openclaw本地服务器部署

44 阅读1分钟

背景

我有一台ubuntu服务器,我想部署openclaw体验一下,然后在我mac电脑进行访问。在ubuntu下安装很方便

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

然后参考damodev.csdn.net/697dff7b7c1… 做一下设置,主要是设置一下后续使用deepseek大模型。

openclaw config set 'models.providers.deepseek' --json '{
  "baseUrl": "https://api.deepseek.com/v1",
  "apiKey": "sk-xxxxx",
  "api": "openai-completions",
  "models": [
    { "id": "deepseek-chat", "name": "DeepSeek Chat" },
    { "id": "deepseek-reasoner", "name": "DeepSeek Reasoner" }
  ]
}'

#设置 models.mode 为 merge
openclaw config set models.mode merge


#设置默认模型(以deepseek-chat为例)
openclaw models set deepseek/deepseek-chat

但是启动后无法直接访问,比如http://{ubuntu ip}:18789/。好像是openclaw只允许本地机器访问

解决办法

mac上启动,做一个端口转发

ssh -N -L 18789:127.0.0.1:18789 xxx@10.151.179.187

访问提示unauthorized: gateway token missing (open the dashboard URL and paste the token in Control UI settings)

在ubuntu服务器的~/.openclaw/openclaw.json中找到token,然后访问就行了 http://127.0.0.1:18789/chat?session=main&token=3644b07faa7cb8a07eafa686d732e7b74