# Local Agents

_Here is a simple method to build your AI Agent(s)._

I work with a family of local [Agents(cxw tooltip click)]("An AI Agent is a program that uses Large Language Models to make decisions, pursue goals, and take actions on behalf of the user.") that streamline what I do. 

![A local ai agent works on behalf of their user, who is relaxing while it works (full trans)](images/illustration.img)

Yes, they multiply my productivity. These Agents follow a set of simple principles that reach these goals:

Goals [<]
  - One method that works across any use case
  - Isolate [domain expertise(cxw tooltip click)]("Your expertise is what the AIs don't have: Taste. You know how to turn data into information, how to apply that in your domain, and how to talk about it.") in portable files
  - Stay [Model(cxw tooltip click)]("A Large Language Model (short: LLM or Model) is a machine learning model capable of generating text that aims at completing the input of its user.")- and [Harness(cxw tooltip click)]("A Harness is a program that enables LLMs to operate as an Agent and users to provide that Agent with input. Examples are ChatGPT Work, Claude Code/Work, OpenCode.")-agnostic
  - Keep [Token(cxw tooltip click)]("Tokens are the atoms of AI inference and the currency Model providers use to price the usage of their Models.") cost at minimum
  - Use future compatible standards
  - Be ready for the next big thing

Let us assume you have not yet built your own Agents (or are unhappy with them).
Let us further assume you are a non-technical person.
Then I think there are good reasons to use the method as your next step:

* _Simplicity_: Each Agent is a folder on your computer that contains your domain expertise as single files. Each file is a self-contained program made of natural language, arranged in sub-folders that define its purpose and application.

* _Portability_: We don't know what the future brings, but we do know that we want to participate. So any effort you put in must result in your domain expertise being consolidated in a standardized, ready-to-transfer format.

* _Sovereignty_: I suppose you value technical independence. These Agents work with any Model, Provider, and Harness, including local Open Source. They even don't require the latest and greatest Models: Small and fast works best.

* _Locality_: With the Agents being a mere filesystem on your computer, you and you alone have control over what it knows and does. To provide your Agents to others, there are options (but the basic variant is not collaborative).

* _Extensibility_: Once you implemented one Agent, you can apply the same method to other use cases. The filesystem-approach allows you to link folders and files, so nothing needs to be written twice.

If these benefits resonate with you, I invite you to set up your Agent(s) by following my tutorial, which will take an afternoon: 

[Tutorial: Build your Local Agent (primary-button)](https://homepage.sefzig-net.workers.dev/tutorial/local-agent)

It explains the method's conventions, walks you through all folders and files, and provides you with all instructions that implement the core behavior. Once set up, you will understand the method, your Agent, and how to refine it.

But before you start, please note these three restrictions:

Prerequisites [<]
   * You need administrative rights on your computer.
   * You need to have a [Harness(cxw tooltip click)]("A Harness is a program that enables LLMs to operate as an Agent and users to provide that Agent with input. Examples are ChatGPT Work, Claude Code/Work, OpenCode.") installed.
   * If you want your Agent to be accessible for others, you need to have [Git (cxw tooltip click)]("Git is a way to keep code in sync across machines. If uncertain, approach your developers or IT.") or the means to securely deploy a [Container(cxw tooltip click)]("You can host the filesystem together with a headless Harness in the cloud (which is not trivial to set up). With such a solution, your Agent(s) become(s) an API you can connect to with systems such as Slack, n8n, or your website.") in your private cloud (not covered here).

I hope my method helps you enter the space of agentic AI or to refine your approach!

> [Hint]
> I like the topic and love to connect about it.
> Feel free to [contact me](https://homepage.sefzig-net.workers.dev/contact) if you need help or want to talk.