For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

Hermes Agent, the self-improving AI agent built by Nous Research, runs on your machine or server runs and lets you chat with an AI assistant through the terminal, a TUI, or messaging platforms like Telegram, Discord, Slack, WhatsApp, Signal, and email. It is designed for long-running personal automation: it can remember context across sessions, use tools, create and improve skills, run scheduled jobs, and work from a cloud VM instead of being tied to your laptop.

On this Droplet, Hermes is installed for the dedicated hermes user. Start with:

hermes

To configure or change your model provider:

hermes setup
hermes model

For DigitalOcean Serverless Inference, use a model access key and the preconfigured endpoint https://inference.do-ai.run/v1. The first-login wizard loads the current chat-model catalog from that API. If you do not choose a model, it uses the first chat-model id in alphabetical order.

Useful commands:

hermes doctor          # diagnose setup issues
hermes update          # update Hermes
hermes gateway setup   # configure messaging platforms
hermes gateway start   # start the messaging gateway
hermes tools           # configure available tools

Important paths:

/home/hermes/.hermes/config.yaml
/home/hermes/.hermes/.env
/home/hermes/workspace
/opt/hermes/

Tips:

• Run hermes doctor after setup if anything feels off.
• Use hermes model to switch providers or models later.
• Use hermes gateway setup only if you want messaging integrations.
• Keep API keys in /home/hermes/.hermes/.env, not in shell history.

Links:

• Docs: https://hermes-agent.nousresearch.com/docs/
• GitHub: https://github.com/NousResearch/hermes-agent
• DigitalOcean Serverless Inference: https://cloud.digitalocean.com/model-studio/serverless-inference

Software Included

Creating an App using the Control Panel

Click the Deploy to DigitalOcean button to create a Droplet based on this 1-Click App. If you aren’t logged in, this link will prompt you to log in with your DigitalOcean account.

Creating an App using the API

In addition to creating a Droplet from the Hermes Agent 1-Click App using the control panel, you can also use the DigitalOcean API. As an example, to create a 4GB Hermes Agent Droplet in the SFO2 region, you can use the following curl command. You need to either save your API access token to an environment variable or substitute it in the command below.

curl -X POST -H 'Content-Type: application/json' \
         -H 'Authorization: Bearer '$TOKEN'' -d \
        '{"name":"choose_a_name","region":"sfo2","size":"s-2vcpu-4gb","image":"hermesagent"}' \
        "https://api.digitalocean.com/v2/droplets"

Getting Started After Deploying Hermes Agent

Getting Started

Follow these steps to get your Hermes Agent instance running as a Droplet on DigitalOcean.

1. Deploy the Droplet

• Deploy the Hermes Agent 1-Click App from the DigitalOcean Marketplace.
• Wait for the Droplet to finish provisioning.
• The DigitalOcean dashboard may say “ready” before SSH is available. If SSH fails, wait about 60 seconds and retry.

2. Connect via SSH

ssh root@your-droplet-ip

On first login, you will see the Hermes welcome message and the setup flow may run automatically.

3. Configure Hermes

Hermes is installed for the dedicated hermes user. The first-login wizard asks you to choose:

1. DigitalOcean Serverless Inference
2. Hermes setup (hermes setup)

For Serverless Inference, create a model access key at https://cloud.digitalocean.com/model-studio/manage-keys, then pick a model from the live catalog.

4. Start Chatting

hermes

This starts an interactive Hermes Agent session in your terminal.

5. Verify Installation

Check Hermes health:

hermes doctor

Check template status:

/opt/hermes/status-hermes.sh

Check the configured model or provider:

hermes model

6. Configure DigitalOcean Serverless Inference Manually

Edit /etc/environment or /opt/hermes/hermes.env and set:

MODEL_ACCESS_KEY=your_model_access_key
INFERENCE_MODEL=minimax-m2.5

INFERENCE_MODEL is optional. Leave it empty to use the first chat-model id in alphabetical order. minimax-m2.5 is an example model id, not a model baked into the image.

Apply the config:

sudo /opt/hermes/apply-inference-from-env.sh

Hermes writes provider secrets to /home/hermes/.hermes/.env and model config to /home/hermes/.hermes/config.yaml.

7. Configure Messaging Channels

Hermes can connect to messaging platforms such as Telegram, Discord, Slack, WhatsApp, Signal, and email.

hermes gateway setup
hermes gateway start
hermes gateway status

Managing Hermes

Hermes is an interactive CLI. The messaging gateway is the long-running piece.