OpenClaw Installation and MYAI168 Setup Guide — Linux

Goal of this guide: install OpenClaw (an open-source AI agent that runs on your own machine, nicknamed the "lobster" 🦞) on a Linux desktop and connect it to your own MYAI168 API, using Claude Opus 4.8 (with gpt-5.6-sol as an optional backup).

On Linux desktop, configuring the lobster with the cc-switch GUI has been verified to work (settings are written successfully). (Prerequisite: cc-switch is installed — for installation, see the "cc-switch Linux" page in the Developer Center.)

Endpoints and Model

Anthropic native endpoint    https://www.myai168.com/en/api/anthropic
OpenAI-compatible endpoint   https://www.myai168.com/en/api/openai/v1
Main model                   claude-opus-4-8 (via the Anthropic endpoint)

Important Security Notes

• The lobster has very broad system permissions (reading files, running commands, sending messages, browsing the web). Do not install it on a primary machine holding lots of sensitive data; if possible use a dedicated machine or a clean account.
• Do not expose the admin console (Control UI) to the public internet; keep it on localhost or behind a Tailscale / SSH tunnel.
• Always install the latest version (older versions had serious security vulnerabilities).
• Early token usage can be high; set a usage cap in the MYAI168 dashboard.

Prerequisites

Node.js 22.22.3+, 24.15+, or 25.9+ (Node 24 is the official default target and the recommended choice).

Check Node:

node --version

If missing, install (Ubuntu / Debian):

curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
sudo apt-get install -y nodejs

If it conflicts with the distro's old built-in Node (libnode-dev), remove that first and install again:

sudo apt-get remove -y libnode-dev
sudo apt-get install -y nodejs

Check your shell:

echo $SHELL

Ends with /bash → use ~/.bashrc; ends with /zsh → use ~/.zshrc.

npm install -g openclaw@latest

Verify:

openclaw --version

If command not found, add the npm global bin directory to PATH:

echo 'export PATH="$PATH:'$(npm config get prefix)'/bin"' >> ~/.bashrc
source ~/.bashrc

1. Open cc-switch and click the "OpenClaw" tab at the top.
2. Click "+" to add a provider.
3. Fill in:
   • Provider Key: myai168-claude (lowercase, hyphen)
   • Provider Name: MYAI168 Claude
   • API Protocol: choose Anthropic (not the default OpenAI Completions)
   • API Endpoint: https://www.myai168.com/en/api/anthropic
   • API Key: your MYAI168 key
   • Models: click "+ Add Model" and set Model ID to claude-opus-4-8
4. Click "+ Add", then Enable on the card.

cc-switch writes the settings into models.providers of ~/.openclaw/openclaw.json, looking roughly like this (for reference — usually no manual editing needed):

"models": {
  "mode": "merge",
  "providers": {
    "myai168-claude": {
      "baseUrl": "https://www.myai168.com/en/api/anthropic",
      "apiKey": "your-key",
      "api": "anthropic-messages",
      "models": [ { "id": "claude-opus-4-8",
                    "name": "claude-opus-4-8", "input": ["text"] } ]
    }
  }
}

(Note: the anthropic baseUrl is .../anthropic, without /v1 — OpenClaw's Anthropic client appends /v1 automatically; verified to work.)

Confirm it was written:

cat ~/.openclaw/openclaw.json

openclaw doctor

doctor asks a few setup questions; recommended answers:

• Tighten permissions on ~/.openclaw to 700? → Yes
• Update gateway service config to recommended defaults? → Yes
• Disable unavailable skills? → Yes (disabling tools your environment does not have keeps things clean)
• Enable bash shell completion? → Yes

Confirm the models were loaded:

openclaw models list

You should see your models, with yes in the Auth column and the main model tagged default / configured. (If a claude-cli/... entry also appears, it was auto-detected from a local Claude CLI install — ignore it.)

Launch test:

openclaw

Once in the chat UI (if the built-in OpenClaw setup agent — formerly called Crestodian — appears first, it hands you over to the main agent; the status bar at the bottom should show myai168-claude/claude-opus-4-8), ask a math question:

What is 123456 times 789? Reply with the number only.

If it answers 97406784, the connection works. (Do not verify with "who are you" — model self-identification is unreliable.)

You can also try chatting in the dashboard (it needs the Gateway running; on a fresh install start it first):

openclaw gateway start
openclaw gateway status     # Runtime: running means it is up
openclaw dashboard      # opens http://127.0.0.1:18789/ in the browser

• command not found: openclaw → PATH not in effect. Run source ~/.bashrc (for zsh: source ~/.zshrc) or reopen the terminal; if still not found, see the PATH fix in "1. Install OpenClaw". (On macOS: source ~/.zshrc.)
• npm ... EACCES → global directory permission problem; point the npm global directory to your home directory (npm config set prefix ~/.npm-global, then add ~/.npm-global/bin to PATH) and reinstall.
• doctor reports a JSON syntax error (after manually editing openclaw.json) → the editor turned straight quotes into curly quotes. Edit with nano, or disable smart quotes and paste again.
• model not allowed → the model is not on the allowlist. cc-switch usually takes care of this; if you edited the config manually, add it under agents.defaults.models.
• Replies fail with model-related errors → the model id or endpoint does not match the provider's actual values; compare and fix.
• Switch the main model → switch the enabled provider in cc-switch. (For manual setups on macOS: change agents.defaults.model.primary.)

Update:

openclaw update
# or: npm update -g openclaw

Security audit:

openclaw security audit --deep

Rotate the API Key

Update the API Key on the cc-switch card and Enable it again. (For manual setups on macOS: update the apiKey in ~/.openclaw/openclaw.json and restart.)

Config File Location

~/.openclaw/openclaw.json (the same directory also holds state/, logs/, etc.)

Official docs: https://docs.openclaw.ai