Hermes Ollama Setup For Beginners (Step-By-Step)

How to setup Hermes with Ollama — written for someone who's never installed an AI agent before.

If you've never set up an AI agent before, the technical jargon online is brutal.

GitHub repos.

Terminal commands.

Config files.

It's enough to put anyone off.

Good news — you don't need any of that.

This post walks you through setting up Hermes + Ollama the easy way, in plain language, step by step.

What You're Building

By the end of this post, you'll have:

Ollama running on your computer (a free local AI model engine).
Hermes installed (a free AI agent).
A free local AI agent that runs offline, costs nothing, and can chat with you.

Total time: under 30 minutes.

Total cost: £0.

What You'll Need

Three things.

1. A computer. Mac, Windows, or Linux all work.

2. About 15GB free disk space. For Ollama and one model.

3. Internet connection for the install (after that, you can run offline).

That's it.

No GitHub knowledge.

No terminal commands.

Two simple installs.

Step 1 — Install Ollama

Go to ollama.com.

Click the big download button for your operating system.

When the file finishes downloading, double-click and follow the installer.

Same as installing any other app.

Once installed, Ollama runs quietly in the background.

You can verify it's working by opening your browser and going to http://localhost:11434 — you should see "Ollama is running".

If you see that, Ollama is set up. Move on.

Step 2 — Pick A Model

Models are what give Ollama its smarts.

There are dozens.

For beginners, I'd pick Gemma 4.

Why?

Small (~7GB).
Works on most laptops.
Smart enough for everyday tasks.
Fast install.

Other beginner-friendly options:

DeepSeek (better for agent tasks, slightly bigger).
Qwen 3.6 (general-purpose).

Don't overthink it.

Gemma 4 first.

You can always swap later.

Step 3 — Install The Model

This is the only "terminal" step.

Open Terminal (Mac) or Command Prompt (Windows).

Don't panic — you only type one line.

Type this:

ollama run gemma4

Hit Enter.

The model will download.

Could take 5–15 minutes depending on your internet speed.

When it's done, you can close the terminal.

The model is now installed and ready.

Step 4 — Install Hermes

Hermes is the AI agent that uses your model.

The official install instructions are on the Hermes GitHub page.

Two ways to do this.

The technical way

Run the install command from the GitHub README in your terminal.

If terminal commands intimidate you, skip to the easier way.

The easier way (my recommendation for beginners)

Use Claude Code or Codex to do the install for you.

Download Claude Code or Codex.
Open it.
Copy the Hermes install command from GitHub.
Paste it into Claude Code.
Type "set this up for me".

Claude Code will install Hermes automatically.

I cover this exact trick in Free Claude Code.

Step 5 — Connect Hermes To Ollama

Once Hermes is installed, you need to tell it to use Ollama.

Open Hermes' config file.

Add these lines:

provider: ollama
url: http://localhost:11434
model: gemma4

Save the file.

Restart Hermes.

If you're using Claude Code, you can ask it: "Configure Hermes to use my local Ollama with Gemma 4."

Done in seconds.

🔥 Brand new to AI agents? Inside the AI Profit Boardroom, I have a beginner's track for Hermes — start-from-zero tutorials, the exact configs I use, and weekly live coaching where I'll set this up with you on a screen-share. Plus a 2-hour Hermes course. 2,800+ members ready to help. → Get started here

Step 6 — Test It

Open Hermes.

Send a message: "Hello, are you working?"

You should get a reply.

If you do — congratulations.

You now have a free local AI agent running on your computer.

If you don't — check the troubleshooting section below.

Common Beginner Issues

1. "Ollama is not running."

Open Ollama from your applications.

It needs to be running for Hermes to talk to it.

2. "Model not found."

Run ollama list in terminal to see what's installed.

If your model isn't there, run ollama run gemma4 again.

3. Hermes can't connect.

Restart Hermes after Ollama is open.

Make sure the URL in your Hermes config is http://localhost:11434.

4. Replies are very slow.

Your machine might be too small for the model.

Try a smaller model like Gemma 4 if you started with something bigger.

What To Try First

Don't go straight for complex automations.

Start simple:

Ask it to summarise an article you paste in.
Have it draft a tweet about a topic.
Get it to explain a concept you don't understand.

Once you've used it for a few simple tasks, you'll get the hang of how it thinks.

Then move up to skills like web search and browser automation.

Why Local Beats Cloud For Beginners

Two reasons.

1. No bills.

Cloud APIs charge per token. Daily use adds up to real money.

Local Ollama is free forever.

2. No surprises.

Cloud APIs sometimes go down or rate-limit you.

Local runs whenever you want.

For beginners building confidence, removing those barriers matters.

What To Do After Setup

Once you've got Hermes + Ollama working, here's the next steps.

Try a few different models in Ollama to see which one you like (ollama run deepseek etc).
Turn on Hermes' built-in skills (web search is the most useful).
Set up your first scheduled task.
Connect Hermes to a channel like WhatsApp.

I cover each of these in detail inside the Boardroom.

Free Models Beginners Should Try

If Gemma 4 is working great, try these next:

DeepSeek — better at agent tasks.
Qwen 3.6 — general-purpose.
Nemotron 3 Nano Omni — Nvidia's new model (bigger, needs more RAM).

I cover Gemma 4 in Hermes Gemma 4 and DeepSeek in Hermes DeepSeek.

🚀 Want a guided beginner roadmap? The AI Profit Boardroom has a beginner's Hermes track — week 1 is "get it running", week 2 is "first useful task", week 3 is "first automation". Plus weekly live coaching, a 2-hour Hermes course, and 2,800+ members helping each other. The friendliest community for AI agent beginners. → Join here

FAQ — Hermes With Ollama (Beginner Version)

Is this actually free?

Yes — Ollama, Hermes, and the local models are all free.

Will it work on my old laptop?

If your laptop runs Chrome smoothly, Gemma 4 will probably run too.

Can I do this without using the terminal at all?

Almost — only one terminal command (ollama run gemma4) is required.

You can even let Claude Code or Codex run it for you.

How long does the whole setup take?

15–30 minutes for a beginner.

What can I do with Hermes once it's set up?

Chat, summarise, research, write, automate tasks, connect to apps.

Will my data leave my computer?

No — when you use local Ollama models, everything stays on your machine.

Should I use cloud models too?

Optional — local is enough for most beginners.

You can always add cloud later.