Skip to content
UncomplicateAI

Open source, decoded

Open source means the code or model is public and you can run it yourself. What that buys you, what it costs, and why so many AI tools say it on the label.

By Nick

2 min read

AI BasicsLocal AI Beginner
On this page

Open source means the code is public. Anyone can read it, copy it, change it and run it on their own machine. For AI, it also covers open models: ones whose insides are published so you can download them and run them yourself, which is what local AI is built on.

What it buys you

Control. It runs where you put it, talks to what you connect, and nobody can change the price or switch it off. Hermes is the agent version of that; n8n is the automation version.

Privacy. Your data stays on the machine you run it on, with the four caveats on the local is not private page.

No bill for the software. The tool itself is free.

What it costs you

You run it. A machine that stays on, updates, backups, the restart at three in the morning. “Free” is the download; the rest is your time.

You pay for the thinking. An open agent still needs a model. Run an open one locally and pay in hardware, or call a hosted one and pay per use. The agent is free; the brain is not.

Setup is real. An afternoon, not five minutes, and the documentation assumes you can read a terminal (a window where you type commands).

The honest rule

Hosted when you want it working this week and are happy to rent. Open source when you want to own it and are happy to run it. Most people on this site start hosted and move one piece at a time.

If you are weighing a specific tool, ask it:

For [the tool], tell me plainly: is it open source, what would I have to run myself to use
it, what would still cost money, and what is the hosted alternative that does the same job?
Four short answers.
Example reply (trimmed). Your app will word it differently.

Asked about Inkwell Notes, a note-taking tool, plus the prompt above

  1. Open source? Yes. The code is public and anyone can run their own copy.
  2. What you run: a small server or an always-on computer, plus updates and backups.
  3. What still costs money: the machine, and any AI model it calls, which is billed per use.
  4. Hosted alternative: Inkwell Cloud does the same job, and they run it for you for a monthly fee.

Common questions

Is open source free?

The software, yes. The computer it runs on, the electricity, and the model it calls are not. Free to use is not the same as free to run.

Is it safer?

More inspectable, which is not the same. Anyone can read the code, so bad things get found. But you are the one keeping it updated, and an unpatched server is less safe than a well-run service.

What is an open model?

A model whose weights are published, so you can download and run it. Ollama and LM Studio are full of them. The big hosted models are not open; you rent access.

What to do next

  • Learn

    What is local AI?

    Local AI means running the model on your own computer instead of somebody else's. What you gain, what you give up, and if your machine can cope.

    5 min read

  • Tools

    Hermes: an AI agent you can run yourself

    Hermes Agent is a free, open-source AI agent from Nous Research. It uses tools, remembers things between sessions and keeps working in the background on a machine you control.

    3 min read

Related reading

Last reviewed 9 October 2026 by Nick.

Software changes fast. If something here is out of date, tell me and I'll fix it.

Get new guides by email

Occasional and practical. No spam, no hype, unsubscribe whenever.

Occasional practical guides from UncomplicateAI. You will get a confirmation email before anything else is sent. Unsubscribe any time. Privacy

You are not subscribed until you confirm the email. Unsubscribe any time.