What it does is break a PDF down into Markdown while trying to preserve the information and structure inside it. The impressive part is that it is not limited to reading lines of text. It is designed to handle tables, diagrams, flows, graphs, and other visual elements that ordinary OCR can easily flatten or misinterpret.

That distinction matters. A PDF is often not just a sequence of sentences. It can be a report with a table, a diagram explaining a process, a chart carrying the actual argument, or a page whose meaning depends on how all of those pieces fit together. Unlimited OCR is interesting because it appears to understand that document-level context rather than simply extracting isolated characters.

It runs locally, like a local model on your laptop. The download is not tiny, and I had roughly 6 GB in mind while setting it up, but I like the idea of being able to process documents locally instead of sending everything to a remote service.

The first setup was a little difficult for me. At one point I thought it had stopped working, when it was probably still doing something in the background. Once it was running, though, the results were impressive.

It also has a practical advantage for working with AI assistants. If you convert a complex PDF into clean, structured Markdown first, you can give the model a much more useful representation of the source. That can mean fewer repeated image uploads, less wasted context, and fewer tokens spent trying to reconstruct the document’s layout from scratch.

I am still playing with it, so I am not going to pretend it is perfect. But it is very good at the part that matters: understanding the document well enough to turn it into usable Markdown without losing the relationships between the text, tables, diagrams, and other elements.

Worth checking out:

• Unlimited OCR on GitHub

It is called book-to-skill, and it turns technical books, PDFs, document folders, and collections of sources into reusable agent skills.

A skill is basically a set of instructions and reference material that an AI agent can load when needed. When you invoke the skill, you are telling the assistant: this is the subject matter, this is the domain, and this is the expert frame you should use.

You could have a skill for copywriting. A skill for legal analysis. A skill for drafting rental agreements. A skill for accounting. A skill for chemistry. A skill for anti-money laundering. There are so many use cases once you understand the pattern.

Now imagine you are a marketer, a salesperson, an accountant, a chemist, a compliance person, or a specialist in any field. In your field, there are books. There are manuals. There are technical PDFs, white papers, product documents, research papers, training guides, and internal notes.

That is where book-to-skill becomes interesting.

You can take material you have the right to use, such as books you bought, public documents, open materials, company documentation, or technical manuals, and convert that knowledge into a skill. Instead of dumping a giant PDF into a chat every time, the skill becomes structured reference material that can be invoked when needed.

For example, let us say you are an anti-money laundering expert. You could take a large AML training manual, convert it into a skill, and suddenly you have a reusable knowledge layer around that material. You can invoke it when you are working, asking questions, drafting, reviewing, or thinking through a compliance issue.

You could do this with one book. You could do it with ten books. You could do it with a collection of manuals and papers. The point is not that the AI magically becomes perfect. The point is that you are giving it a structured, domain-specific body of knowledge to work from.

That is powerful.

The project is open source, available on GitHub, and it had about 28.7k stars at the time I wrote this. Try it with a book, manual, or PDF you know well and see how it changes the way you work with an AI assistant.

Useful link:

• book-to-skill on GitHub

DHH is David Heinemeier Hansson, co-owner of 37signals and the creator of Ruby on Rails. He is also the creator of Omarchy, and you can feel his taste all over it. This is not a neutral Linux install. It is opinionated, polished, and clearly built around a certain idea of how computing should feel.

The video that made it click for me was this one by NetworkChuck:

Watch the NetworkChuck video on YouTube

There is also this detailed NetworkChuck video showing Omarchy in use. This is the kind of walkthrough that makes the whole thing feel less theoretical and more like something you can actually install, touch, break, fix, and enjoy.

Watch the detailed Omarchy video on YouTube

And here is another useful one: 50 Tips after You Install Omarchy. Once you have Omarchy running, this is exactly the kind of practical follow-up video that helps you get comfortable with the environment.

Watch 50 Tips after You Install Omarchy on YouTube

The video is really well done. It made me understand what Omarchy is, and now I cannot wait to put it on some old machine and run it. There is something about this whole thing that brings back the beautiful side of computing and the internet for me. It feels playful again. It feels like tinkering again. It feels like the machine is yours again.

Also, if you search for DHH on X and look at the people interacting around Omarchy, you can see how much activity has suddenly appeared. Plugins, discussions, setups, screenshots, and people trying things out. The whole Omarchy Linux arena feels alive right now.

Suddenly, internet and computing is beautiful again.

Useful links:

• Omarchy official website
• Omarchy on GitHub
• DHH on X
• NetworkChuck’s Omarchy video
• NetworkChuck’s detailed Omarchy walkthrough
• 50 Tips after You Install Omarchy

The repository is worth looking at because it includes templates for things like:

• Advisor Agreement
• Master Services Agreement
• Mutual Non-Disclosure Agreement
• One-Way Non-Disclosure Agreement
• Privacy Policy
• Terms of Use
• Data Processing Addendum for the U.S. and global use
• Cookie Notice

That is a pretty useful collection, especially for startups, small technology companies, and anyone who needs a starting point for standard legal documents. Of course, templates are not a substitute for legal advice, but having a well-structured starting point can still save a lot of time.

The repository is here:

https://github.com/General-Legal/legal-templates

The secret is patience, and then more patience. Go through the results slowly. If you take your time, you will find gold mines you may not have known existed. It is also worth noting that some people on X consistently post about these kinds of projects, so they may be worth following once you start recognizing the useful accounts.

I do not want to recommend anyone specific yet because I am still going through the process myself, but the method works. Go back through older results, even as far back as a year. It can take hours, but it is well worth the effort. You can also write better search queries over time to narrow the results and find more relevant projects.

The search I used was:

https://x.com/search?q=open%20source%20github&src=typed_query