OpenClaw Linux/WSL Deployment Notes

1.Install Node

# Download and install nvm:
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.3/install.sh | bash

# Instead of restarting shell
\. "$HOME/.nvm/nvm.sh"
# Download and install Node.js:
nvm install 24
# Verify Node.js version:
node -v # Should print "v24.14.0".
# Verify npm version:
npm -v # Should print "11.9.0".

Without VPN access:

# Chinese mirror without VPN access
/bin/bash -c "$(curl -fsSL https://gitee.com/iamzhihuix/nvm-install-cn/raw/main/install.sh)"

2.Install Git

sudo  apt-get install git

# Verify git version
git --version

3.Install OpenClaw

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

# If not configured, run manually
openclaw onboard --install-daemon

A QuickStart configuration reference (configuration items may vary by version):

◇  I understand this is powerful and inherently risky. Continue? → Yes
◇  Onboarding mode → QuickStart
◇  Model/auth provider  → Z.AI (or other provider models, see Appendix 1 for deepseek)
◇  Select channel (QuickStart) → Skip for now
◇  Search provider → Skip for now (can configure SKILL later)
◇  Configure skills now? (recommended) → Yes
◇  Set GOOGLE_PLACES_API_KEY for goplaces? → No
◇  Set GEMINI_API_KEY for nano-banana-pro? → No
◇  Set NOTION_API_KEY for notion?? → No
◇  Set OPENAI_API_KEY for openai-image-gen? → No
◇  Set OPENAI_API_KEY for openai-whisper-api? → No
◇  Set ELEVENLABS_API_KEY for sag? → No
◇  Enable hooks? →  boot-md， session-memory
◇  How do you want to hatch your bot? → Open the Web UI

Or use Manual mode:

◇  I understand this is powerful and inherently risky. Continue? → Yes
◇  Onboarding mode → Manual
◇  What do you want to set up? → Local gateway (this machine)
◇  Workspace directory → /home/node/.openclaw/workspace (default)
◇  Model/auth provider → Skip for now (can configure Alibaba Cloud Bailian models later)
◇  Filter models by provider → All providers
◇  Default model → Keep current (default)
◇  Gateway port → 18789 (default, consistent with Nginx config)
◇  Gateway bind → LAN (0.0.0.0) (allow LAN access)
◇  Gateway auth → Password (set login password)
◇  Tailscale exposure → Off
◇  Gateway password → Enter custom password (required for subsequent logins)
◇  Configure chat channels now? → No
◇  Configure skills now? → No
◇  Enable hooks? → Skip for now (select with space, then enter)

Access Web UI:

http://localhost:18789/

Appendix

1. Integrate DeepSeek Model

If you need to integrate the DeepSeek model, select Custom Provider in Model/auth provider
Then refer to:

2. Integrate DingTalk Bot

Refer to: OpenClaw Docker Deployment and DingTalk Bot Integration

3. Integrate QQ Bot

Refer to: OpenClaw QQ Bot Integration

AI Translation Notice

This article has been translated by AI from Chinese to English. While we strive for accuracy, there may be nuances or expressions that differ from the original. For the most accurate understanding, please refer to the original Chinese version.

本文由AI从中文翻译为英文。我们力求准确，但可能存在细微差异或表达方式不同。如需最准确的理解，请参考中文原文。