OpenClaw部署与接入飞书 | 大家都叫我李哥

龙虾（ClawBot/OpenClaw）很火，作为一个24小时待命在后台工作的助手Agent，它的能力边界超过了很多其他的助手，为了不让其破坏电脑环境，大部分人不得不将其部署在单独的独立环境中，又因为它得24小时工作，所以要么部署在云端，要么部署在macmini或者更加安静省电的机器上。赶个时髦，玩了一下部署，本文记录主要部署和接通飞书的过程。

感谢哇塞提供的服务器。但是最终还是使用自己的服务器完成的部署，希望OpenClaw不会破坏我的服务器。

部署

常规情况下我们可以使用如下命令使用安装脚本直接安装。

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

但是哇塞的机器的curl版本太过老旧，且使用的是CentOS，我并不太了解。故改为npm安装。

🦞 OpenClaw Installer
Because Threads wasn't the answer either.
✓ Detected: linux
Install plan
OS: linux
Install method: npm
Requested version: latest
[1/3] Preparing environment
· Node.js not found, installing it now
· Installing Node.js via NodeSource
· Installing Linux build tools (make/g++/cmake/python3)
✓ Build tools installed
curl: option --retry-connrefused: is unknown

首先安装npm环境，也就是node，如下：

shell

# 首先安装NVM，用来管理node环境，且不用被系统的老旧版本牵制
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.4/install.sh | bash

# 然后安装一个稳定版本
nvm install v22

安装完成后使用node -v检查发现node所依赖的运行环境不存在（依然是CentOS系统老旧问题）。

改为Snap安装node。将以下命令保存为snap.sh并执行：

# 安装 EPEL 仓库并切换到归档源
sudo yum install -y https://archives.fedoraproject.org/pub/archive/epel/7/x86_64/Packages/e/epel-release-7-14.noarch.rpm
sudo sed -i 's/^mirrorlist/#mirrorlist/g' /etc/yum.repos.d/epel.repo
sudo sed -i 's|#baseurl=http://download.fedoraproject.org/pub/epel|baseurl=http://archives.fedoraproject.org/pub/archive/epel|g' /etc/yum.repos.d/epel.repo
 
# 安装 snapd
sudo yum install -y snapd
sudo systemctl enable --now snapd.socket
sudo ln -s /var/lib/snapd/snap /snap

安装node：

sudo snap install node --channel=22/stable --classic

添加环境变量：

echo 'export PATH=$PATH:/snap/bin' >> ~/.bashrc
source ~/.bashrc

发现依然有依赖问题：

/var/lib/snapd/snap/node/11315/bin/node: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.30' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.21' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.20' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libstdc++.so.6: version `CXXABI_1.3.9' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.26' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libm.so.6: version `GLIBC_2.27' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libm.so.6: version `GLIBC_2.29' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libc.so.6: version `GLIBC_2.33' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libc.so.6: version `GLIBC_2.34' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libc.so.6: version `GLIBC_2.27' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libc.so.6: version `GLIBC_2.32' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libc.so.6: version `GLIBC_2.28' not found (required by /var/lib/snapd/snap/node/11315/bin/node)
/var/lib/snapd/snap/node/11315/bin/node: /lib64/libc.so.6: version `GLIBC_2.25' not found (required by /var/lib/snapd/snap/node/11315/bin/node)

classic模式安装依然会依赖系统库，但是我们无法使用strict，因为node本身必然要访问系统资源的。

正式部署

那么，我们就只剩下更换或者升级操作系统这一条路了。最终又回到了使用安装脚本直接安装的老路。

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

这个脚本会帮我们自动安装node环境与OpenClaw，但是可能会卡住，我们自己手动执行npm install -g opeclaw@xxxx可以看到错误信息：

m error ^[[?25hNot searching for unused variables given on the command line.
npm error -- Configuring incomplete, errors occurred!
npm error Not searching for unused variables given on the command line.
npm error -- Configuring incomplete, errors occurred!
npm error [node-llama-cpp] The prebuilt binary for platform "linux" "x64" is not compatible with the current system, falling back to building from source
npm error ^[[?25l^[[?25hCMake Error at CMakeLists.txt:1 (cmake_minimum_required):
npm error CMake 3.19 or higher is required. You are running version 3.16.3
npm error
npm error
npm error CMake Error at CMakeLists.txt:1 (cmake_minimum_required):
npm error CMake 3.19 or higher is required. You are running version 3.16.3
npm error
npm error
npm error ERROR OMG Process terminated: 1
npm error [node-llama-cpp] Failed to build llama.cpp with no GPU support. Error: SpawnError: Command npm run -s cmake-js-llama -- compile --log-level warn --config Release --arch=x64 --out localBuilds/linux-x64 --runtime-versio
n=22.22.1 --parallel=4 --CDGGML_BUILD_NUMBER=1 --CDCMAKE_CONFIGURATION_TYPES=Release --CDNLC_CURRENT_PLATFORM=linux-x64 --CDNLC_TARGET_PLATFORM=linux-x64 --CDNLC_VARIANT=b8121 --CDGGML_METAL=OFF --CDGGML_CCACHE=OFF --CDLLAMA_CU
RL=OFF --CDLLAMA_HTTPLIB=OFF --CDLLAMA_BUILD_BORINGSSL=OFF --CDLLAMA_OPENSSL=OFF exited with code 1
npm error at createError (file:///usr/lib/node_modules/openclaw/node_modules/node-llama-cpp/dist/utils/spawnCommand.js:34:20)
npm error at ChildProcess. (file:///usr/lib/node_modules/openclaw/node_modules/node-llama-cpp/dist/utils/spawnCommand.js:47:24)
npm error at ChildProcess.emit (node:events:519:28)
npm error at ChildProcess._handle.onexit (node:internal/child_process:293:12)
npm error SpawnError: Command npm run -s cmake-js-llama -- compile --log-level warn --config Release --arch=x64 --out localBuilds/linux-x64 --runtime-version=22.22.1 --parallel=4 --CDGGML_BUILD_NUMBER=1 --CDCMAKE_CONFIGURATION_
TYPES=Release --CDNLC_CURRENT_PLATFORM=linux-x64 --CDNLC_TARGET_PLATFORM=linux-x64 --CDNLC_VARIANT=b8121 --CDGGML_METAL=OFF --CDGGML_CCACHE=OFF --CDLLAMA_CURL=OFF --CDLLAMA_HTTPLIB=OFF --CDLLAMA_BUILD_BORINGSSL=OFF --CDLLAMA_OP
ENSSL=OFF exited with code 1
npm error at createError (file:///usr/lib/node_modules/openclaw/node_modules/node-llama-cpp/dist/utils/spawnCommand.js:34:20)
npm error at ChildProcess. (file:///usr/lib/node_modules/openclaw/node_modules/node-llama-cpp/dist/utils/spawnCommand.js:47:24)
npm error at ChildProcess.emit (node:events:519:28)
npm error at ChildProcess._handle.onexit (node:internal/child_process:293:12)
npm error A complete log of this run can be found in: /root/.npm/_logs/2026-03-07T11_53_48_277Z-debug-0.log
root@toy:~# cmake --version
cmake version 3.16.3
CMake suite maintained and supported by Kitware (kitware.com/cmake).

