Nuwax Agent OS
经 AI Skill Hub 精选评估，Nuwax Agent OS 获评「强烈推荐」。这款AI工具在功能完整性、社区活跃度和易用性方面表现出色，AI 评分 8.8 分，适合有一定技术背景的用户使用。
📚 深度解析
**为什么要使用开源工具而非商业 SaaS？**
对于个人开发者和有隐私需求的用户，本地部署的开源工具意味着数据不离本机，不受第三方服务商的数据政策约束。同时，开源工具通常没有使用次数限制和月度费用，一次安装即可长期使用，对于高频使用场景的总拥有成本（TCO）远低于订阅制商业工具。
**安装与环境准备**
Nuwax Agent OS 依赖 TypeScript 运行环境。建议通过 pyenv（Python）或 nvm（Node.js）管理 TypeScript 版本，避免全局环境污染。对于新手用户，推荐先创建虚拟环境（python -m venv venv && source venv/bin/activate），再安装依赖，这样即使出现问题也可以随时删除虚拟环境重新开始，不影响系统稳定性。
**社区与维护**
GitHub Issue 和 Discussion 是获取帮助的最快渠道。在提问前建议先检查 Closed Issues（已关闭的问题），大多数常见问题都已有解答。遇到 Bug 时，提供 pip list 的输出、完整错误堆栈和最小可复现示例，能显著提高开发者响应速度。AI Skill Hub 将持续追踪 Nuwax Agent OS 的版本更新，及时通知重要功能变化。
📋 工具概览
一个企业级的AI Agent开发与运维平台，基于MCP协议实现Agent与工具的标准化连接。提供沙箱环境和Agent-to-Agent通信能力，适合需要构建复杂、可扩展且具备工业级稳定性的AI智能体开发者和企业团队。
Nuwax Agent OS 是一款基于 TypeScript 开发的开源工具，专注于 MCP协议、智能体操作系统、企业级AI 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
📖 中文文档
一个企业级的AI Agent开发与运维平台，基于MCP协议实现Agent与工具的标准化连接。提供沙箱环境和Agent-to-Agent通信能力，适合需要构建复杂、可扩展且具备工业级稳定性的AI智能体开发者和企业团队。
Nuwax Agent OS 是一款基于 TypeScript 开发的开源工具，专注于 MCP协议、智能体操作系统、企业级AI 等核心功能。作为 GitHub 开源项目，它拥有活跃的社区支持和持续的版本迭代，代码完全透明可审计，支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流，都能提供稳定可靠的解决方案。
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
# 方式一：npm 全局安装 npm install -g nuwax # 方式二：npx 直接运行（无需安装） npx nuwax --help # 方式三：项目依赖安装 npm install nuwax # 方式四：从源码运行 git clone https://github.com/nuwax-ai/nuwax cd nuwax npm install npm start
- 访问 GitHub 仓库页面
- 按照 README 文档完成依赖安装
- 根据系统环境完成初始化配置
- 参考官方示例或文档开始使用
- 遇到问题可在 GitHub Issues 中查找解答
# 命令行使用
nuwax --help
# 基本用法
nuwax [options] <input>
# Node.js 代码中使用
const nuwax = require('nuwax');
const result = await nuwax.run(options);
console.log(result);
# nuwax 配置说明 # 查看配置选项 nuwax --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量（覆盖配置文件） export NUWAX_CONFIG="/path/to/config.yml"
Nuwax
Nuwax AI - Easily build and deploy your private Agentic AI solutions.
