Question 1

Installing n8n on your VPS — Complete Guide

Accepted Answer

## What is n8n?

n8n is a powerful open-source workflow automation platform — similar to Zapier or Make, but self-hosted on your own VPS. With 400+ native integrations, built-in AI capabilities, and a visual drag-and-drop editor, you have full control over your automations and your data.

![n8n Workflow Editor](/images/vps-apps/n8n-template/hero-workflow.png)

---

## System Requirements

| Component | Minimum | Recommended | Enterprise |
|-----------|---------|-------------|------------|
| RAM | 2 GB | 4 GB | 8 GB |
| CPU | 1 vCPU | 2 vCPU | 4 vCPU |
| Storage | 25 GB NVMe | 50 GB NVMe | 100 GB NVMe |
| OS | Ubuntu 24.04 | Ubuntu 24.04 | Ubuntu 24.04 |

---

## Step 1: Order VPS with n8n Template

The easiest way to install n8n is via our **1-click installation**:

1. Go to the [VPS Configurator](/en/configurator/vps)
2. Choose your desired package (minimum 2 GB RAM)
3. Select **n8n** as the application template
4. Complete your order

After payment, your VPS is automatically provisioned with the complete n8n stack.

---

## Step 2: What Gets Installed Automatically?

Our 1-click installation configures the following components:

- **Docker Engine** — Containerized deployment for reliability
- **PostgreSQL 16** — Professional database backend (more reliable than SQLite)
- **Caddy 2 Web Server** — Reverse proxy with automatic HTTPS via Let's Encrypt
- **n8n (latest)** — The latest version of n8n in a Docker container
- **Daily Backups** — Automatic backup every night at 03:00 (7 days retained)
- **Update Script** — Easy updates with a single command

All components are installed in `/opt/n8n/`.

---

## Step 3: First Access to n8n

Once the installation is complete:

1. Open your browser and go to `http://YOUR-VPS-IP`
2. n8n displays the registration screen
3. **The first user to register automatically becomes the owner/admin**
4. Fill in your name, email address, and password
5. You're now ready to build workflows!

> **Important:** Create your admin account as soon as possible after installation. Anyone with access to the IP address can otherwise claim the first account.

---

## Step 4: Connect Your Own Domain (Recommended)

For a professional setup with HTTPS:

### Set Up DNS
Create an **A record** at your domain provider:
```
n8n.yourdomain.com  →  A  →  YOUR-VPS-IP
```

### Configure Caddy
Connect via SSH to your VPS and edit the Caddyfile:
```bash
sudo nano /opt/n8n/Caddyfile
```

Replace the existing content with:
```
n8n.yourdomain.com {
    reverse_proxy n8n:5678
}
```

Restart Caddy:
```bash
cd /opt/n8n && docker compose restart caddy
```

Caddy automatically obtains a free SSL certificate via Let's Encrypt. After a few seconds, your n8n is accessible at `https://n8n.yourdomain.com`.

---

## Step 5: Updating n8n

To update n8n to the latest version:

```bash
sudo /opt/n8n/update.sh
```

This script:
- Downloads the latest n8n Docker image
- Restarts the containers automatically
- Cleans up old Docker images
- Your workflows and data remain fully preserved

---

## Step 6: Managing Backups

### Automatic Backups
Every night at 03:00, an automatic backup is made of:
- The PostgreSQL database
- The n8n configuration and data

Backups are stored in `/opt/n8n/backups/` (last 7 days).

### Manual Backup
You can also make a manual backup:
```bash
sudo /opt/n8n/backup.sh
```

### Restoring a Backup
To restore a backup:
```bash
# Stop n8n
cd /opt/n8n && docker compose down

# Restore the database
gunzip < /opt/n8n/backups/BACKUP-FILE.sql.gz | docker exec -i n8n-postgres psql -U n8n

# Start n8n again
docker compose up -d
```

---

## Directory Structure

The complete n8n installation is located in `/opt/n8n/`:

```
/opt/n8n/
├── docker-compose.yml    # Docker configuration
├── Caddyfile             # Web server configuration
├── .env                  # Environment variables
├── update.sh             # Update script
├── backup.sh             # Backup script
├── backups/              # Backup files
└── data/                 # n8n workflow data
```

---

## FAQ

**How many workflows can I run?**
Unlimited! There are no limits on the number of workflows or executions. The only limitation is your VPS capacity.

**Can I install n8n manually?**
Yes, but we recommend the 1-click installation. Manual installation requires Docker, PostgreSQL, and a reverse proxy — our template configures all of this automatically.

**What if I need more resources?**
You can upgrade your VPS at any time via your dashboard. RAM and CPU upgrades require a short reboot, storage can be expanded online.

