DEV Community

Cover image for Deploying Hermes Agent on Ubuntu 26.04
Vultr profile image Aashish Chaurasiya
Aashish Chaurasiya for Vultr

Posted on Originally published at docs.vultr.com

Deploying Hermes Agent on Ubuntu 26.04

#ai #docker #linux #devops

Hermes Agent is an open-source self-hosted AI agent framework by Nous Research that runs continuously on a server with persistent memory and tool access. It integrates with Telegram, Discord, Slack, and WhatsApp, and supports any OpenAI-compatible LLM provider including Vultr Serverless Inference. This guide deploys Hermes Agent using Docker Compose with Traefik handling automatic HTTPS, and configures an LLM backend. By the end, you'll have a self-hosted AI agent running with a secured web dashboard and verified LLM connectivity.

Install Docker

The official Docker repository gives you the most current Docker Engine builds.

1. Install dependency packages:

$ sudo apt install apt-transport-https ca-certificates curl -y
Enter fullscreen mode Exit fullscreen mode

2. Add Docker's GPG key:

$ sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
Enter fullscreen mode Exit fullscreen mode

3. Register the Docker repository:

$ echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
Enter fullscreen mode Exit fullscreen mode

4. Refresh APT and install Docker:

$ sudo apt update
$ sudo apt install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin -y
Enter fullscreen mode Exit fullscreen mode

5. Add your user to the Docker group:

$ sudo usermod -aG docker $USER
$ newgrp docker
Enter fullscreen mode Exit fullscreen mode

Set Up the Project Directory

1. Create the project directory:

$ mkdir -p ~/hermes/data
$ cd ~/hermes
Enter fullscreen mode Exit fullscreen mode

2. Create the environment file:

$ nano .env
Enter fullscreen mode Exit fullscreen mode 
DOMAIN=hermes.example.com
LETSENCRYPT_EMAIL=admin@example.com
Enter fullscreen mode Exit fullscreen mode

3. Generate dashboard authentication credentials:

$ docker run --rm httpd:2.4-alpine htpasswd -nbB admin 'your_dashboard_password' > .htpasswd
Enter fullscreen mode Exit fullscreen mode

Deploy with Docker Compose

1. Create the Docker Compose file:

$ nano docker-compose.yml
Enter fullscreen mode Exit fullscreen mode 
services:
  traefik:
    image: traefik:v3
    command:
      - --providers.docker=true
      - --entrypoints.web.address=:80
      - --entrypoints.websecure.address=:443
      - --certificatesresolvers.letsencrypt.acme.email=${LETSENCRYPT_EMAIL}
      - --certificatesresolvers.letsencrypt.acme.storage=/data/acme.json
      - --certificatesresolvers.letsencrypt.acme.tlschallenge=true
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock
      - ./data:/data

  hermes:
    image: nousresearch/hermes-agent:latest
    volumes:
      - ./data:/opt/data
    labels:
      - traefik.enable=true
      - traefik.http.routers.hermes.rule=Host(`${DOMAIN}`)
      - traefik.http.routers.hermes.entrypoints=websecure
      - traefik.http.routers.hermes.tls.certresolver=letsencrypt

  dashboard:
    image: nginx:alpine
    volumes:
      - ./.htpasswd:/etc/nginx/conf.d/.htpasswd
    labels:
      - traefik.enable=true
      - traefik.http.routers.dashboard.rule=Host(`${DOMAIN}`) && PathPrefix(`/dashboard`)
      - traefik.http.middlewares.dashboard-auth.basicauth.usersfile=/etc/nginx/conf.d/.htpasswd
      - traefik.http.routers.dashboard.middlewares=dashboard-auth
Enter fullscreen mode Exit fullscreen mode

2. Open the firewall:

$ sudo ufw allow 80/tcp
$ sudo ufw allow 443/tcp
Enter fullscreen mode Exit fullscreen mode

3. Start the services:

$ docker compose up -d
Enter fullscreen mode Exit fullscreen mode

4. Verify the services are running:

$ docker compose ps
Enter fullscreen mode Exit fullscreen mode

Configure the LLM

1. Run the model configuration command:

$ docker run -it --rm \
    -v ~/hermes/data:/opt/data \
    nousresearch/hermes-agent:latest model
Enter fullscreen mode Exit fullscreen mode

2. Follow the prompts to select a provider and model.

The configuration supports OpenAI, Anthropic, OpenRouter, and any OpenAI-compatible endpoint. To use Vultr Serverless Inference, select the OpenAI-compatible option and provide your Vultr API key and the inference endpoint URL.

Verify the Deployment

1. Check the service logs:

$ docker compose logs hermes
Enter fullscreen mode Exit fullscreen mode

2. Open the dashboard in a browser:

Visit https://hermes.example.com and log in with the credentials from the .htpasswd file.

3. Test LLM connectivity:

Send a simple query through the dashboard. A response from the model confirms the LLM connection is working.

Next Steps

Hermes Agent is running and connected to a language model. From here you can:

  • Connect messaging integrations for Telegram, Discord, Slack, or WhatsApp through the dashboard
  • Enable persistent memory so the agent retains context across sessions
  • Switch to Vultr Serverless Inference for a cost-effective, OpenAI-compatible LLM backend

For the full guide with additional tips, visit the original article on Vultr Docs.

Top comments (0)