐5.3k · TypeScript |
| Topics | aiagentautomationtypescript |
| GitHub | https://github.com/netease-youdao/LobsterAI |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-06-17 · 更新时间:2026-06-20 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端