Setup Guide — Vibe Coding for Localization Engineers

❗

🚫 DO NOT USE LLMs TO TROUBLESHOOT OPENCLAW!

OPENCLAW IS TOO NEW. LLMs (ChatGPT, Claude, Gemini, etc.) do not know it. They will hallucinate commands that will break your setup.

Force LLMs consult only docs.openclaw.ai and find the right way to fix issues there based on the documentation.

🤖 Prompt for AI assistants — copy & paste

remember that when you troubleshoot openclaw you should always consult only this https://docs.openclaw.ai/ and find there the right way to fix it and not come up with your internal knowledge, when you provide an answer you reference the docs and say why to do it according to the docs

What you'll build

A Website Linguistic Quality Scanner

Scan any website and evaluate its linguistic quality across languages — all through your own web app with a friendly frontend. No coding background needed. Leave the session with a working tool you can deploy, share with colleagues, and show off on LinkedIn.

🎯 Tone of Voice
Formal vs casual, brand voice consistency

📖 Readability
Reading level, sentence complexity, clarity

✅ Accuracy
Terminology use, grammar, translation quality

🌐 UX per Language
Layout, navigation, locale-specific experience

Before the workshop

⚠

Required — please complete before May 20

We won't have time to troubleshoot installations during the session. This takes roughly 10 minutes. Complete it in advance so you can start building from minute one.

✨

First time using Terminal?

Terminal (Mac) and PowerShell (Windows) are just text-based ways to give your computer instructions. Instead of clicking icons, you type commands and press Enter. Don't worry — we'll tell you exactly what to type.

On a Mac

1. Press ⌘ Command + Space — this opens Spotlight Search
2. Type Terminal and press Return (Enter)
3. A dark window appears — that's Terminal! ✅

On Windows

1. Press Win + R — this opens the Run dialog
2. Type powershell and press Enter
3. A blue window appears — that's PowerShell! ✅

How to use the commands on this page

1. Click the "Copy" button next to any command — it copies the text automatically.
2. Go to Terminal / PowerShell and right-click → Paste (or press Ctrl+V on Windows / ⌘+V on Mac).
3. Press Enter / Return — the command runs and shows you the result.

💡 What do these commands do?

Every box with a dark background is a command — an instruction you give to your computer. We've added short explanations underneath each one so you always know what's happening. If something goes wrong, the error message usually tells you what's missing.

Install Python 3

The scanner we'll build runs on Python 3. Most computers already have it — check once, and if it's there, skip this step entirely.

1
Check if Python is already installed:
Terminal · macOS
```
python3 --version
```
If you see Python 3.x.x — you're done.
2

If not installed — go to python.org/downloads and click the big yellow Download Python 3.x.x button. Open the downloaded file and click through the installer.

1
Check if Python is already installed:
PowerShell · Windows
```
python --version
```
If you see Python 3.x.x — you're done.
2
If not installed — the fastest way is one command in PowerShell:
PowerShell · Windows
```
winget install Python.Python.3
```
Or go to python.org/downloads, download the installer, and run it. Important: on the first installer screen, tick "Add Python to PATH" before clicking Install.

Install OpenClaw

OpenClaw is the tool we'll use throughout the session. Select your OS below and run the command in your terminal.

docs.openclaw.ai/install

1

Open Terminal — see how below if you're not sure
2
Paste and run this command:
Terminal · macOS
```
curl -fsSL https://openclaw.ai/install.sh | bash
```
Official installer — detects your OS, installs Node if needed, installs OpenClaw, and launches the setup wizard.
3

Follow the on-screen prompts to finish the wizard.

How to open Terminal macOS

Press ⌘ Command + Space to open Spotlight Search
Type Terminal and press Return
Click the Copy button on the command above — then right-click → Paste into Terminal (or press ⌘+V)
Press Return to run it

Using an AI coding assistant?

If you have Claude Code, GitHub Copilot, or GitHub Codex — paste the install command directly and ask it to guide you through setup. Say: "Help me run this OpenClaw install command."

1

Open PowerShell — see how below
2
Paste and run this command:
PowerShell · Windows
```
& ([scriptblock]::Create((iwr -useb https://openclaw.ai/install.ps1)))
```
Official Windows installer. PowerShell works well; WSL2 also supported for extra stability.
3

Follow the on-screen prompts to finish the wizard.

