Running your own AI agent used to be complicated. Expensive cloud setups. 

Complex DevOps configs. Your data is handed off to platforms you don’t control.

OpenClaw changes that. It’s an open-source AI agent framework. You deploy it on your own server. 

It lives there, always online, fully autonomous.

It connects via WhatsApp or Telegram. It books appointments. Clears your inbox. 

Monitors GitHub repos. Runs multi-step workflows while you sleep.

As of April 2026, OpenClaw has crossed 347,000 GitHub stars. It’s the most-starred project in the platform’s history. 

That kind of traction doesn’t happen by accident.

This guide shows you how to self host AI agents with openclaw vps on a Truehost VPS. From picking a plan to having a live agent answering your messages. 

Let’s get started.

Step 1: Choose Your Plan

Go to the Truehost Openclaw page.

You’ll find two plan categories. The right choice depends on how technical you are and where your users are.

Managed VPS (Europe/US)

Truehost handles the server, OS patches, and OpenClaw runtime. You get a fully configured environment. 

No command line needed. This is the right pick for non-technical users, solo founders, and teams who’d rather focus on using the agent than maintaining it.

Unmanaged Kenya VPS

Full root SSH access. You control the stack entirely. Built for developers who want to fine-tune configurations or run custom scripts. 

Also, the best choice if you need the lowest latency to East Africa. 

That is important if your users are in Kenya, Uganda, Tanzania, or anywhere in the region.

Plan Overview

Plan	Price	Specs	Best For
Cloud Starter	KES 1,120/mo	1 vCPU, 2 GB RAM, 50 GB SSD	Personal use, testing
Cloud Pro	KES 2,240/mo	2 vCPU, 4 GB RAM, 100 GB SSD	Active agents and workflows
Cloud Business	KES 5,040/mo	4 vCPU, 8 GB RAM, 200 GB SSD	Multi-agent, heavy workloads
Kenya Cloud VPS 1	KES 1,400/mo	Nairobi datacenter, full root	Lowest latency to Kenya
Kenya Cloud VPS 2	KES 2,800/mo	1 vCPU, 2 GB RAM	Mid-load agent, East Africa
Kenya Cloud VPS 3	KES 5,600/mo	2 vCPU, 4 GB RAM	High-traffic agents and APIs
Cloud VPS 4 (Limited)	KES 1,849/mo	4 vCPU, 8 GB RAM	Best price-to-power ratio (EU/US)

How to decide: Testing your first agent? Start with Cloud Starter. 

Running active automations like email triage or Telegram responses? Move to Cloud Pro. Running a team or multi-agent setup? 

Cloud Business or Kenya Cloud VPS 3 is the better fit.

All plans include a 30-day satisfaction guarantee.

Check our guide on Openclaw OpenAI integration

Step 2: Pick Your Add-Ons and Server Location

Europe/US datacenters (managed) give you hands-off reliability. Best if your APIs are mostly hosted in those regions.

Nairobi datacenter (unmanaged) delivers sub-10ms latency to East Africa. If your agent serves Kenyan users responding to WhatsApp messages, handling M-PESA callbacks, or pulling data from local APIs, this is the one to pick.

Domain Registration at Checkout

Register a domain during checkout. Truehost auto-connects it to your OpenClaw install. Free SSL is included. No extra configuration needed.

Available options:

• .co.ke: KES 999: Kenya’s #1 TLD, great for local credibility
• .com: KES 999: Standard global option
• .ai: KES 22,520: Purpose-built for AI projects
• .africa: KES 1,800: Solid for Pan-African reach

Free SSL is included on all plans. Daily snapshots come with Cloud Starter and above on managed plans. Automated backups and dedicated IP are available as optional add-ons.

Step 3: Complete Account Setup and Payment

Creating an account with Truehost takes under two minutes. If you already have one, just log in.

Review your order summary before checking out. Confirm the plan, domain, and any add-ons are correct.

Supported payment methods: M-PESA, credit/debit card, and bank transfer. Kenya-based users can pay directly via M-PESA at checkout.

