Bluehost Self-Managed VPS: Reimage Your Server for Hermes Agent + Open WebUI Installation

Learn how to reimage your Self-Managed VPS and install Hermes Agent + Open WebUI using the one-click installer. This guide covers how to start the process, select the application, and confirm your server update.

Reimage Your Server for Hermes Agent + Open WebUI Installation

Important:

You can install only one application using the one-click installer.
To change or delete your application, follow the guide: Bluehost Self-Managed VPS: How to Change and Delete an Application. Create a backup of your existing applications or templates.
If you want to keep your current template, install the new application manually using SSH. The system will automatically apply the recommended OS for Hermes Agent + Open WebUI.

Changing the server image will permanently erase all data and settings on this VPS. This action cannot be undone.

Log in to your Bluehost Portal.
In the left-hand menu, click Hosting.

Click the Manage button on the Self-Managed VPS package.
Click the Reimage button.
Select the Applications tab.
From the list, locate Hermes Agent + Open WebUI and click Select.
To confirm, type "reimage" and then click Proceed to start the process.
Wait a few minutes while the installation completes.
Once completed, you will see Hermes Agent + Open WebUI listed in the Server Image section.

Deployment and Configuration Guide

Nginx, Open WebUI, and Hermes Agent connect automatically out of the box, eliminating the need for manual component configuration.

Here is your step-by-step walkthrough to get everything configured and running.

After installation completes:

Connect to your VPS via SSH.

Use your VPS IP and credentials with an SSH client, follow the prompts, and enter your root password when asked:

BH AM -hosting software root password and ip

ssh root@your_server_ip

Example Output:

   
  Welcome to Ubuntu 24.04.4 LTS (GNU/Linux 6.8.0-124-generic x86_64)
================================================================================

  Hermes Agent + Open WebUI

  The UFW firewall is enabled.
  Open ports: 22 (SSH), 80 (HTTP), 443 (HTTPS).

  The first thing to do is to configure an LLM model in Hermes:
    HOME=/var/lib/hermes-agent hermes model
    systemctl restart hermes-agent

  To manually configure a model using standard environment keys
  (GITHUB_TOKEN, OPENROUTER_API_KEY, ANTHROPIC_API_KEY, etc):
    nano /var/lib/hermes-agent/.hermes/.env
    systemctl restart hermes-agent

  After that is done, you can access (in a browser):
    Open WebUI:   https://12.2.2.123/

  Credentials:
    cat /root/.app_passwords

  Service logs:
    journalctl -u hermes-agent -f
    journalctl -u open-webui   -f

For more details, please see the README at /root/README.md

Step 1: Configure Your LLM Backend

Before you do anything in the browser, Hermes Agent needs an API key to talk to an actual LLM backend.

Open the configuration file using the nano text editor:

nano /var/lib/hermes-agent/.hermes/.env

Example Output:

GNU nano 7.2            /var/lib/hermes-agent/.hermes/.env                  

# Hermes Agent Configuration Environment Variables
NODE_ENV=production
PORT=8080

# API and Network Settings
HERMES_API_URL=https://api.hermes-service.internal
HERMES_AGENT_ID=agent_usr_12x12abc
HERMES_AUTH_TOKEN=ghp_SecReTToKeN12345678abc

# Logging and Performance
LOG_LEVEL=info
MAX_CONCURRENT_TASKS=5
TIMEOUT_MS=30000

# Database / Cache Connection (if local)
REDIS_URL=redis://localhost:6379/0

^G Help       ^O Write Out  ^W Where Is   ^K Cut        ^J Justify    ^C Cur Pos
^X Exit       ^R Read File  ^\ Replace    ^U Paste      ^T To Spell   ^_ Go To Line

Look for the API lines and add your provider keys.

If using OpenRouter:

Example Output:

# OpenRouter
OPENAI_API_KEY=sk-or-...
OPENAI_API_BASE=https://openrouter.ai/api/v1

If using Anthropic:

Example Output:

# Anthropic
ANTHROPIC_API_KEY=sk-ant-...

Restart the service to apply your changes:
```
systemctl restart hermes-agent
```

Step 2: Access the Web UI and Create an Account

To ensure a smooth login, please follow the steps below:

Log In via Your Browser:
Open your preferred web browser and navigate to your server's IP .
```
http://your-server-ip/
```
Sign Up:
Create your account immediately. The first user to register automatically becomes the global Admin.
Verify Settings:
Go to Admin -> Settings -> Connections in Open WebUI to ensure the pre-configured hermes-agent model is active and communicating.
Start Chatting:
Open a new chat, select hermes-agent from the top model dropdown menu, and test a prompt.