⚠ If you get a "SecurityException" error

Windows blocks scripts by default. If you see an error like:
SecurityException : The term 'SecurityException' is not recognized...
You're hitting a PowerShell execution policy block. Run this command first to allow scripts, then retry the install:

PowerShell · Windows

Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser

If that still fails, use this temporary bypass instead:

PowerShell · Windows

Set-ExecutionPolicy -ExecutionPolicy Bypass -Scope Process

How to open PowerShell Windows

Press Win + R to open the Run dialog
Type powershell and press Enter
Click the Copy button on the command above — then right-click → Paste into PowerShell (or press Ctrl+V)
Press Enter to run it

Using an AI coding assistant?

If you have Claude Code, GitHub Copilot, or GitHub Codex — paste the install command directly and ask it to guide you through setup. Say: "Help me run this OpenClaw install command."

📺 During setup — you can skip everything for now

The wizard will ask about channels (Telegram, WhatsApp, Signal, etc.), skills, and other extras. You can safely skip everything for now — just choose "Skip for now" on each screen. For the workshop, we'll be using the built-in Web UI, which doesn't need any of this. Everything can be added later.

When asked "How do you want to hatch your agent?", choose "Hatch in Browser". This opens the chat in your web browser — exactly what we need for the workshop.

Configure OpenRouter

OpenClaw uses OpenRouter to access AI models. Connect your API key so the workshop tools can run. Custom.MT will provide the key before the session.

docs.openclaw.ai — OpenRouter provider openrouter.ai — OpenClaw integration guide

Easiest: use the guided wizard

The onboard command walks you through the entire OpenRouter setup interactively. Recommended if this is your first time.

Terminal · macOS & Windows

openclaw onboard

When you see the prompt ◆ Model/auth provider, choose More, then select OpenRouter from the list and press Enter. Paste the OpenRouter API key you received from Custom.MT (begins with sk-or-...). If you did not receive a key from Custom.MT, just skip this step.

⚡ Fastest: one command

Already have your OpenRouter key? Run this single command — replace the key with the one from Custom.MT:

Terminal · macOS & Windows

openclaw onboard --auth-choice apiKey --token-provider openrouter --token "sk-or-v1-your-key-here"

Replace sk-or-v1-your-key-here with the actual key from Custom.MT.

Or set the key directly without the wizard:

1
Open Terminal (same as Step 1)
2
Set your OpenRouter key:
Terminal · macOS
```
openclaw config set env.OPENROUTER_API_KEY \$OPENROUTER_API_KEY
```
Make sure the OPENROUTER_API_KEY environment variable is already set in your terminal session before running this command.
📌 Make it permanent

Run this command to add the key to your ~/.zshrc:
Terminal · macOS
```
echo 'export OPENROUTER_API_KEY="sk-or-v1-your-key-here"' >> ~/.zshrc && source ~/.zshrc
```
Replace sk-or-v1-your-key-here with your actual key from Custom.MT. This appends the line to ~/.zshrc and loads it immediately.
3
Verify the key was saved:
Terminal · macOS
```
openclaw models status
```
You should see openrouter listed as an active provider.
4
Probe the connection to confirm it works:
Terminal · macOS
```
openclaw models status --probe
```
This actually tests the connection by making a small API call. If you see ✓ openrouter (green checkmark), your connection is working. Run openclaw models status anytime to check the status of all your providers.

Or set the key directly without the wizard:

1
Open PowerShell (same as Step 1)
2
Set your OpenRouter key:
PowerShell · Windows
```
openclaw config set env.OPENROUTER_API_KEY \$OPENROUTER_API_KEY
```
Make sure the OPENROUTER_API_KEY environment variable is already set in your terminal session before running this command.

📌 Make it permanent

Run this once in PowerShell to make the key available in all future sessions:

[System.Environment]::SetEnvironmentVariable('OPENROUTER_API_KEY','sk-or-v1-your-key-here','User')

Replace the key with the one from Custom.MT. Restart PowerShell for it to take effect.
3
Verify the key was saved:
PowerShell · Windows
```
openclaw models status
```
You should see openrouter listed as an active provider.
4
Probe the connection to confirm it works:
PowerShell · Windows
```
openclaw models status --probe
```
This actually tests the connection by making a small API call. If you see ✓ openrouter (green checkmark), your connection is working. Run openclaw models status anytime to check the status of all your providers.