**Does n8n run on Windows?**
Our VPS templates run on Ubuntu 24.04 (Linux). n8n itself runs in a Docker container, so the OS doesn't matter for n8n.

Question 2

Stream Monitor: monitoring your audio stream

Accepted Answer

## What is the Stream Monitor?

The Stream Monitor is a comprehensive monitoring tool that lets you track the health and availability of your audio streaming service in real time. The monitor checks your stream at regular intervals and automatically detects issues such as outages, silence, and quality degradation.

![Stream Monitor Dashboard](/images/help/stream-monitor-enterprise.png)

The Stream Monitor is available as an add-on to your audio streaming package and is offered in three subscription tiers: **Basic**, **Pro**, and **Enterprise**.

---

## Subscription Tiers

The Stream Monitor is available in three tiers, each with more features:

### Basic

- **Check interval:** every 5 minutes
- Online/offline status detection
- Uptime statistics (24 hours, 7 days, 30 days)
- Email notifications on outages
- Incident history

### Pro

All Basic features, plus:

- **Check interval:** every 1 minute
- **Silence detection** — detects when your stream is silent (configurable threshold)
- **Metadata monitoring** — tracks what's currently playing and detects stuck metadata
- Advanced incident types (silence, bitrate drop, stuck metadata)

### Enterprise

All Pro features, plus:

- **Check interval:** every 30 seconds
- **Multi-mount point monitoring** — monitor multiple mount points (e.g., main, mobile, fallback) simultaneously
- **Webhook notifications** — receive real-time notifications via webhook with HMAC-SHA256 signing
- **Maintenance windows** — schedule times when notifications are suppressed

---

## The Dashboard

After activation, you can find the Stream Monitor in your dashboard under **Services > [Your Streaming Service] > Manage > Stream Monitor**.

### Status Page

The main page shows an overview of your stream:

- **Current status** — Online, Offline, Silent, Degraded, or Error
- **Protocol** — Shoutcast or Icecast
- **Subscription tier** — Basic, Pro, or Enterprise
- **Last check** — time of the most recent check
- **Uptime percentages** — availability over 24 hours, 7 days, and 30 days

### Check History

A visual timeline shows the results of recent checks. Each check records:

- Status (online/offline/silent/degraded/error)
- Response time in milliseconds
- Bitrate (kbps)
- Audio level (dB)
- Current track (artist and title)
- Listener count
- AutoDJ status

### Active Incidents

When an issue is detected, an incident appears on the dashboard. Incidents include:

- **Type** — offline, silence, bitrate drop, stuck metadata, AutoDJ failover, high latency
- **Severity** — warning or critical
- **Start time** and duration
- **Description** of the issue

You can **acknowledge** incidents to indicate you're aware of them.

---

## Setting Up Notifications

### Email Notifications

By default, notifications are sent to your account email address. You can customize this:

1. Go to **Stream Monitor > Settings**
2. Enable **Notifications**
3. Enter a **Notification email address**
4. Set the **Cooldown period** (default: 15 minutes) — this prevents you from being flooded with notifications

### Webhook Notifications (Enterprise)

For advanced integrations, you can set up webhook notifications:

1. Go to **Stream Monitor > Settings**
2. Enter your **Webhook URL**
3. Webhooks are sent with an **HMAC-SHA256 signature** in the `X-Maenda-Signature` header

**Webhook payload example:**

```json
{
  "event": "incident_created",
  "timestamp": "2025-02-25T12:00:00Z",
  "monitor": {
    "id": "mon_123",
    "serviceId": "svc_456",
    "streamUrl": "https://stream.example.nl:8000/live",
    "tier": "enterprise"
  },
  "incident": {
    "type": "offline",
    "severity": "critical",
    "description": "Stream is unreachable"
  },
  "check": {
    "status": "offline",
    "responseTimeMs": 10000,
    "bitrate": null,
    "isSilent": false,
    "nowPlaying": null
  }
}
```

**Webhook events:**
- `incident_created` — new incident detected
- `incident_resolved` — incident resolved
- `check_failed` — individual check failed

The webhook retries up to 3 times with increasing delay (1s, 5s, 15s) on failed delivery.

---

## Silence Detection (Pro & Enterprise)

Silence detection recognizes when your stream is technically online but not broadcasting audio. This is essential for radio streams where silence can be a serious issue.

### How It Works

The monitor analyzes 32KB of audio data from your stream and calculates:

- **Byte variance** — how varied the audio data is
- **Shannon entropy** — information content of the audio signal
- **dB level** — estimated sound level (RMS and peak)

Silence is detected when byte variance is below 50 AND entropy is below 5.0 bits.