Official Website: https://nuwax.com
Demo: https://agent.nuwax.com
Project Repository Overview
The Nuwax AI Agent Platform consists of multiple interconnected repositories:
Frontend & Mobile
| Repository | Description | URL |
|---|---|---|
| **nuwax** | Frontend Web | [https://github.com/nuwax-ai/nuwax](https://github.com/nuwax-ai/nuwax) |
| **nuwax-mobile** | Mobile Application | [https://github.com/nuwax-ai/nuwax-mobile](https://github.com/nuwax-ai/nuwax-mobile) |
| **noVNC** | Web-based VNC Client | [https://github.com/nuwax-ai/noVNC](https://github.com/nuwax-ai/noVNC) |
Backend & Application Layer
| Repository | Description | URL |
|---|---|---|
| **nuwax-backend** | Application Layer (Backend) | [https://github.com/nuwax-ai/nuwax-backend](https://github.com/nuwax-ai/nuwax-backend) |
Agent Engine & Clients
| Repository | Description | URL |
|---|---|---|
| **nuwaclaw** | Agent PC Client (mac/win/docker) | [https://github.com/nuwax-ai/nuwaclaw](https://github.com/nuwax-ai/nuwaclaw) |
| **nuwaxcode** | Nuwa Agent Engine (based on open-source opencode) | [https://github.com/nuwax-ai/nuwaxcode](https://github.com/nuwax-ai/nuwaxcode) |
| **claude-code-acp-ts** | Claude Code ACP based on Zed | [https://github.com/nuwax-ai/claude-code-acp-ts](https://github.com/nuwax-ai/claude-code-acp-ts) |
Infrastructure & Services
| Repository | Description | URL |
|---|---|---|
| **rcoder** | Sandbox & Container Scheduling (includes General Agent Engine) | [https://github.com/nuwax-ai/rcoder](https://github.com/nuwax-ai/rcoder) |
| **mcp-proxy** | MCP Service (used by sandbox) | [https://github.com/nuwax-ai/mcp-proxy](https://github.com/nuwax-ai/mcp-proxy) |
| **nuwax-file-server** | File Service (used by sandbox and nuwaclaw, includes skill sync) | [https://github.com/nuwax-ai/nuwax-file-server](https://github.com/nuwax-ai/nuwax-file-server) |
Web Application Development
| Repository | Description | URL |
|---|---|---|
| **xagi-frontend-templates** | Web Application Development Templates | [https://github.com/nuwax-ai/xagi-frontend-templates](https://github.com/nuwax-ai/xagi-frontend-templates) |
| **vite-plugin-design-mode** | Visual Editor Vite Plugin | [https://github.com/nuwax-ai/vite-plugin-design-mode](https://github.com/nuwax-ai/vite-plugin-design-mode) |
| **dev-inject** | Web Application Smart Script Injection | [https://github.com/nuwax-ai/dev-inject](https://github.com/nuwax-ai/dev-inject) |
Plugin & Script Execution
| Repository | Description | URL |
|---|---|---|
| **run_code_rmcp** | Plugin Script Execution (TypeScript/JavaScript/Python) | [https://github.com/nuwax-ai/run_code_rmcp](https://github.com/nuwax-ai/run_code_rmcp) |
Network & Utilities
| Repository | Description | URL |
|---|---|---|
| **lanproxy-go-client** | Network Tunnel Client (used by nuwaclaw) | [https://github.com/ffay/lanproxy-go-client](https://github.com/ffay/lanproxy-go-client) |
Installation & Deployment
Use the official nuwax-cli command tool to quickly deploy services locally.
Check if deployment client has new version and update
./nuwax-cli check-update install
Docker Environment Installation
Important Note: Docker and Docker Compose are core dependencies for running this service and must be installed correctly.
If your system doesn't have Docker environment installed yet, please refer to the detailed Docker Environment Installation Guide.
This installation guide includes detailed installation steps for the following platforms:
- Ubuntu 24.04.3 LTS (recommended Linux distribution)
- macOS (supports OrbStack and Docker Desktop)
- Mirror acceleration configuration (for mainland China users)
Recommended: One-Click Docker Installation Script
Community one-click Docker installation script
This script supports 13 Linux distributions, including domestic operating systems (openEuler, Anolis OS, OpenCloudOS, Alinux, Kylin Linux), one-click installation of docker, docker-compose with automatic configuration of Xuanyuan mirror acceleration.
