# How to Set Up OpenClaw with VidClaw: Complete Guide

In this guide, you'll set up an **OpenClaw AI agent** on your own VPS and connect it to **VidClaw** — a self-hosted dashboard for managing tasks, tracking usage, and shaping your agent's behavior. By the end, you'll have a fully working AI agent with a visual command center you can access from anywhere.

## What is OpenClaw?

[OpenClaw](https://github.com/openclaw/openclaw) is an open-source framework for running autonomous AI agents. It gives your agent a workspace on your server where it can execute tasks, write code, manage files, and interact with APIs. Think of it as the engine that powers your AI agent — it handles scheduling, memory, tool use, and model communication.

OpenClaw runs headlessly on your server. You configure it, point it at a model provider (like Anthropic), and it works autonomously on tasks you assign.

## What is VidClaw?

[VidClaw](/content/features/index.html) is a self-hosted dashboard that sits on top of OpenClaw. It gives you a visual interface to manage everything your agent does:

- **Kanban board** — queue and prioritize tasks with drag-and-drop
- **Usage tracking** — real-time token counts and cost estimates
- **Skills manager** — enable, disable, or create agent skills
- **Soul editor** — shape your agent's persona and instructions
- **Activity calendar** — see what your agent worked on each day
- **File browser** — browse your agent's workspace files

VidClaw binds to `localhost` only — you access it securely through an SSH tunnel. No accounts, no cloud, no tracking.

## Prerequisites

Before you start, make sure you have:

- **A VPS** — any Linux server (Ubuntu 22.04+ recommended) with at least 1 GB RAM
- **SSH access** — you should be able to SSH into your server as root or a sudo user
- **An Anthropic API key** — sign up at [console.anthropic.com](https://console.anthropic.com/) and create an API key
- **Basic terminal skills** — you'll be running commands on your server

## Setup Steps

### Prepare your VPS

SSH into your server and make sure everything is up to date:

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

# Update packages
apt update && apt upgrade -y

# Install required dependencies
apt install -y git curl
```

You'll also need **Node.js 18+**. If it's not installed:

```bash
curl -fsSL https://deb.nodesource.com/setup_20.x | bash -
apt install -y nodejs
```

### Install OpenClaw

Clone the OpenClaw repository and run the installer:

```bash
git clone https://github.com/openclaw/openclaw.git ~/.openclaw
cd ~/.openclaw
./install.sh
```

During installation, you'll be prompted for your **Anthropic API key**. Paste it when asked.

Verify the installation:

```bash
openclaw --version
```

**Tip:** OpenClaw stores its configuration at `~/.openclaw/openclaw.json`. You can edit this file directly, or use VidClaw's Settings panel later.

### Configure your agent

Set up your agent's workspace and persona. OpenClaw uses a workspace directory where your agent stores its files, memory, and task data:

```bash
mkdir -p ~/.openclaw/workspace
```

Edit the OpenClaw config to set your preferred model and workspace path:

```json
# ~/.openclaw/openclaw.json
{
  "model": "claude-sonnet-4-20250514",
  "workspace": "~/.openclaw/workspace",
  "api_key": "sk-ant..."
}
```

**Note:** You can switch models at any time from VidClaw's navbar — no need to edit this file manually once VidClaw is running.

### Install VidClaw

The fastest way to install VidClaw is the one-liner:

```bash
curl -fsSL vidclaw.com/install.sh | bash
```

This installs dependencies, builds the frontend, and sets up a systemd service automatically.

Alternatively, install manually:

```bash
cd ~/.openclaw/workspace
git clone https://github.com/madrzak/vidclaw.git dashboard
cd dashboard
./setup.sh
```

The setup script handles everything: npm dependencies, Vite build, and systemd service registration.

### Access the dashboard

VidClaw binds to `localhost:3333` for security. To access it from your local machine, create an SSH tunnel:

```bash
ssh -L 3333:localhost:3333 root@your-server-ip
```

Now open [http://localhost:3333](http://localhost:3333/) in your browser. You should see the VidClaw dashboard with the Kanban board ready to go.

**Tip:** Add an alias to your shell config for quick access:

```bash
alias vc="ssh -L 3333:localhost:3333 root@your-server-ip"
```

### Create your first task

With the dashboard open, it's time to give your agent something to do:

1. Click the **\+ Add** button at the top of the **Todo** column
2. Enter a task title — for example, "Write a README for the project"
3. Set a priority (P1 is highest) and optionally attach a skill
4. Click **Create** — your task appears on the board

Your OpenClaw agent picks up tasks from the Todo column automatically, ordered by priority. As it works, the card moves to **In Progress**, and when it's done, it lands in **Done** with a timestamp.

You can also use the **quick-add bar** at the top of the Kanban board. Type your task, use `@skill` to attach a skill, and hit Enter.

## Next Steps

You now have a fully working OpenClaw agent with VidClaw as your command center. Here are some things to explore next:

- **[Explore all features](/content/features/index.html)** — usage tracking, skills manager, soul editor, and more
- **[Read the install guide](/content/install/index.html)** — configuration options, updating, and uninstalling
- **Customize your agent's soul** — open the Soul Editor panel and pick a starter template
- **Set up recurring tasks** — use the schedule feature to automate repetitive work
- **[Star the repo](https://github.com/madrzak/vidclaw)** — if VidClaw is useful, a star helps others find it

Ready to take control of your AI agent?

VidClaw is free, open-source, and takes 60 seconds to install.