基于VMware+Ubuntu 24.04环境完成OpenClaw安装、配置与使用

OpenClaw是最近比较火爆?的开源AI助手，短短几个月就已登顶GitHub热门榜，目前star⭐️达到24.3w。

OpenClaw爆火的核心，在于它用本地执行 + 多渠道统一 + 模型无关 + 安全可控 + 插件生态五大技术，解决了 AI 助手 “只会聊、不会做、记不住、不安全、难扩展” 的行业痛点。

下文会基于 VMware + Ubuntu 24.04 环境，从零开始完成 OpenClaw 的安装、配置，并实现与飞书机器人的打通。

OpenClaw安装配置

安装

在安装openclaw之前，先给Ubuntu系统换源，以提高安装速度，这里使用小鱼的一键安装指令：

# 选5wget http://fishros.com/install -O fishros && . fishros

有nodejs环境的可以轻易安装openclaw，另外openclaw也提供了一键安装脚本，它会自动安装环境所需要的nodejs、make、gcc、cmake和python3：

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

初次安装时间比较长…

配置

等待安装好后，终端会自动弹出配置界面。此外，为了后续能在终端识别openclaw的命令，需要在~/.bashrc文件添加export PATH="/home/xsf/.npm-global/bin:$PATH"。

以下是配置页面：

配置页面按键：左右上下键是选择，空格键是勾选，回车是确认并下一步。

这个选Yes，回车

◆  I understand this is personal-by-default and shared/multi-user use requires lock-down. Continue?│  ● Yes / ○ No

选QuickStart，回车

◆  Onboarding mode│  ● QuickStart (Configure details later via openclaw configure.)│  ○ Manual

选择大语言模型，这里我选MiniMax (M2.5 (recommended))，回车

◆  Model/auth provider│  ○ OpenAI│  ○ Anthropic│  ○ Chutes│  ○ vLLM│  ● MiniMax (M2.5 (recommended))│  ○ Moonshot AI (Kimi K2.5)│  ○ Google│  ○ xAI (Grok)│  ○ Mistral AI│  ○ Volcano Engine│  ○ BytePlus

因为模型API是国内，以下选MiniMax M2.5 (CN) (China endpoint (api.minimaxi.com))，回车

◆  MiniMax auth method│  ○ MiniMax OAuth│  ○ MiniMax M2.5│  ● MiniMax M2.5 (CN) (China endpoint (api.minimaxi.com))│  ○ MiniMax M2.5 Lightning│  ○ Back

现在输入API，回车

◆  How do you want to provide this API key?│  ● Paste API key now (Stores the key directly in OpenClaw config)│  ○ Use secret reference└

获取MiniMax API的步骤：

登录网址https://platform.minimaxi.com/docs/api-reference/api-overview，根据以下步骤获取API密钥，注意要充点钱才能使用，第一次充值会送15元。

充钱步骤

书接上文，输入API密钥并回车

选择Keep current (minimax-cn/MiniMax-M2.5)，回车

◆  Default model│  ● Keep current (minimax-cn/MiniMax-M2.5)│  ○ Enter model manually│  ○ minimax-cn/MiniMax-M2.5│  ○ minimax-cn/MiniMax-M2│  ○ minimax-cn/MiniMax-M2.1│  ○ minimax-cn/MiniMax-M2.5-highspeed

选Skip for now (You can add channels later via: openclaw channels add)，跳过移动端接入，回车

◆  Select channel (QuickStart)│  ...│  ○ Google Chat (Chat API)│  ○ Slack (Socket Mode)│  ○ Signal (signal-cli)│  ○ iMessage (imsg)│  ○ Feishu/Lark (飞书)│  ○ Nostr (NIP-04 DMs)│  ○ Microsoft Teams (Bot Framework)│  ○ Mattermost (plugin)│  ○ Nextcloud Talk (self-hosted)│  ○ Matrix (plugin)│  ○ BlueBubbles (macOS app)│  ○ LINE (Messaging API)│  ○ Zalo (Bot API)│  ○ Zalo (Personal Account)│  ○ Synology Chat (Webhook)│  ○ Tlon (Urbit)│  ● Skip for now (You can add channels later via `openclaw channels │  add`)