What happens immediately after payment:

1. Order confirmation is sent to your email
2. VPS provisioning begins automatically
3. Truehost installs the OpenClaw runtime, plugin registry, and SSL fully configured, no command-line work needed on managed plans

Step 4: Save Your Gateway Token

Once provisioning is complete, you’ll receive your OpenClaw gateway token. Check your order confirmation or dashboard.

This token authenticates your OpenClaw instance. Treat it like a password.

How to store it securely:

• Use a password manager like Bitwarden or 1Password
• Or store it in an encrypted notes app
• Never save it in a plain text file. Never share it in chat.

This is also the stage to connect your WhatsApp number or preferred messaging platform if you didn’t set it up during checkout.

Lost your token? Log in to your Truehost dashboard. Navigate to your OpenClaw service. Retrieve or regenerate it from the settings panel.

Step 5: Deploy and Wait

On managed plans, Truehost handles everything automatically:

1. Provisions your Cloud VPS
2. Installs Node runtime and OpenClaw core
3. Wires the LLM gateway, plugin registry, and SSL
4. Connects your domain (e.g., agent.yoursite.co.ke)

Average deploy time: under 60 seconds.

On managed plans, you land directly in your live OpenClaw dashboard when it’s done.

Step 6: Open Your Dashboard

Access your OpenClaw dashboard via your auto-connected domain. It’ll look something like https://agent.yoursite.co.ke.

On unmanaged plans, access the dashboard via SSH tunnel using your root credentials.

Dashboard layout overview:

• Active agent status running or idle?
• Plugin registry, Skills installed and available
• LLM connection panel, which model is active
• Resource usage vCPU, RAM, and SSD in real time

Security note: Don’t expose the Control UI to a public IP without authentication. On unmanaged plans, always access the dashboard through an SSH tunnel.

Step 7: Set Up Your Admin Account and Verify Your Instance

The first account you create becomes the administrator account.

Set a strong, unique password. Don’t reuse one from another service.

Confirm your instance is running correctly:

• Check that the OpenClaw runtime shows as active
• Verify the dashboard loads without errors
• Send a quick test message to confirm the agent is listening

Key configuration areas to explore:

• Plugin/Skills settings show what capabilities the agent has right now
• Active messaging channels that platforms are connected to
• Performance tuning concurrency limits and resource allocation
• Notification preferences where alerts and errors go

Learn more about Openclaw use cases

Step 8: Connect an AI Model

This is where your agent gets its brain.

OpenClaw is fully provider-agnostic. Switch models any time no redeployment needed.

Supported providers:

• OpenAI (GPT-4o and later)
• Anthropic (Claude Sonnet, Claude Opus)
• Google (Gemini)
• Mistral
• Groq
• Local models via Ollama on the same VPS

Open the LLM connection panel in the dashboard. Enter your API key. Select your model. Hit save.

Send a test message through your connected channel. If the model responds, you’re live.

Tips on managing costs:

• OpenAI and Anthropic charge per token set usage limits in your provider dashboard
• Groq offers fast inference at lower cost, good for high-volume agents
• Local models via Ollama have no API fees but they need more RAM on your VPS

Step 9: Connect Your Channels and APIs

Channels are the messaging platforms your agent listens and responds on. Think of them as the front door to your agent.

Start With Telegram

Telegram is the easiest first channel. No port forwarding needed.

Get a Bot Token from @BotFather on Telegram. Paste it into your OpenClaw channel settings. Done.

Send your bot a message. Your agent should respond within seconds.

Connect WhatsApp

Didn’t link WhatsApp during checkout? Do it now from the channel settings panel. Follow the on-screen pairing steps.

Add Slack and Other Platforms

Slack, Discord, Signal, iMessage, and Microsoft Teams are all supported. Each has its own setup flow in the dashboard. Follow the platform-specific instructions for each one.

Set Up External API Connections

Need deeper automation? Use the API connections panel. Connect your agent to webhooks, external services, Notion, GitHub, or your own internal APIs.

Always test each channel after connecting it. Send a message. Confirm the agent receives it and responds correctly before moving on.