### Adjusting Thresholds

1. Go to **Stream Monitor > Settings**
2. Adjust the **Silence threshold** (default: -50 dB)
3. Set the **Silence duration** (default: 30 seconds) — how long silence must last before an incident is created

---

## Multi-Mount Point Monitoring (Enterprise)

If your stream has multiple mount points (e.g., `/live`, `/mobile`, `/fallback`), you can monitor them all simultaneously.

### Setup

1. Go to **Stream Monitor > Settings**
2. Add your **Mount points** as a list
3. Each mount point is checked individually
4. Incidents are tracked per mount point

---

## Maintenance Windows (Enterprise)

Schedule periods when notifications are suppressed, for example during planned maintenance or nightly tests.

### Setup

1. Go to **Stream Monitor > Maintenance Windows**
2. Select the **day** (Monday through Sunday)
3. Set the **start and end hour**
4. During maintenance windows, no notifications are sent, but checks continue normally

---

## Supported Protocols

The Stream Monitor supports the two most commonly used streaming protocols:

### Shoutcast

- Fully supported with ICY metadata
- Automatic listener detection via the statistics page
- AutoDJ detection

### Icecast

- Fully supported with ICY metadata
- Support for multiple mount points
- Metadata parsing for now-playing information

Both protocols support:
- HTTPS/TLS connections
- Automatic redirect following
- Bitrate detection via ICY headers
- Artist and title information

---

## Incident Types

The Stream Monitor can detect the following issues:

| Type | Description | Minimum Tier |
|------|-------------|--------------|
| **Offline** | Stream is unreachable | Basic |
| **Silence** | Audio is silent (below threshold) | Pro |
| **Bitrate drop** | Bitrate is lower than expected | Pro |
| **Stuck metadata** | Same track displayed for too long | Pro |
| **AutoDJ failover** | AutoDJ has taken over (live DJ dropped) | Pro |
| **High latency** | Response time is abnormally high | Basic |

---

## Uptime Statistics

The Stream Monitor automatically calculates uptime percentages:

- **24 hours** — availability over the past day
- **7 days** — availability over the past week
- **30 days** — availability over the past month

These percentages are calculated based on the number of successful checks relative to the total number of checks. Maintenance windows are excluded from the calculation.

---

## Frequently Asked Questions

### How quickly am I notified of an outage?

This depends on your subscription tier:
- **Basic:** maximum 5 minutes
- **Pro:** maximum 1 minute
- **Enterprise:** maximum 30 seconds

### Can I use the Stream Monitor without a streaming package?

No, the Stream Monitor is an add-on that is linked to an existing audio streaming package at Maenda Media.

### What happens during a maintenance window?

Checks are still performed and recorded, but no notifications are sent. Incidents are still created for record-keeping.

### How do I verify the webhook signature?

The webhook contains an `X-Maenda-Signature` header with the format `sha256=<hex>`. Calculate the HMAC-SHA256 of the request body with your secret key and compare it with the value in the header.

### Can I export historical data?

Yes, via the Stream Statistics page you can export data as CSV or PDF. This includes listener counts, bandwidth, and peaks over the selected period.

### Does the monitor also detect video issues?

No, the Stream Monitor is specifically designed for audio streams (Shoutcast/Icecast). Video streaming has a separate statistics panel.

Question 3

Building n8n Workflows — User Guide

Accepted Answer

# Building n8n Workflows — User Guide

This guide walks you through using n8n to build powerful automation workflows step by step. From simple tasks to complex AI-driven processes.

---

## The n8n Interface

After logging into your n8n installation, you'll see the **dashboard** with an overview of all your workflows.

![n8n workflow editor — visual drag-and-drop interface](/images/vps-apps/n8n-template/hero-workflow.png)

The interface consists of:

| Component | Description |
|-----------|-------------|
| **Canvas** | The central workspace where you place and connect nodes |
| **Node Panel** | Left panel with all available nodes and integrations |
| **Toolbar** | Top bar with options to test, activate, and save |
| **Execution Log** | Bottom right for viewing previous executions |
| **Settings** | Workflow settings like name, tags, and error handling |

---

## Your First Workflow

Let's build a simple workflow that sends a weather report email every morning.