Set the model & verify

Configure OpenClaw to use MiniMax M2.7 — the model we'll use in the workshop — then launch the WebUI and confirm it responds in the chat. If you get an answer, you're fully set up.

openrouter.ai — MiniMax M2.7 model page

1

Open Terminal / PowerShell (same as Steps 1 & 2)
2
Set MiniMax M2.7 as your active model:
Terminal · macOS & Windows
```
openclaw models set openrouter/minimax/minimax-m2.7
```
If prompted to choose from a list, select "Enter manually" and type the full model ID: openrouter/minimax/minimax-m2.7

When prompted "How do you want to hatch your bot?" — choose Open the Web UI:

Prompt

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

4
Or launch the WebUI at any time with:
Terminal · macOS & Windows
```
openclaw dashboard
```
This opens the browser dashboard at http://127.0.0.1:18789. If it doesn't open automatically, paste that address into your browser.

💡 Tip: You can view your agent's logs at http://127.0.0.1:18789/logs — useful for debugging if something goes wrong.
⚠ If you see "Device pairing required"

You might get an error in the browser saying "Device pairing required" with a device code. This is a one-time security step. Copy the device code from the error and run this in your Terminal / PowerShell:
Terminal · macOS & Windows
```
openclaw devices approve YOUR-DEVICE-CODE
```
Replace YOUR-DEVICE-CODE with the code shown in the error (it will look like a long ID, e.g. xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx). Then reconnect — the dashboard should open.
5

Send a test message in the chat — type anything, for example: "Hello, what model are you?"

If MiniMax M2.7 responds in the chat window, your setup is complete. ✓

No response in the chat?

Run the doctor command — it detects common issues and can fix them automatically:

Terminal · macOS & Windows

openclaw doctor --fix

Also check that openclaw models status shows openrouter as an active provider, and that the model name is spelled exactly as shown above — including the openrouter/ prefix.

🔄 If any error persists after fixing

Restart OpenClaw and try the doctor — most issues clear up after a restart:

Terminal · macOS & Windows

openclaw gateway restart

If the problem still doesn't go away, run the doctor with auto-fix and restart again:

Terminal · macOS & Windows

openclaw doctor --fix && openclaw gateway restart

Run the setup validator

One final check before the workshop. This command tests everything at once — Node.js, OpenClaw, API key, internet connection, and gateway. You'll see a ✅ grid if you're ready, or ✘ with exact fix-it instructions for anything that's missing.

🎯

Run this last — after completing Steps 00, 01, 02, and 03

Copy this command by clicking the button below, then go to your Terminal / PowerShell, paste it, and press Enter.

Terminal · macOS & Linux

curl -fsSL https://custommt-workshop.pages.dev/check_setup.sh | bash

PowerShell · Windows

irm https://custommt-workshop.pages.dev/check_setup.ps1 | iex

This downloads and runs the check automatically — same as the macOS version, just adapted for PowerShell.

Expected result

You'll see a checklist with 8 items. If all show ✔ — you're all set! 🦞
If any show ✘, the script tells you exactly what to fix (it's usually a missing step from 00–03 above).

💡 If the script says your OpenRouter key is missing but you already configured it — try sending a test message in the dashboard chat anyway. It might actually work — the key is sometimes stored in a different location than where the script looks. If the chat doesn't respond, follow the script's instructions and restart with openclaw gateway restart.

Pre-workshop checklist

Confirm all five before May 20:

☑ Python 3 installed — python3 --version (macOS) or python --version (Windows) prints a version number

☑ OpenClaw installed — running openclaw --version prints a version number

☑ OpenRouter key configured — openclaw models status --probe shows ✓ for openrouter

☑ Web browser ready — Chrome, Firefox, Safari, Edge, anything works

☑ Setup validator passes — run curl -fsSL https://custommt-workshop.pages.dev/check_setup.sh | bash (macOS) or irm https://custommt-workshop.pages.dev/check_setup.ps1 | iex (Windows) and see all ✅

Need help before the session?

Reach out to the Custom.MT team if you run into issues. The OpenClaw FAQ also covers the most common installation problems.

⚠️ Stuck on opening Terminal? See the ✨ First time using Terminal? section above for step-by-step instructions with screenshots of what to expect.