在 Ubuntu 上快速部署 OpenClaw 完整教程

在 Ubuntu 上快速部署 OpenClaw 完整教程

文章目录

在 Ubuntu 上部署 OpenClaw 完整教程

本文记录我在 Ubuntu 22.04 服务器上从零部署 OpenClaw 并接入飞书的完整过程,包括遇到的坑和解决方法。

环境信息

  • 系统: Ubuntu 22.04 LTS
  • 配置: 4核 8GB 内存,100M 带宽
  • 类型 CPU

一、安装依赖

1.1 更新系统包索引

sudoapt update 

1.2 安装 curl

sudoaptinstall-ycurl

1.3 通过 NodeSource 安装最新稳定 LTS 版本

# 添加 NodeSource 仓库并安装curl-fsSL https://deb.nodesource.com/setup_lts.x |sudo-Ebash - sudoapt-getinstall-y nodejs # 安装完成后,验证版本node-vnpm-v

实际输出:

ubuntu@gt-ubuntu22-04-cmd-v3-0-8gb-100m:~$ node-v v24.14.0 ubuntu@gt-ubuntu22-04-cmd-v3-0-8gb-100m:~$ npm-v11.9.0 

1.4 设置淘宝镜像(最常用)

npm config set registry https://registry.npmmirror.com # 查询是否配置成功npm config get registry 

验证输出:

ubuntu@gt-ubuntu22-04-cmd-v3-0-8gb-100m:~$ npm config get registry https://registry.npmmirror.com 

二、安装 OpenClaw

执行安装脚本(注意:安装过程中要勾选 yes):

curl-fsSL https://openclaw.ai/install.sh |bash

完整安装日志:

 ubuntu@gt-ubuntu22-04-cmd-v3-0-8gb-100m:~$ curl-fsSL https://openclaw.ai/install.sh |bash 🦞 OpenClaw Installer The only crab in your contacts you actually want to hear from. 🦞 ✓ Detected: linux Install plan OS: linux Install method: npm Requested version: latest [1/3] Preparing environment ✓ Node.js v24.14.0 found · Active Node.js: v24.14.0 (/usr/bin/node) · Active npm: 11.9.0 (/usr/bin/npm)[2/3] Installing OpenClaw ✓ Git already installed · Configuring npmfor user-local installs ✓ npm configured for user installs · Installing OpenClaw v2026.2.26 ✓ OpenClaw npm package installed ✓ OpenClaw installed [3/3] Finalizing setup !PATH missing npm global bin dir: /home/ubuntu/.npm-global/bin This can make openclaw show as "command not found"in new terminals. Fix (zsh: ~/.zshrc, bash: ~/.bashrc): exportPATH="/home/ubuntu/.npm-global/bin:$PATH" 🦞 OpenClaw installed successfully (2026.2.26)! All done! I promise to only judge your code a little bit. · Starting setup 🦞 OpenClaw 2026.2.26 (bc50708) — Ship fast, log faster. ▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄▄ ██░▄▄▄░██░▄▄░██░▄▄▄██░▀██░██░▄▄▀██░████░▄▄▀██░███░██ ██░███░██░▀▀░██░▄▄▄██░█░█░██░█████░████░▀▀░██░█░█░██ ██░▀▀▀░██░█████░▀▀▀██░██▄░██░▀▀▄██░▀▀░█░██░██▄▀▄▀▄██ ▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀ 🦞 OPENCLAW 🦞 ┌ OpenClaw onboarding │ ◇ Security ─────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Security warning — please read. │ │ │ │ OpenClaw is a hobby project and still in beta. Expect sharp edges. │ │ By default, OpenClaw is a personal agent: one trusted operator boundary. │ │ This bot can read files and run actions if tools are enabled. │ │ A bad prompt can trick it into doing unsafe things. │ │ │ │ OpenClaw is not a hostile multi-tenant boundary by default. │ │ If multiple users can message one tool-enabled agent, they share that delegated tool │ │ authority. │ │ │ │ If you’re not comfortable with security hardening and access control, don’t run │ │ OpenClaw. │ │ Ask someone experienced to help before enabling tools or exposing it to the internet. │ │ │ │ Recommended baseline: │ │ - Pairing/allowlists + mention gating. │ │ - Multi-user/shared inbox: split trust boundaries (separate gateway/credentials, ideally │ │ separate OS users/hosts). │ │ - Sandbox + least-privilege tools. │ │ - Shared inboxes: isolate DM sessions (`session.dmScope: per-channel-peer`) and keep │ │ tool access minimal. │ │ - Keep secrets out of the agent’s reachable filesystem. │ │ - Use the strongest available model for any bot with tools or untrusted inboxes. │ │ │ │ Run regularly: │ │ openclaw security audit --deep │ │ openclaw security audit --fix │ │ │ │ Must read: https://docs.openclaw.ai/gateway/security │ │ │ ├────────────────────────────────────────────────────────────────────────────────────────────╯ │ ◇ I understand this is personal-by-default and shared/multi-user use requires lock-down. Continue? │ Yes │ ◇ Onboarding mode │ QuickStart │ ◇ QuickStart ─────────────────────────╮ │ │ │ Gateway port: 18789 │ │ Gateway bind: Loopback (127.0.0.1) │ │ Gateway auth: Token (default) │ │ Tailscale exposure: Off │ │ Direct to chat channels. │ │ │ ├──────────────────────────────────────╯ │ ◇ Model/auth provider │ Z.AI │ ◇ Z.AI auth method │ CN │ ◇ How do you want to provide this API key? │ Paste API key now │ ◇ Enter Z.AI API key │ xxx.xxxx │ ◇ Model configured ───────────────╮ │ │ │ Default model set to zai/glm-5 │ │ │ ├──────────────────────────────────╯ │ ◇ Default model │ zai/glm-4.7 │ ◇ Channel status ────────────────────────────╮ │ │ │ Telegram: needs token │ │ WhatsApp (default): not linked │ │ Discord: needs token │ │ Slack: needs tokens │ │ Signal: needs setup │ │ signal-cli: missing (signal-cli) │ │ iMessage: needs setup │ │ imsg: missing (imsg) │ │ IRC: not configured │ │ Google Chat: not configured │ │ Feishu: install plugin to enable │ │ Google Chat: install plugin to enable │ │ Nostr: install plugin to enable │ │ Microsoft Teams: install plugin to enable │ │ Mattermost: install plugin to enable │ │ Nextcloud Talk: install plugin to enable │ │ Matrix: install plugin to enable │ │ BlueBubbles: install plugin to enable │ │ LINE: install plugin to enable │ │ Zalo: install plugin to enable │ │ Zalo Personal: install plugin to enable │ │ Synology Chat: install plugin to enable │ │ Tlon: install plugin to enable │ │ │ ├─────────────────────────────────────────────╯ │ ◇ How channels work ───────────────────────────────────────────────────────────────────────╮ │ │ │ DM security: default is pairing; unknown DMs get a pairing code. │ │ Approve with: openclaw pairing approve <channel><code> │ │ Public DMs require dmPolicy="open" + allowFrom=["*"]. │ │ Multi-user DMs: run: openclaw config set session.dmScope "per-channel-peer"(or │ │ "per-account-channel-peer"for multi-account channels) to isolate sessions. │ │ Docs: channels/pairing │ │ │ │ Telegram: simplest way to get started — register a bot with @BotFather and get going. │ │ WhatsApp: works with your own number; recommend a separate phone + eSIM. │ │ Discord: very well supported right now. │ │ IRC: classic IRC networks with DM/channel routing and pairing controls. │ │ Google Chat: Google Workspace Chat app with HTTP webhook. │ │ Slack: supported (Socket Mode). │ │ Signal: signal-cli linked device;more setup (David Reagans: "Hop on Discord."). │ │ iMessage: this is still a work in progress. │ │ Feishu: 飞书/Lark enterprise messaging with doc/wiki/drive tools. │ │ Nostr: Decentralized protocol; encrypted DMs via NIP-04. │ │ Microsoft Teams: Bot Framework; enterprise support. │ │ Mattermost: self-hosted Slack-style chat;install the plugin to enable. │ │ Nextcloud Talk: Self-hosted chat via Nextcloud Talk webhook bots. │ │ Matrix: open protocol;install the plugin to enable. │ │ BlueBubbles: iMessage via the BlueBubbles mac app + REST API. │ │ LINE: LINE Messaging API bot for Japan/Taiwan/Thailand markets. │ │ Zalo: Vietnam-focused messaging platform with Bot API. │ │ Zalo Personal: Zalo personal account via QR code login. │ │ Synology Chat: Connect your Synology NAS Chat to OpenClaw with full agent capabilities. │ │ Tlon: decentralized messaging on Urbit;install the plugin to enable. │ │ │ ├───────────────────────────────────────────────────────────────────────────────────────────╯ │ ◇ Select channel (QuickStart) │ Skip for now Updated ~/.openclaw/openclaw.json Workspace OK: ~/.openclaw/workspace Sessions OK: ~/.openclaw/agents/main/sessions │ ◇ Skills status ─────────────╮ │ │ │ Eligible: 4 │ │ Missing requirements: 40 │ │ Unsupported on this OS: 7 │ │ Blocked by allowlist: 0 │ │ │ ├─────────────────────────────╯ │ ◇ Configure skills now? (recommended) │ No │ ◇ Hooks ──────────────────────────────────────────────────────────────────╮ │ │ │ Hooks let you automate actions when agent commands are issued. │ │ Example: Save session context to memory when you issue /new or /reset. │ │ │ │ Learn more: https://docs.openclaw.ai/automation/hooks │ │ │ ├──────────────────────────────────────────────────────────────────────────╯ │ ◇ Enable hooks? │ Skip for now Config overwrite: /home/ubuntu/.openclaw/openclaw.json (sha256 f763f7d577aba2ed75a863a91e3e9a116eab6ecc856e7731972988b006426453 -> 8eac9ee80087618bf88b5f7a2f1f6bdb4b5abf5dfa646c22bf65f64e92063204, backup=/home/ubuntu/.openclaw/openclaw.json.bak) │ ◇ Systemd ────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Linux installs use a systemd user service by default. Without lingering, systemd stops │ │ the user session on logout/idle and kills the Gateway. │ │ Enabling lingering now (may require sudo; writes /var/lib/systemd/linger). │ │ │ ├──────────────────────────────────────────────────────────────────────────────────────────╯ │ ◇ Systemd ───────────────────────────────╮ │ │ │ Enabled systemd lingering for ubuntu. │ │ │ ├─────────────────────────────────────────╯ │ ◇ Gateway service runtime ────────────────────────────────────────────╮ │ │ │ QuickStart uses Node for the Gateway service(stable + supported). │ │ │ ├──────────────────────────────────────────────────────────────────────╯ │ ◐ Installing Gateway service… Installed systemd service: /home/ubuntu/.config/systemd/user/openclaw-gateway.service ◇ Gateway service installed. │ ◇ Agents: main (default) Heartbeat interval: 30m (main) Session store (main): /home/ubuntu/.openclaw/agents/main/sessions/sessions.json (0 entries) │ ◇ Optional apps ────────────────────────╮ │ │ │ Add nodes for extra features: │ │ - macOS app (system + notifications) │ │ - iOS app (camera/canvas) │ │ - Android app (camera/canvas) │ │ │ ├────────────────────────────────────────╯ │ ◇ Control UI ─────────────────────────────────────────────────────────────────────╮ │ │ │ Web UI: http://127.0.0.1:18789/ │ │ Web UI (with token): │ │ http://127.0.0.1:18789/#token=2962e8f5116c63d86ea9c8224bc8d6445cce2e806ed1e183 │ │ Gateway WS: ws://127.0.0.1:18789 │ │ Gateway: reachable │ │ Docs: https://docs.openclaw.ai/web/control-ui │ │ │ ├──────────────────────────────────────────────────────────────────────────────────╯ │ ◇ Start TUI (best option!) ─────────────────────────────────╮ │ │ │ This is the defining action that makes your agent you. │ │ Please take your time. │ │ The more you tell it, the better the experience will be. │ │ We will send: "Wake up, my friend!" │ │ │ ├────────────────────────────────────────────────────────────╯ │ ◇ Token ─────────────────────────────────────────────────────────────────────────────────╮ │ │ │ Gateway token: shared auth for the Gateway + Control UI. │ │ Stored in: ~/.openclaw/openclaw.json (gateway.auth.token) or OPENCLAW_GATEWAY_TOKEN. │ │ View token: openclaw config get gateway.auth.token │ │ Generate token: openclaw doctor --generate-gateway-token │ │ Web UI stores a copy in this browser's localStorage (openclaw.control.settings.v1). │ │ Open the dashboard anytime: openclaw dashboard --no-open │ │ If prompted: paste the token into Control UI settings (or use the tokenized dashboard │ │ URL). │ │ │ ├─────────────────────────────────────────────────────────────────────────────────────────╯ │ ◇ How do you want to hatch your bot? │ Open the Web UI │ ◇ Dashboard ready ────────────────────────────────────────────────────────────────╮ │ │ │ Dashboard link(with token): │ │ http://127.0.0.1:18789/#token=2962e8f5116c63d86ea9c8224bc8d6445cce2e806ed1e183 │ │ Copy/paste this URL in a browser on this machine to control OpenClaw. │ │ No GUI detected. Open from your computer: │ │ ssh-N-L18789:127.0.0.1:18789 [email protected] │ │ Then open: │ │ http://localhost:18789/ │ │ http://localhost:18789/#token=2962e8f5116c63d86ea9c8224bc8d6445cce2e806ed1e183 │ │ Docs: │ │ https://docs.openclaw.ai/gateway/remote │ │ https://docs.openclaw.ai/web/control-ui │ │ │ ├──────────────────────────────────────────────────────────────────────────────────╯ │ ◇ Workspace backup ────────────────────────────────────────╮ │ │ │ Back up your agent workspace. │ │ Docs: https://docs.openclaw.ai/concepts/agent-workspace │ │ │ ├───────────────────────────────────────────────────────────╯ │ ◇ Security ──────────────────────────────────────────────────────╮ │ │ │ Running agents on your computer is risky — harden your setup: │ │ https://docs.openclaw.ai/security │ │ │ ├─────────────────────────────────────────────────────────────────╯ │ ◇ Shell completion ────────────────────────────────────────────────────────╮ │ │ │ Shell completion installed. Restart your shell or run: source ~/.bashrc │ │ │ ├───────────────────────────────────────────────────────────────────────────╯ │ ◇ Web search (optional) ─────────────────────────────────────────────────────────────────╮ │ │ │ If you want your agent to be able to search the web, you’ll need an API key. │ │ │ │ OpenClaw uses Brave Search for the `web_search` tool. Without a Brave Search API key, │ │ web search won’t work. │ │ │ │ Set it up interactively: │ │ - Run: openclaw configure --section web │ │ - Enable web_search and paste your Brave Search API key │ │ │ │ Alternative: set BRAVE_API_KEY in the Gateway environment (no config changes). │ │ Docs: https://docs.openclaw.ai/tools/web │ │ │ ├─────────────────────────────────────────────────────────────────────────────────────────╯ │ ◇ What now ─────────────────────────────────────────────────────────────╮ │ │ │ What now: https://openclaw.ai/showcase ("What People Are Building"). │ │ │ ├────────────────────────────────────────────────────────────────────────╯ │ └ Onboarding complete. Use the dashboard link above to control OpenClaw. ubuntu@gt-ubuntu22-04-cmd-v3-0-8gb-100m:~$ 