### Step 1: Create a new workflow

1. Click **"+ New Workflow"** in the top right
2. Name your workflow, e.g., *"Daily Weather Report"*
3. You start on an empty canvas with a **trigger node**

### Step 2: Set up the trigger

The trigger determines **when** your workflow starts:

- **Schedule Trigger** — At fixed times (e.g., every day at 07:00)
- **Webhook** — When a URL is called
- **Event-based** — On an app event (e.g., new email)

For our weather report, we choose **Schedule Trigger**:

```
Trigger: Schedule
Rule: Every day at 07:00
Timezone: Europe/Amsterdam
```

### Step 3: Add nodes

1. Click the **+** icon to the right of the trigger
2. Search for **"HTTP Request"** in the node panel
3. Configure the node:

```
Method: GET
URL: https://api.openweathermap.org/data/2.5/weather
Query Parameters:
  q: Amsterdam
  appid: your-api-key
  units: metric
  lang: en
```

4. Add a **"Send Email"** node after the HTTP Request
5. Connect the HTTP Request output to the Email node

### Step 4: Test and activate

1. Click **"Test Workflow"** to run the workflow manually
2. Check the output of each node in the **execution log**
3. When everything works, click the **"Active"** toggle to enable the workflow

---

## Commonly Used Nodes

Here are the nodes you'll use most frequently:

### Triggers

| Node | Usage |
|------|-------|
| **Schedule Trigger** | Run workflows at fixed times |
| **Webhook** | Start workflows via HTTP request |
| **Email Trigger (IMAP)** | React to incoming emails |
| **Cron** | Advanced schedules with cron expressions |

### Data & Logic

| Node | Usage |
|------|-------|
| **IF** | Conditional logic (if/then) |
| **Switch** | Multiple paths based on value |
| **Merge** | Combine data from multiple sources |
| **Set** | Add or modify fields |
| **Code** | Custom JavaScript or Python code |
| **Split In Batches** | Process large datasets in parts |

### Communication

| Node | Usage |
|------|-------|
| **Send Email** | Send emails via SMTP |
| **Slack** | Messages to Slack channels |
| **Telegram** | Messages via Telegram bot |
| **Discord** | Messages to Discord servers |

### Data Storage

| Node | Usage |
|------|-------|
| **Google Sheets** | Read/write to spreadsheets |
| **Airtable** | Database-like storage |
| **PostgreSQL** | Execute SQL queries directly |
| **MySQL** | MySQL database operations |

---

## AI Workflows with LangChain

n8n has built-in AI capabilities via **LangChain integration**. Build AI agents that autonomously execute tasks.

![AI Agent workflow in n8n with LangChain nodes](/images/vps-apps/n8n-template/ai-agent-workflow.png)

### AI Nodes Overview

![Available AI nodes in the n8n panel](/images/vps-apps/n8n-template/ai-nodes-panel.png)

The key AI nodes:

| Node | Function |
|------|----------|
| **AI Agent** | Autonomous agent that can use tools |
| **Basic LLM Chain** | Simple prompt → response chain |
| **Conversational Agent** | Agent with conversation memory |
| **OpenAI Chat Model** | GPT-4, GPT-3.5 models |
| **Anthropic Chat Model** | Claude models |
| **Vector Store** | Storage for embeddings (RAG) |
| **Text Splitter** | Split documents for embeddings |

### Example: AI Customer Service Agent

Here we build an AI agent that answers customer questions based on your knowledge base:

![AI Agent configuration with tools and memory](/images/vps-apps/n8n-template/ai-agent-config.png)

**Workflow setup:**

1. **Webhook Trigger** — Receives customer questions via API
2. **AI Agent** — Processes the question with:
   - **Chat Model**: OpenAI GPT-4 or Anthropic Claude
   - **Memory**: Window Buffer Memory (remembers last 10 messages)
   - **Tools**:
     - *Vector Store Tool* — Searches your knowledge base
     - *HTTP Request Tool* — Fetches live product info
     - *Calculator* — For price calculations
3. **Respond to Webhook** — Returns the answer

```
System Prompt:
"You are a customer service representative for [company].
Answer questions based on the knowledge base.
Be friendly and professional.
If you don't know the answer, refer to support@company.com."
```

### Multi-Agent Workflows

For more complex scenarios, combine multiple AI agents:

![Multi-agent workflow example](/images/vps-apps/n8n-template/multi-agent-example.jpg)

Examples:

- **Content Pipeline**: Agent 1 (research) → Agent 2 (writing) → Agent 3 (review)
- **Data Analysis**: Agent 1 (data fetching) → Agent 2 (analysis) → Agent 3 (report)
- **Customer Service**: Router Agent → Specialist Agent (technical/billing/general)

---

## Writing Custom Code

With the **Code** node, you can run JavaScript or Python for complex logic:

### JavaScript Example

```javascript
// Filter and transform all items
const results = items.map(item => {
  const data = item.json;
  return {
    json: {
      name: data.firstName + ' ' + data.lastName,
      email: data.email.toLowerCase(),
      isActive: data.lastLogin > Date.now() - 30 * 24 * 60 * 60 * 1000,
      label: data.totalOrders > 10 ? 'VIP' : 'Standard'
    }
  };
});

return results;
```

