DEV Community

Cover image for Build Your Own Personal AI Agent That Works for You With Hermes
Rijul Rajesh
Rijul Rajesh

Posted on

Build Your Own Personal AI Agent That Works for You With Hermes

#ai #agents

Hello, I'm Rijul. I'm building git-lrc, a micro AI code reviewer that runs on every commit. It's free and source-available on GitHub. Star git-lrc to help more developers discover the project. Do give it a try and share your feedback

AI assistants can remember things about you now.

But what if you wanted to run your own personal AI agent that acts as your assistant across different parts of your life?

One that can:

  • Access your environment
  • Use tools
  • Remember the things you want it to remember
  • Continue working beyond a single chat window

For that, I want to introduce you to Hermes Agent.

What Is Hermes Agent?

Hermes Agent is an open-source personal AI agent developed by Nous Research.

At its core, it is a program that connects a language model to an environment where it can actually perform tasks.

You give Hermes a task.

Hermes sends that task to an AI model, receives the model's decisions, and then gives the model access to tools that can perform actions in the real world.

This makes it more than just a chatbot.

It is also different from traditional coding agents.

Coding agents are primarily designed to work on software projects.

Hermes is designed to act more like a personal AI assistant.

You can use it for tasks such as:

Research this topic.

Check my server.

Fix this code.

Search my previous conversations.

Run this workflow every morning.

Message me on Telegram when it's done.

The idea is to have an AI agent that can work across different areas instead of being limited to a single coding environment.

Now let's see how quickly we can set it up.

Setting Up Hermes Agent

You can find the repository here:

https://github.com/nousresearch/hermes-agent

The installation instructions are available in the README.

For this article, I'll demonstrate the Linux installation.

curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
Enter fullscreen mode Exit fullscreen mode

Once the installation is complete the setup wizard is launched, where you can configure the agent.

Once the setup is complete, we can start Hermes:

hermes
Enter fullscreen mode Exit fullscreen mode

Hermes Agent in Action

Now let's try a simple example.

I'll give Hermes a workflow that I regularly follow when publishing technical articles.

I regularly publish technical articles.

When I finish an article, my usual workflow is:

1. Check the article structure
2. Create a thumbnail
3. Create a short LinkedIn post

Remember this workflow.
Enter fullscreen mode Exit fullscreen mode

At this point, Hermes has been told about my workflow.

Now I'll close Hermes.

Later, I start it again and ask:

I just finished an article.

What should I do next?
Enter fullscreen mode Exit fullscreen mode

Hermes is able to retrieve the workflow I previously told it about and suggest the next steps.

It even offers to help me with those steps.

This is the interesting part.

The memory belongs to an agent that I can run myself.

It is not limited to a single chat session.

I can run the agent, give it information, close it, and return later.

The agent can then use the information I previously asked it to remember.

That starts to feel much more like a personal assistant than a traditional chatbot.

More Than Just Memory

Memory is only one part of Hermes Agent.

It also supports various connectors and tools that allow the agent to interact with different systems.

This means you can potentially build workflows around things like:

  • Your local environment
  • Servers
  • Messaging platforms
  • Research
  • Scheduled tasks
  • Other external services

I'll cover some of those connectors in a separate article.

For now, the main idea is simple:

You can run your own personal AI agent, give it access to tools, teach it your workflows, and allow it to remember information across sessions.

That's it for this introduction to Hermes Agent.

Thanks for reading. I'd love to hear your thoughts in the comments.

AI agents write code fast. They also silently remove logic, change behavior, and introduce bugs -- without telling you. You often find out in production.

git-lrc fixes this. It hooks into git commit and reviews every diff before it lands. 60-second setup. Completely free.

Any feedback or contributors are welcome! It's online, source-available, and ready for anyone to use.

Give it a ⭐ star on Github

Top comments (0)