Step 3: Run Validation Tests

To make sure Open WebUI, Hermes Agent, and your backend connection are all talking to each other perfectly, run the built-in test suite:

prove /root/app_test/main.t

Example Output:


root@server-123456:~# prove /root/app_test/main.t
/root/app_test/main.t .. ok   
All tests successful.
Files=1, Tests=5,  2.34 wallclock secs ( 0.03 usr  0.01 sys +  0.42 cusr  0.12 csys = 0.58 CPU)
Result: PASS

Additional Information and Example Documentation Output

You can run cat /root/README.md to see more information and useful commands:

Example Output:


root@server-123456:~# cat /root/README.md
# Hermes Agent + Open WebUI

## Description

Hermes Agent is Nous Research's autonomous AI agent that exposes an
OpenAI-compatible API. It connects to any LLM backend you choose OpenRouter,
Together AI, Anthropic, a local Ollama instance, or any other provider and
handles tool use, reasoning, and multi-step tasks on your behalf.

Open WebUI is a polished, self-hosted chat interface that lets you interact
with AI models through a browser, with no data leaving your server.

This image combines both into a ready-to-use AI assistant stack: Open WebUI
provides the chat frontend, Hermes Agent powers the intelligence layer behind
it, and nginx handles HTTPS termination so you can reach everything securely
through a single URL. Connect your preferred LLM provider, create an account,
and start chatting no additional setup required.

Architecture:

  User Browser
      |
      v :80 / :443
    nginx  (reverse proxy + TLS termination)
      |
      v :8080 (internal)
    Open WebUI  (chat frontend)
      |
      v :8642 (internal, OpenAI-compatible API)
    Hermes Agent  (autonomous AI agent)
      |
      v
    LLM Backend  (configured by you: OpenRouter, Together AI, Ollama, etc.)


## Services

Service       | Ports           | Purpose
--------------|-----------------|--------
nginx         | 80, 443         | Reverse proxy with TLS termination (self-signed cert)
Open WebUI    | 8080 (internal) | Web chat frontend
Hermes Agent  | 8642 (internal) | Autonomous AI agent with OpenAI-compatible API
OpenSSH       | 22              | SSH

Ports are protected using ufw (22, 80, 443 open; 8080 and 8642 internal only).


## How-to-use

After first boot, open a browser and navigate to:

`http://your-server-ip/`

1. Create your **admin account** on the sign-up page (first user becomes admin)
2. The **hermes-agent** model is pre-configured under Admin -> Settings -> Connections
3. Select **hermes-agent** from the model dropdown in a new chat

Read generated credentials:

```
cat /root/.app_passwords      # HERMES_API_KEY and WEBUI_SECRET_KEY
cat /root/.app_info           # full connection info
```

Configure the LLM backend (edit then restart):

```
nano /var/lib/hermes-agent/.hermes/.env
systemctl restart hermes-agent
```

Example LLM provider entries:

```
# OpenRouter
OPENAI_API_KEY=sk-or-...
OPENAI_API_BASE=https://openrouter.ai/api/v1

# Anthropic
ANTHROPIC_API_KEY=sk-ant-...
```

Service management:

```
systemctl status hermes-agent
systemctl status open-webui
systemctl status nginx

journalctl -u hermes-agent -f
journalctl -u open-webui   -f
tail -f /var/log/hermes-agent/gateway.log
tail -f /var/log/open-webui/webui.log
```

Run validation tests:

```
prove /root/app_test/main.t
```

Replace the self-signed certificate:

```
cp your-cert.crt /etc/ssl/hermes-openwebui/server.crt
cp your-key.key  /etc/ssl/hermes-openwebui/server.key
chmod 0644 /etc/ssl/hermes-openwebui/server.crt
chmod 0640 /etc/ssl/hermes-openwebui/server.key
systemctl reload nginx
```


## Links

Documentation: [https://hermes-agent.nousresearch.com/docs/](https://hermes-agent.nousresearch.com/docs/)
Manage: [http://{serve

Summary

By following these steps, you can reimage your Self-Managed VPS to install Hermes Agent + Open WebUI using the one-click installer. Remember, reimaging will erase all existing data, so ensure you have backups before proceeding. Once complete, Hermes Agent + Open WebUI will be available on your server for use.

Did you find this article helpful?