### Python Example

```python
# Data analysis with Python
import json
from datetime import datetime

results = []
for item in items:
    data = item['json']
    # Calculate age in days
    created = datetime.fromisoformat(data['createdAt'])
    age_days = (datetime.now() - created).days
    
    results.append({
        'json': {
            'id': data['id'],
            'age_days': age_days,
            'status': 'new' if age_days < 30 else 'existing'
        }
    })

return results
```

---

## Managing Credentials

Credentials (API keys, passwords) are securely stored in n8n:

1. Go to **Settings** → **Credentials**
2. Click **"+ Add Credential"**
3. Choose the type (e.g., *OpenAI API*, *Gmail OAuth*, *Slack Bot*)
4. Fill in the required details
5. Click **"Save"**

**Security tips:**

- Credentials are encrypted in the database
- Use **environment variables** for sensitive values
- Create separate credentials per environment (test/production)
- Limit API keys to only the required permissions

---

## Organizing Workflows

### Tags

Use tags to categorize workflows:

- `production` — Active, tested workflows
- `development` — Workflows in development
- `marketing` — Marketing automation
- `finance` — Financial processes

### Folders

Organize workflows in folders by department or project.

### Versioning

n8n supports **workflow versioning**:

- Each save creates a new version
- You can revert to previous versions
- Export workflows as JSON for version control in Git

```bash
# Export workflow as JSON backup
curl -X GET https://your-n8n.com/api/v1/workflows/WORKFLOW_ID \
  -H "X-N8N-API-KEY: your-api-key" \
  -o workflow-backup.json
```

---

## Error Handling

Make your workflows robust with proper error handling:

### Error Trigger

Create a separate workflow that starts on errors:

1. Use the **Error Trigger** node
2. Send a notification via Slack/email on errors
3. Log error details to a spreadsheet

### Try/Catch Pattern

1. Add an **IF** node after a risky operation
2. Check for successful output
3. Route errors to an alternative path

### Retry Logic

For API nodes, you can set up automatic retries:

```
Retry On Fail: Enabled
Max Tries: 3
Wait Between Tries: 1000ms
```

---

## Useful Tips

1. **Sticky Notes** — Add notes to your canvas to document workflows
2. **Sub-workflows** — Split complex workflows into smaller, reusable parts
3. **Expressions** — Use `{{ $json.field }}` to dynamically reference data
4. **Pinned Data** — Pin test data for consistent testing
5. **Keyboard shortcuts**:
   - `Ctrl+S` — Save
   - `Ctrl+Enter` — Run test
   - `Tab` — Open node panel
   - `Ctrl+Shift+E` — Open execution log
6. **Webhook URLs** — In production, always use the *Production URL*, not the test URL
7. **Rate Limiting** — Add `Wait` nodes between API calls to respect rate limits

---

## More Information

- **n8n Documentation**: [docs.n8n.io](https://docs.n8n.io)
- **Community Forum**: [community.n8n.io](https://community.n8n.io)
- **Workflow Templates**: [n8n.io/workflows](https://n8n.io/workflows)
- **LangChain in n8n**: [docs.n8n.io/langchain](https://docs.n8n.io/langchain)

Need help building a specific workflow? Contact our support team via the chat window at the bottom right or send an email to support@maenda.media.

Question 4

Installing OpenClaw on Your VPS — Complete Guide

Accepted Answer

# Installing OpenClaw on Your VPS — Complete Guide

OpenClaw is an **open-source AI assistant** that runs on your own server. You maintain full control over your data and privacy. This guide walks you through the complete installation process.

---

## What is OpenClaw?

OpenClaw is a self-hosted AI assistant that you can connect to popular messaging platforms like **Telegram**, **WhatsApp**, **Discord**, and **Slack**. It offers:

- **AI conversations** with GPT-4, Claude, or local models
- **Web browsing** — the assistant can visit websites and retrieve information
- **File management** — read, write, and analyze documents
- **Command execution** — controlled shell access on your server
- **Skills system** — modular capabilities you can enable/disable
- **Privacy-first** — all data stays on your server

---

## System Requirements

| Component | Minimum | Recommended |
|-----------|---------|-------------|
| **RAM** | 2 GB | 4 GB (for web browsing) |
| **CPU** | 1 vCPU | 2 vCPU |
| **Storage** | 25 GB NVMe | 50 GB NVMe |
| **OS** | Ubuntu 24.04 LTS | Ubuntu 24.04 LTS |

> **Tip:** Choose at least the **Browser Automation** package (4 GB RAM) if you want to use the web browsing feature. Headless Chrome requires additional memory.