Step 10: Install Skills As You Need Them

Skills are modular add-ons. They expand what your agent can do. They’re the difference between a chatbot that answers questions and an agent that actually gets work done.

Common starting Skills:

• Web research (browser automation and scraping)
• Email triage (Gmail read/draft/send)
• Scheduling (cron-based recurring tasks)
• GitHub automation (monitor repos, summarize issues)
• Multi-channel support bots

Where to find Skills: ClawHub and community repositories. As of Q1 2026, ClawHub had over 13,000 available skills from Cron Scheduler to Gmail Pub/Sub to browser automation.

How to install a Skill from the dashboard:

1. Navigate to the Plugin Registry
2. Search by name or category
3. Click Install and follow any permission prompts

Important: Always review a Skill’s code before enabling it on a production server. Community skill quality varies.

Check what file system permissions each Skill needs. Remove anything your agent doesn’t actually require.

Start with one or two Skills. Get comfortable. Then expand.

Troubleshooting Common OpenClaw Self-Hosting Issues

Things will occasionally break. Here’s how to fix the most common problems fast.

OpenClaw Won’t Start

Check the container logs first:

docker compose logs openclaw

Also verify your .env file exists and has valid API keys:

cat .env

A missing or misconfigured .env is the most common cause of startup failures.

Telegram Bot Not Responding

• Confirm the bot token is correctly set in .env
• Verify your Telegram user ID is listed in ALLOWED_TELEGRAM_USERS
• Check network connectivity from the container to Telegram’s API

AI Model Not Responding

• Verify your API keys are valid and have sufficient credits
• Confirm the selected model is available with your provider
• Restart the containers:

docker compose restart

Ollama Running Out of Memory

Large local models can exhaust VPS resources quickly.

• Switch to a smaller model like phi3:mini
• Upgrade to a plan with more RAM
• Limit concurrent inference:

OLLAMA_NUM_PARALLEL=1

OpenClaw Is Slow

• Monitor CPU, RAM, and disk with htop
• Reduce the number of concurrently running agents
• Use lighter models if resources are tight
• Upgrade your plan. Truehost supports live upgrades with no downtime

Container Deployment Issues After Updates

docker compose down
docker compose pull
docker compose up -d

Then verify all services are running:

docker compose ps

Read also: How to Set Up OpenClaw on a VPS

Self Host AI Agents with Openclaw VPS FAQs

Can I use OpenClaw to build an app?

Yes. OpenClaw supports building AI-powered applications through its Skills system and API integrations. It can be used to create Slack bots, customer automation tools, workflow systems, and other custom AI-driven applications.

What are people using OpenClaw for?

Common use cases include inbox management, GitHub issue monitoring, Telegram briefings, web research automation, project coordination, and customer support bots that can escalate conversations to human agents when necessary.

What is the cost of OpenClaw hosting on Truehost?

Hosting plans start at KES 1,120/month for entry-level VPS resources and go up to KES 5,600/month for higher-performance Nairobi-hosted VPS plans. All plans include a 30-day satisfaction guarantee.

What is the best Linux distro for OpenClaw?

Ubuntu 24.04 LTS is the recommended distribution due to its stability, broad support, and compatibility with Node.js 22+. Managed Truehost plans come pre-configured with it.

How do I build an AI agent using OpenClaw?

Install OpenClaw on a VPS, connect an LLM provider, integrate your messaging channels, and add the Skills relevant to your use case. For more advanced automation, connect OpenClaw to your existing tools through its API integrations.

What to Expect Once You’re Live

Your agent now runs 24/7 without keeping your laptop on. Start simple, let it handle scheduling, email triage, or web research through chat commands. Over time, expand to internal team bots, GitHub automation, and complex multi-channel workflows.

We at Truehost provide 24/7 human support (average first response under 4 minutes) via chat, ticket, or phone for both managed and unmanaged plans. Monitor resource usage in the dashboard and upgrade live as your agent grows, with no downtime.

Keep OpenClaw updated. It’s a fast-moving project with regular improvements.