Ubuntu默认安装的CMake版本过低，需要升级，使用以下脚本：

# 移除旧版本（如果有）
sudo apt remove --purge cmake
# 安装必要的依赖
sudo apt update
sudo apt install -y gpg wget
# 添加 Kitware 签名密钥
wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | sudo tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null
# 添加 Kitware 仓库（根据你的 Ubuntu 版本选择对应的代号，例如 focal 20.04, jammy 22.04, noble 24.04）
echo 'deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ focal main' | sudo tee /etc/apt/sources.list.d/kitware.list
sudo apt update
# 安装 cmake
sudo apt install cmake

此时重新执行curl -fsSL https://openclaw.ai/install.sh | bash 便可以完成安装可以开始初始化了。

[1/3] Preparing environment
✓ Node.js v22.22.1 found
· Active Node.js: v22.22.1 (/usr/bin/node)
· Active npm: 10.9.4 (/usr/bin/npm)
[2/3] Installing OpenClaw
✓ Git already installed
· Installing OpenClaw v2026.3.2
✓ OpenClaw npm package installed
✓ OpenClaw installed
[3/3] Finalizing setup
· Running doctor to migrate settings
✓ Doctor complete

初始化向导，一路yes就行，核心是配置模型和接入飞书。其实际上就是生成的修改配置文件.openclaw/openclaw.json ，并启动服务:

json

{
// 上面省略一大堆
  "models": {
    "mode": "merge",
    "providers": {
      "custom-api-deepseek-com": {
        "baseUrl": "https://api.deepseek.com",
        "apiKey": "自己的key",
        "api": "openai-completions",
        "models": [
          {
            "id": "deepseek-reasoner",
            "name": "deepseek-reasoner (Custom Provider)",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 16000,
            "maxTokens": 4096
          }
        ]
      }
    }
  },
// 中间省略一大堆
  "channels": {
    "feishu": {
      "enabled": true,
      "appId": "自己的key",
      "appSecret": "自己的secret",
      "connectionMode": "websocket",
      "domain": "feishu",
      "groupPolicy": "allowlist",
      "groupAllowFrom": [
        "oc_18c84e60ae9df0bc2db30c9444d97041"
      ]
    }
  },
  // 下面省略一大堆
}

这里只是展示了核心部分：模型配置与接入飞书。模型配置由于在openclaw onboard初始化设置中没有看到deepseek，这里使用的是自定义模式，然后使用OpenAI的兼容API。

我们可以使用openclaw status查看当前状态。建议防火墙拦截dashboard端口18789，避免不必要的麻烦。

如果需要更改配置可以使用openclaw configure。（梦回远古时候的管理方式）

接入飞书

上面我们已经部署完成了，完成之后一般会使用TUI测试一下是否接入了大模型之类的。但是我们肯定不希望使用命令行来操作，那就和Claude Code一样了。我们想要的是一个24小时待命并且会在后台完成工作的助手。

我们要将其接入聊天软件。我这里是接入飞书。

首先我们登录飞书开放平台创建一个应用机器人：创建企业自建应用。

将APP_ID和APP_SECRET复制出来，配置到上面部署阶段会用到的地方。

添加机器人能力

导入权限

json

{
  "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:write",
      "contact:user.employee_id:readonly",
      "corehr:file:download",
      "docs:document.content:read",
      "event:ip_list",
      "im:chat",
      "im:chat.access_event.bot_p2p_chat:read",
      "im:chat.members:bot_access",
      "im:message",
      "im:message.group_at_msg:readonly",
      "im:message.group_msg",
      "im:message.p2p_msg:readonly",
      "im:message:readonly",
      "im:message:send_as_bot",
      "im:resource",
      "sheets:spreadsheet",
      "wiki:wiki:readonly"
    ],
    "user": ["aily:file:read", "aily:file:write", "im:chat.access_event.bot_p2p_chat:read"]
  }
}