---

## Step 1: Order Your VPS

1. Go to [maenda.media/configurator/vps](https://maenda.media/configurator/vps)
2. Choose a VPS package that meets the system requirements
3. Select **"OpenClaw"** as the **Template**
4. Complete your order

After payment, your VPS is automatically created and configured. This takes approximately **3-5 minutes**.

---

## Step 2: What Gets Automatically Installed?

When choosing the OpenClaw template, the following is automatically installed and configured:

| Component | Version | Description |
|-----------|---------|-------------|
| **Ubuntu** | 24.04 LTS | Operating system |
| **Node.js** | 22 LTS | Runtime for OpenClaw |
| **Go** | 1.23 | Compiler for native modules |
| **UFW** | Latest | Firewall (only port 22 open) |
| **fail2ban** | Latest | Brute-force protection |
| **OpenClaw** | Latest | The AI assistant itself |
| **logrotate** | System | Automatic log rotation |

### Security Configuration

The following security measures are automatically applied:

```
✅ UFW Firewall — Only SSH (port 22) allowed
✅ fail2ban — Blocks IPs after 5 failed login attempts
✅ Automatic updates — Security updates installed automatically
✅ SSH hardening — Root login disabled, key-based auth only
✅ Logrotate — Prevents logs from filling the disk
```

---

## Step 3: Connect via SSH

After installation, you'll receive an email with your SSH credentials.

```bash
ssh user@your-server-ip
```

> **Note:** On the first connection, you'll be asked to accept the server fingerprint. Type `yes` to continue.

---

## Step 4: Initial Configuration (Onboarding)

Upon first SSH login, the **OpenClaw onboarding wizard** starts automatically:

![OpenClaw onboarding wizard — step-by-step configuration](/images/vps-apps/openclaw-template/onboarding.png)

The wizard guides you through:

### 4.1 Setting Up AI Provider

Choose your AI provider and enter your API key:

| Provider | Models | API Key |
|----------|--------|--------|
| **OpenAI** | GPT-4, GPT-4o, GPT-3.5 | [platform.openai.com/api-keys](https://platform.openai.com/api-keys) |
| **Anthropic** | Claude 4.5 Sonnet, Claude 3.5 Haiku | [console.anthropic.com](https://console.anthropic.com) |
| **Local** | Ollama, LM Studio | No API key needed |

### 4.2 Connecting a Messaging Platform

Connect at least one messaging platform:

**Telegram (recommended for beginners):**
1. Open Telegram and search for **@BotFather**
2. Send `/newbot` and follow the instructions
3. Copy the bot token
4. Paste the token in the wizard

### 4.3 Configuring Skills

Choose which capabilities your assistant has:

- **Web Browsing** — Visit websites and retrieve information
- **File Management** — Read and write files
- **Command Execution** — Execute shell commands (with restrictions)
- **Image Generation** — Generate images with DALL-E
- **Code Execution** — Run Python/JavaScript code in sandbox

---

## Step 5: The Terminal UI (TUI)

OpenClaw has a built-in terminal interface for direct interaction:

![OpenClaw Terminal UI — interactive console interface](/images/vps-apps/openclaw-template/terminal-tui.gif)

### Starting the TUI

```bash
openclaw tui
```

### TUI Commands

| Command | Description |
|---------|-------------|
| `/help` | Show all available commands |
| `/status` | View status of all services |
| `/config` | Open configuration editor |
| `/logs` | View recent logs |
| `/restart` | Restart the OpenClaw service |
| `/skills` | Manage capabilities |
| `/quit` | Exit the TUI |

---

## Step 6: Connecting a Domain (Optional)

To access OpenClaw via a web browser (for the Control UI), connect a domain:

### DNS Configuration

```
Type: A
Name: openclaw (or @ for main domain)
Value: your-server-ip
TTL: 3600
```

### Caddy Reverse Proxy

```bash
sudo nano /etc/caddy/Caddyfile
```

```
openclaw.yourdomain.com {
    reverse_proxy localhost:3000
}
```

```bash
sudo systemctl restart caddy
```

Caddy automatically handles SSL certificates via Let's Encrypt.

---

## Updates & Maintenance

### Updating OpenClaw

```bash
openclaw update
```

### Viewing Logs

```bash
journalctl -u openclaw -f
```

### Backup

```bash
tar -czf openclaw-backup-$(date +%Y%m%d).tar.gz /opt/openclaw/data
```

---

## Directory Structure

```
/opt/openclaw/
├── data/               # Conversation history, files
│   ├── conversations/  # Saved conversations
│   ├── files/          # Uploaded/generated files
│   └── db/             # SQLite database
├── config/             # Configuration files
│   ├── config.yml      # Main configuration
│   ├── skills.yml      # Skills configuration
│   └── platforms.yml   # Messaging platform configuration
├── skills/             # Installed capabilities
├── logs/               # Log files
└── node_modules/       # Node.js dependencies
```

---

## FAQ

### Which messaging platforms are supported?

OpenClaw supports: **Telegram**, **WhatsApp**, **Discord**, **Slack**, **Signal**, and **Matrix**. You can connect multiple platforms simultaneously.