bash <(wget -qO- https://xuanyuan.cloud/docker.sh)Script Features and Advantages
✅ Supports 13 mainstream distributions: openEuler, OpenCloudOS, Anolis OS, Alinux (Alibaba Cloud), Kylin Linux, Fedora, Rocky Linux, AlmaLinux, Ubuntu, Debian, CentOS, RHEL, Oracle Linux
✅ Complete support for domestic operating systems: Deep adaptation for domestic OS (openEuler, Anolis OS, OpenCloudOS, Alinux, Kylin Linux), supports automatic version detection and optimal configuration
✅ Intelligent multi-mirror source switching: Built-in 6+ domestic mirror sources including Alibaba Cloud, Tencent Cloud, Huawei Cloud, USTC, Tsinghua, etc., automatically detects and selects the fastest source
✅ Special handling for older systems: Supports expired systems like Ubuntu 16.04, Debian 9/10, automatically configures compatible installation solutions
✅ Dual installation guarantee: Automatically switches to binary installation if package manager installation fails, ensuring installation success rate
✅ macOS/Windows friendly prompts: Automatically detects macOS and Windows systems, provides appropriate Docker Desktop installation guidance
Quick Docker Installation Verification:
```bash
Check Docker version
docker --version
Check Docker Compose version
docker compose version
Quick Start
Environment Preparation
System Requirements
- System Requirements: Ubuntu 22.04 LTS or later (other Linux versions not fully tested), macOS 10.15+, Windows 10/11 (support coming soon)
- Hardware Requirements: 4 cores 8GB RAM or higher
- Environment Requirements: docker, docker-compose V2 environment Docker Installation Guide
Supported Platforms
- Linux: x86_64, ARM64
- Ubuntu 22.04 LTS (recommended)
- Current user needs Docker permissions, verify with
docker ps. If you encounter permission issues, you can run with sudo privileges. - Alibaba Cloud mirror acceleration is recommended
- macOS: Intel, Apple Silicon (M1/M2), Universal
- macOS 10.15 (Catalina) and later versions
- OrbStack is recommended (free for personal use, better performance)
- Ensure OrbStack or Docker Desktop is started
- First-time use may require allowing unknown developers: System Preferences → Security & Privacy
Local Deployment Service Guide
There are 2 deployment services:
- Main project service (required)
- Agent Computer (Sandbox) deployment guide (optional)
In the main local service, configure one or more Agent Computer deployment addresses to use the Agent Computer (Sandbox). Since the "Agent Computer (Sandbox)" includes a personal computer (sandbox) which requires more resources, it supports separate deployment across multiple servers.
Deploy Main Service
Agent Computer (Sandbox) Deployment Guide
You can deploy Agent Computer services on multiple different servers, achieving distributed agent sandbox capabilities through configuration.
Environment Requirements: Each server needs Docker and Docker Compose environment installed, refer to Docker Installation Documentation.
aiskill88点评：深度集成MCP协议，将Agent能力平台化，架构前瞻性强，是构建复杂Agent生态的优秀底座。
⚡ 核心功能
- 开源免费，支持本地部署，数据完全自主可控
- 活跃的 GitHub 开源社区，持续迭代更新
- 提供详细文档和使用示例，新手友好
- 支持自定义配置，灵活适配不同使用环境
- 可作为基础组件集成进现有技术栈或进行二次开发
👥 适合人群
🎯 使用场景
- 本地部署运行，保护数据隐私，满足合规要求
- 自定义集成到现有系统，扩展技术栈能力
- 作为开源基础组件进行商业化二次开发
⚖️ 优点与不足
- +Apache-2.0 协议，可免费商用
- +完全开源免费，无授权费用
- +本地部署，数据完全自主可控
- +开发者社区支持，遇问题可查可问
- −安装和初始配置可能需要一定技术基础
- −功能完整性通常不如成熟商业产品
- −技术支持主要依赖开源社区，响应速度不稳定
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。
✅ Apache 2.0 — 宽松开源协议，可商用，需保留版权声明和 NOTICE 文件，含专利授权条款。
🔗 相关工具推荐
❓ 常见问题 FAQ
AI Skill Hub 点评：Nuwax Agent OS 的核心功能完整，质量优秀。对于AI爱好者来说，这是一个值得纳入个人工具库的选择。建议先在非生产环境试用，再逐步推广。
| 原始名称 | nuwax |
| 原始描述 | 开源MCP工具：Nuwax Agent OS - An enterprise-grade AI Agent Development and Operation Platform。⭐829 · TypeScript |
| Topics | MCP协议智能体操作系统企业级AITypeScript |
| GitHub | https://github.com/nuwax-ai/nuwax |
| License | Apache-2.0 |
| 语言 | TypeScript |
收录时间：2026-07-05 · 更新时间：2026-07-05 · License：Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。