三、解决 PATH 问题

安装完成后,如果执行 which openclaw 找不到命令,需要手动配置 PATH:

# 检查 openclaw 是否在 PATH 中which openclaw # 如果找不到,查看 npm 全局安装目录npm prefix -g# 查看当前 shellecho$SHELL# 如果输出 /bin/bash,使用 ~/.bashrc# 如果输出 /bin/zsh,使用 ~/.zshrc# 将 npm 全局 bin 目录添加到 PATHecho'export PATH="$(npm prefix -g)/bin:$PATH"'>> ~/.bashrc # 重新加载配置文件source ~/.bashrc # 验证添加是否成功echo$PATH|grepnpm

四、访问控制界面

4.1 本地ssh连接服务器

在本地电脑执行,按提示输入远程linux云主机密码即可:

ssh-N-L18789:127.0.0.1:18789 ubuntu@你的云主机IP 
在这里插入图片描述

4.2 访问openclaw web ui

携带部署过程中生成的Dashboard link在本地进行访问,如下图:

http://localhost:18789/#token=你的token
在这里插入图片描述

4.3 测试

  1. 询问背后模型,如下图告知是glm4.7,与配置的一致

给AI助手起名为“大衍AI”,如下图,可切换界面等待其生效

在这里插入图片描述


在这里插入图片描述

五、总结

本文详细记录了在 Ubuntu 22.04 服务器上从零部署 OpenClaw 的完整流程,包括:

  • 环境准备:Node.js LTS 安装与 npm 镜像配置
  • OpenClaw 安装:通过官方脚本一键安装,处理 PATH 配置问题
  • 初始化配置:QuickStart 模式、Z.AI 模型接入
  • 远程访问:通过 SSH 隧道访问 Web 控制界面进行问答

六、后续内容预告

OpenClaw 的功能远不止于此,接下来我将在博客和B站频道推出更多深度内容,包括:

  • 🔧 进阶配置:自定义 Skills 技能、Hooks 自动化、多 Agent 管理
  • 🔒 安全加固:生产环境部署、访问控制、审计日志配置
  • 🛠️ 插件开发:自定义飞书工具插件、接入企业内部系统
  • 🤖 模型调优:Prompt 工程、多模型切换、上下文管理
  • 📊 实战案例:搭建团队知识库助手、自动化工作流机器人

六、视频教程

如果您觉得文字教程不够直观,欢迎访问我的 B 站频道观看完整视频版部署教程:

👉 点击观看《Ubuntu 部署 OpenClaw 手把手教学》

视频中我会实时演示每一步操作,详细讲解配置选项的含义,并演示如何在飞书中与机器人进行交互。建议搭配本文一起食用,效果更佳!