### Is my data safe?

Yes. All data is stored locally on your server. No data is sent to external servers (except to the AI provider for generating responses). You can also use a local AI model (via Ollama) for complete privacy.

### How much memory do I need?

- **2 GB RAM** — Basic: text conversations and simple tasks
- **4 GB RAM** — Recommended: web browsing and file management
- **8 GB RAM** — Full: all features including local AI models

---

## More Information

- **OpenClaw Documentation**: [open-claw.org/docs](https://open-claw.org/docs)
- **GitHub Repository**: [github.com/openclaw/openclaw](https://github.com/openclaw/openclaw)
- **Community Discord**: [discord.gg/openclaw](https://discord.gg/openclaw)

Ready to get started? [Order your OpenClaw VPS →](https://maenda.media/configurator/vps/template/openclaw-template)

Question 5

Using OpenClaw — User Guide

Accepted Answer

# Using OpenClaw — User Guide

This guide shows you how to get the most out of OpenClaw. From daily use to advanced configuration.

---

## The Control UI

OpenClaw has a web-based dashboard for managing your assistant:

![OpenClaw Control UI — web-based management dashboard](/images/vps-apps/openclaw-template/control-ui.png)

### Accessing the Control UI

The Control UI is available at:

```
https://your-openclaw-domain.com
— or —
http://your-server-ip:3000
```

### Dashboard Overview

The dashboard shows:

| Section | Description |
|---------|-------------|
| **Status** | Online/offline status of all services |
| **Conversations** | Overview of recent conversations per platform |
| **Skills** | Active capabilities and their status |
| **System** | CPU, memory, and storage usage |
| **Logs** | Recent activity and error messages |

---

## Connecting Messaging Platforms

OpenClaw supports multiple messaging platforms simultaneously.

### Telegram

Telegram is the easiest to configure and is recommended for beginners.

**Step 1: Create a bot**
1. Open Telegram and search for **@BotFather**
2. Send the command `/newbot`
3. Choose a name for your bot (e.g., *"My AI Assistant"*)
4. Choose a username (must end with `bot`, e.g., *"my_ai_bot"*)
5. You'll receive a **bot token** — keep it safe!

**Step 2: Configure the token**
```bash
openclaw config set telegram.token "your-bot-token"
openclaw restart
```

**Step 3: Test**
1. Find your bot in Telegram
2. Send `/start`
3. Start chatting!

![OpenClaw Telegram chat — conversation with your AI assistant](/images/vps-apps/openclaw-template/telegram-chat.png)

**Useful Telegram commands:**

| Command | Description |
|---------|-------------|
| `/start` | Start a new conversation |
| `/clear` | Clear conversation history |
| `/model` | Switch AI model |
| `/skills` | View active capabilities |
| `/help` | Show all commands |

### WhatsApp

For WhatsApp, you need a **WhatsApp Business API** account:

1. Go to [business.facebook.com](https://business.facebook.com)
2. Create a Meta Business account (or log in)
3. Navigate to **WhatsApp** → **Getting Started**
4. Create a WhatsApp Business app
5. Note your **Phone Number ID** and **Permanent Access Token**

```bash
openclaw config set whatsapp.phone_id "your-phone-number-id"
openclaw config set whatsapp.token "your-access-token"
openclaw restart
```

### Discord

1. Go to [discord.com/developers](https://discord.com/developers/applications)
2. Click **"New Application"**
3. Go to **Bot** → **"Add Bot"**
4. Copy the bot token
5. Go to **OAuth2** → **URL Generator**
6. Select scopes: `bot`, `applications.commands`
7. Select permissions: `Send Messages`, `Read Message History`

```bash
openclaw config set discord.token "your-bot-token"
openclaw restart
```

### Slack

1. Go to [api.slack.com/apps](https://api.slack.com/apps)
2. Click **"Create New App"** → **"From scratch"**
3. Go to **OAuth & Permissions** → add scopes:
   - `chat:write`, `im:history`, `im:read`, `im:write`
4. Install the app in your workspace
5. Copy the **Bot User OAuth Token**

```bash
openclaw config set slack.token "xoxb-your-token"
openclaw restart
```

---

## Configuring Skills

Skills are modular capabilities that give your assistant extra powers.