不安装skills，后续有需要再装，选No，回车

◆  Configure skills now? (recommended)│  ○ Yes / ● No

跳过hook，选Skip for now，回车

◇  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│  ◻ ? boot-md│  ◻ ? bootstrap-extra-files│  ◻ ? command-logger│  ◻ ? session-memory

后续如果想启用，可通过：

列出所有hook：openclaw hooks list

启用hook：openclaw hooks enable session-memory

检查hook状态：openclaw hooks check

选Hatch in TUI (recommended)测试是否可以与大语言模型对话，回车

◆  How do you want to hatch your bot?│  ● Hatch in TUI (recommended)│  ○ Open the Web UI│  ○ Do this later

可以进行对话，说明配置没有问题！打开UI网址，可以更方便配置：

至此，openclaw就已经安装好了。

连接飞书

根据https://docs.openclaw.ai/channels/feishu的步骤，将openclaw作为飞书上的聊天机器人。

创建Feishu app

1.打开飞书网址：https://open.feishu.cn/app，选择企业自建应用

2.定义App名称和描述，获取AppID和Secret

回到openclaw，添加飞书通道AppID和Secret

openclaw channels add

选择Yes，回车

◆  Configure chat channels now?│  ● Yes / ○ No└

选择Feishu/Lark (飞书) (needs app creds)，回车

◆  Select a channel│  ○ Telegram (Bot API)│  ○ WhatsApp (QR link)│  ○ Discord (Bot API)│  ○ IRC (Server + Nick)│  ○ Google Chat (Chat API)│  ○ Slack (Socket Mode)│  ○ Signal (signal-cli)│  ○ iMessage (imsg)│  ● Feishu/Lark (飞书) (needs app creds)│  ○ Nostr (NIP-04 DMs)│  ○ Microsoft Teams (Bot Framework)│  ○ Mattermost (plugin)│  ○ Nextcloud Talk (self-hosted)│  ○ Matrix (plugin)│  ○ BlueBubbles (macOS app)│  ○ LINE (Messaging API)│  ○ Zalo (Bot API)│  ○ Zalo (Personal Account)│  ...└

输入App ID回车

输入App Secret 回车

选择国内，回车

◆  Which Feishu domain?│  ● Feishu (feishu.cn) - China│  ○ Lark (larksuite.com) - International└

选择，回车

◆  Group chat policy│  ○ Allowlist - only respond in specific groups│  ● Open - respond in all groups (requires mention)│  ○ Disabled - don't respond in groups└

最后选完成，回车

◆  Select a channel│  ...│  ○ IRC (Server + Nick)│  ○ Google Chat (Chat API)│  ○ Slack (Socket Mode)│  ○ Signal (signal-cli)│  ○ iMessage (imsg)│  ○ Feishu/Lark (飞书)│  ○ Nostr (NIP-04 DMs)│  ○ Microsoft Teams (Bot Framework)│  ○ Mattermost (plugin)│  ○ Nextcloud Talk (self-hosted)│  ○ Matrix (plugin)│  ○ BlueBubbles (macOS app)│  ○ LINE (Messaging API)│  ○ Zalo (Bot API)│  ○ Zalo (Personal Account)│  ○ Synology Chat (Webhook)│  ○ Tlon (Urbit)│  ● Finished (Done)

剩下如果还有其他选择，直接回车默认即可。

3.授予应用权限

{  "scopes": {    "tenant": [      "aily:file:read",      "aily:file:write",      "application:application.app_message_stats.overview:readonly",      "application:application:self_manage",      "application:bot.menu:write",      "cardkit:card:read",      "cardkit:card:write",      "contact:user.employee_id:readonly",      "corehr:file:download",      "event:ip_list",      "im:chat.access_event.bot_p2p_chat:read",      "im:chat.members:bot_access",      "im:message",      "im:message.group_at_msg:readonly",      "im:message.p2p_msg:readonly",      "im:message:readonly",      "im:message:send_as_bot",      "im:resource"    ],    "user": ["aily:file:read", "aily:file:write", "im:chat.access_event.bot_p2p_chat:read"]  }}

4.启用机器人

5.启用监听事件

im.message.receive_v1

6.飞书发布新版本

7.联合调试

启用openclaw的网关

openclaw gateway

打开开发者助手

随便发个消息获取配对码

使用配对码在openclaw进行与飞书配对

openclaw pairing approve feishu 

再次进行对话，发现openclaw机器人可以回复啦