Read more

Stack-Chan机器人完整入门指南:从零开始构建你的可爱机器人伙伴

Stack-Chan机器人完整入门指南:从零开始构建你的可爱机器人伙伴 【免费下载链接】stack-chanA JavaScript-driven M5Stack-embedded super-kawaii robot. 项目地址: https://gitcode.com/gh_mirrors/sta/stack-chan Stack-Chan是一个基于JavaScript驱动的M5Stack嵌入式超级可爱的机器人项目。这个开源项目让你能够轻松构建一个会眨眼、会转头、会说话的智能机器人伙伴。无论你是嵌入式开发新手还是经验丰富的开发者,都能快速上手这个充满乐趣的项目。 🎯 项目核心亮点 超强可爱属性:Stack-Chan拥有多种可爱的面部表情,能够进行眼神交流,让你的机器人充满个性魅力。 模块化设计:项目采用高度模块化的架构,支持多种舵机驱动、面部渲染器和功能扩展,让你的定制变得简单而灵活。 丰富功能生态:支持人脸追踪、语音对话、表情模仿等智能功能,为你的机器人注入灵魂。 📦 项目快速入门 环境准备与代码获取 首先克隆项目仓库到本地: git clone ht

By Ne0inhk

Vivado完整license文件获取与配置指南

本文还有配套的精品资源,点击获取 简介:Vivado是由Xilinx开发的FPGA和SoC设计综合工具,支持Verilog、VHDL等硬件描述语言,提供高级综合、仿真、IP集成等功能。本资源包“Vivado_的license文件.zip”包含用于解锁Vivado完整功能的许可证文件。介绍了许可证服务器配置、.lic文件管理、浮动与固定许可证区别、激活流程、更新与诊断等核心内容。适用于FPGA开发者、嵌入式系统工程师及学习者,帮助其合法配置Vivado环境,提升开发效率和项目执行能力。 1. Vivado工具与FPGA开发环境概述 Xilinx Vivado设计套件是面向FPGA和SoC开发的集成化软件平台,广泛应用于通信、工业控制、人工智能、嵌入式视觉等多个高科技领域。其核心功能包括项目创建、综合、实现、仿真、调试及系统级集成,支持从设计输入到硬件验证的全流程开发。 Vivado不仅提供了图形化界面(GUI)便于初学者快速上手,还支持Tcl脚本自动化操作,满足高级用户的大规模工程管理需求。其模块化架构设计使得开发者可以灵活选择所需功能组件,如HLS(高层次综合)、IP In

By Ne0inhk
Ubuntu搭建PX4无人机仿真环境(5) —— 仿真环境搭建(以Ubuntu 22.04,ROS2 Humble,Micro XRCE-DDS Agent为例)

Ubuntu搭建PX4无人机仿真环境(5) —— 仿真环境搭建(以Ubuntu 22.04,ROS2 Humble,Micro XRCE-DDS Agent为例)

目录 * 前言 * 1. 准备 * 1.1 下载 PX4 源码 * 方式一: * 方式二: * 1.2 安装仿真依赖 * 1.3 安装 Gazebo * 2. 安装 Micro XRCE-DDS Agent * 3. 编译 PX4 * 4. 通信测试 * 5. 官方 offboard 程序 * 6. offboard 测试 * 参考 前言 本教程基于 ROS2 ,在搭建之前,需要把 ROS2、QGC 等基础环境安装配置完成。但是这块的资料相比较于 ROS1 下的少很多,不利于快速上手和后期开发,小白慎选! 小白必看:

By Ne0inhk

50 行代码搞定 SLAM+AI Agent!机器人自主导航最小原型,看完就能跑

你想快速搞懂「SLAM+AI Agent」到底怎么让机器人变 “智能” 吗?不用堆公式、不用装复杂环境,纯 Python 实现极简可运行 Demo,看完就能复现,还能直接迁移到真实机器人开发! 一、一句话讲透核心逻辑 * SLAM = 机器人的眼睛 + 定位:回答 “我在哪?周围环境什么样?” * AI Agent = 机器人的大脑 + 决策:回答 “我该去哪?怎么走?避障怎么搞?” * SLAM+AI Agent = 能自主走路的智能机器人:眼睛感知→大脑决策→身体执行,形成闭环。 二、极简 Demo 目标(10×10 网格场景) 机器人从 (0,0) 出发,

By Ne0inhk