![OpenClaw skills configuration — managing modular capabilities](/images/vps-apps/openclaw-template/skills-config.png)

### Available Skills

| Skill | Description | RAM Required |
|-------|-------------|-------------|
| **Web Browsing** | Visit websites, retrieve information | +1 GB |
| **File Management** | Read, write, analyze files | Minimal |
| **Command Execution** | Execute shell commands | Minimal |
| **Image Generation** | Generate images (DALL-E) | Minimal |
| **Code Execution** | Run Python/JS in sandbox | +512 MB |
| **Calendar** | Google/Outlook calendar integration | Minimal |
| **Email** | Read and send emails | Minimal |
| **RAG (Retrieval)** | Search your own documents | +512 MB |

### Managing Skills via CLI

```bash
# List all available skills
openclaw skills list

# Enable a skill
openclaw skills enable web-browsing

# Disable a skill
openclaw skills disable image-generation
```

### Skills Configuration File

```yaml
# /opt/openclaw/config/skills.yml
skills:
  web-browsing:
    enabled: true
    settings:
      max_pages: 10
      timeout: 30
      block_domains:
        - facebook.com

file-management:
    enabled: true
    settings:
      allowed_directories:
        - /opt/openclaw/data/files
      max_file_size: 10MB

command-execution:
    enabled: true
    settings:
      allowed_commands:
        - ls
        - cat
        - grep
      blocked_commands:
        - rm
        - sudo
```

---

## Web Browsing

The web browsing skill enables your assistant to visit websites and retrieve information.

### How It Works

1. Ask your assistant to fetch information from a website
2. OpenClaw opens a headless Chrome browser
3. The page is loaded and text is extracted
4. The assistant analyzes the content and gives you an answer

### Example Conversations

```
You: What are the latest n8n release notes?
Bot: Let me look up the n8n release notes...
     [Visits docs.n8n.io/release-notes]
     The latest version is n8n 1.72.0, released on ...

You: Summarize this article: https://example.com/article
Bot: Let me read the article...
     Summary: ...
```

---

## RAG: Searching Your Documents

With the RAG skill, your assistant can search through your own documents.

### Uploading Documents

```bash
openclaw docs add /path/to/document.pdf
openclaw docs reindex
```

### Supported Formats

PDF, Word (.docx), Text (.txt, .md), HTML, CSV, JSON

---

## Advanced Configuration

### Custom System Prompt

```yaml
# /opt/openclaw/config/config.yml
assistant:
  name: "My AI Assistant"
  language: "en"
  system_prompt: |
    You are a friendly AI assistant.
    Your specialization is technical support.
    Be concise but thorough.
```

### Multiple AI Models

```yaml
models:
  default: "gpt-4o"
  available:
    - name: "gpt-4o"
      provider: "openai"
    - name: "claude-sonnet-4-5-20250929"
      provider: "anthropic"
    - name: "llama3.1:70b"
      provider: "ollama"
```

Switch via chat:
```
/model gpt-4o
/model claude-sonnet-4-5
/model llama3.1
```

---

## Troubleshooting

### Common Issues

**Bot not responding:**
```bash
systemctl status openclaw
journalctl -u openclaw -f --since="5 minutes ago"
systemctl restart openclaw
```

**Web browsing not working:**
```bash
which chromium-browser
free -h
openclaw test web-browsing
```

---

## Privacy & Security

### Data Location

All data is stored in `/opt/openclaw/data/`:

- **Conversations** are stored locally
- **Files** are processed locally
- **No telemetry** — no usage data is collected

### What Is Sent Externally?

Only messages to the **AI provider** (OpenAI/Anthropic) for generating responses. Use a **local model** via Ollama for complete privacy.

### Security Tips

1. **Keep software updated** — Run `openclaw update` regularly
2. **Limit skills** — Only enable skills you need
3. **Firewall** — Keep UFW active
4. **SSH keys** — Use SSH keys instead of passwords
5. **API keys** — Rotate your API keys regularly

---

## More Information

- **OpenClaw Documentation**: [open-claw.org/docs](https://open-claw.org/docs)
- **GitHub Repository**: [github.com/openclaw/openclaw](https://github.com/openclaw/openclaw)
- **Community Discord**: [discord.gg/openclaw](https://discord.gg/openclaw)

Need help? Contact our support team via the chat window at the bottom right or send an email to support@maenda.media.

Uitgebreide Handleidingen

Installing n8n on your VPS — Complete Guide

Stream Monitor: monitoring your audio stream

Installing OpenClaw on Your VPS — Complete Guide

Kennisbank

VPS Applications

Finance

Web Hosting

Security

Streaming & Monitoring

Niet gevonden wat je zocht?