I (and I'm sure many others) have been thinking about this a lot over the last couple of months. I called it "Extremely Personal Software" in a blog post a few months ago (https://redfloatplane.lol/blog/14-releasing-software-now/) but there are lots of names and concepts floating about for the same basic idea.
I think it's possible the amount of new software that will be written for an audience of 1-10 will be greater in 2026 than in any previous year, and then the same again for many years to come. I also think a lot of this software will be essentially 'hidden' - people just writing this stuff for themselves because the cost to say things to an agent is very low compared with the cost of actually planning out a software design and so forth.
Interoperability will probably be important in the next few years and I wonder if this is something solvable at the agent/LLM level (standing instructions like 'typically, use sqlite, use plaintext, use open standards' or whatever). I also think observability and ops will be pretty important - many people who want personal software but don't care for the maintenance and upkeep.
Agreed I’ve already started writing software for myself using Claude. I would never have done this if it weren’t for AI - I simply don’t have the time otherwise .
I now have tailor made apps with all kinds of bells and whistles that commercial products can’t offer easily ( I fall under non commercial usage which opens a lot of doors ), and that free software might offer, but later.
I have also learnt a lot technically in the process, since I’ve been able to venture into what was for me unknown territory but at controlled cost
I plan to create more such apps in the future. What is certain though is that my cooking app has immediately displaced all the others on the market , because none of the others cater to my requirements.
The production side is indeed of specific interest - most users don’t run production software so I had to think about that one. Tailscale and Cloudflare came in quite handy and there is indeed a market here
I had the same reaction. We're headed into a period where you can shape your tools exactly as you like them; artisanal rather than factory-created workshops, essentially.
I think the instinct that APIs, validation layers, and so on take on a much higher importance is right.. I have a few internal tools that made sense to make libraries out of, and once the first library is good, and a test suite is comprehensive, porting to a bunch of different languages is extremely simple.
Everting that, it's also going to be simple for someone to hook up to this library with custom tooling.
I shudder to think about the security implications of everyone rolling thier own software. I trust my OS/browser/file system is secure because thousands of people are invovled in a complex network of interests in keeping it secure, from the kid contributing his first bit of code to the PHds at NSA writing encryption standards. The idea that any one person can replace that network is laughable.
That seems like a naive view to me. Most modern software development is gluing vendor code and libraries into a CRUD app, and I don't see why that would change with agents doing the majority of programming. If anything, there's an even bigger market for solid libraries and interoperability, plugging things together like LEGO - only for real this time.
While I wouldn't do asm, I love the approach and do much the same myself but in Ruby instead.
My wm, shell, terminal, editor, file manager, pop-up menu (dmenu-like) are all pure ruby (including font rendering and X11 bindings). These all started before I started using Claude to improve them, so they're still mostly hand-written, but that is changing.
They're messy, they have bugs and "misfeatures" that works for me but likely would be painful for others.
Like OP, I don't really recommend anyone else use my code, at least not directly, and that is extremely liberating.
Overall, the projects covers the largest surface of what I use beyond the kernel, a browser, and Xorg (I'm so, so tempted, but I think an LLM will need to get a lot further first before I could fit it into my schedule).
It doesn't need to be polished because it's mostly for me. It's okay for them to have bugs as long as they work better for me than the alternatives.
I strongly believe more people should do this. It's both a great learning experience, and it gives you a system that has exactly the features you actually want and use.
This is very cool. I wonder how much time did it actually take, and how much did it cost, because Clause Code is very much not free [1] [2]. It's more like hiring a robotic contractor, very fast, but with a serious hourly rate.
I'm on Claude Max, so it didn't cost me anything more than the subscription I already have. Had to use it for Something. As for time - for the full CHasm and Fe2O3 suite of sw, I started the work 2026-03-29 and have probably spent 60h or so of my time. But then again I have a very tailored CC setup that I have fine-tuned since last summer with more than 70 CC projects helping me get it the way I need it to be since then.
So, it's at most $400 in Claude expenses for a fully custom suite of software in 2 months. Even if your time is 300/h, it's less than $2k in your own time (which, I would expect, you enjoyed spending). That's insanely impressive.
I need Claude Max in any case for my work, so the cost is effectively null. And I do creative stuff in my spare time regardless, and I don't really think about my hourly rate when I play with my kids either ;)
I find this fascinating. I also like to customize my desktop experience with my own code, but it's more assembling stuff with some additional code as glue.
A word of warning: a reliable lock tool for X11 is difficult. You should look at XSecureLock, which uses a multiprocess approach to avoid leaving the desktop unprotected in case of crash. It also implements a number of countermeasure to ensure the desktop stays locked and the locker stays in the front of the display. It's small too, so easy to audit (but written in C).
Did you have to look or review any of the code produced, to get the performance/capabilities that you wanted, or were all interactions through CC? In other words, did you hit any walls with the pure agentic workflow?
On this software itself: I’d like to know how this feels to use. It’s so very lightweight. Does it feel categorically different to what we are used to?
One of the things I miss about the 1980s home computers is that they booted into a usable command line in a handful of seconds, from a few KB in ROM. Imagine what today’s HW could do if we’d retained that level of efficiency.
That’s wonderful! I’ve made ultra-lightweight web apps of my own to replace bloated, slow, and poor UIs. It’s a night and day difference when the dependencies are few-to-none. And that’s on a fat browser stack. Your ASM desktop must zip!
seriously.... we already have a constellation of good deterministic tooling for taking a relatively high concept spec to low level assembly. what does an llm offer in generating optimized asm that rust wouldn't??
Less memory footprint. No reliance on libs. Pure first-person control. No wasted CPU cycles is the target here for me. And if you read the post, the asm set is only for the desktop itself. The tools I use are in Rust. Result is: Laptop now runs at between 5-6W (down from ~9W) [XPS14 latest hw] on Ubuntu 26.04 - giving me around 3.5h extra battery life.
My guess is you're likely to waste more cycles on development time, and on suboptimal algorithms because the implementation is harder, than you would waste on rust-related bloat.
Still a cool project, thanks for sharing.
I have wondered about having LLMs output machine code directly and skipping the compiler/assembler altogether. Then you'd just commit your spec/prompt and run it through the LLM to get your binary.
rust can do that. You can run a hyper stripped down rust that was made for embedded devices specifically because those devices don't have room for a runtime.
Sorry I have a question that is a little off-topic: what's the value of generating an image of a laptop on a desk? That's not like it's particularly relevant, when you could have integrated a screen shot of your set-up (like the same one you put on a few of your repos) or something more unique, and even if you want to show that, it's easy to find similar images with the same vibe, so I guess it's for some fun I missed in the process?
Same reason people muck about with knowledge management systems... to put off the day when you have to sit down at your desk and actually do something.
I think this is going to be the OS of the future. You tell the computer what you want to do, and it uses the OS's APIs to create your program for you. No more copilot embedded in notepad unless that what you ask for.
Most software is done after the first or second version and the developers just keep working on it to justify their job; adding features no one needs and just get in the way or make the program worse. It'll be nice when the software I have does exactly what I need and doesn't change until I tell it to change for something I need.
The only feature Macos has shipped in the past 10 years that I actually like is air-drop. Everything else is a PITA annoyance, or as I've found out from upgrading, just bug ridden slop that doesn't work well anymore.
I've been building an object oriented system re-imagined in a world with LLMs called Abject (https://abject.world) and one thought I had was to build an OS that boots into my project. One way to do it would be a minimal linux distro (think firefox os or similar). Has anyone done something like this with their projects?
OP did this:
Prompted CC for all the points I wanted included (something like a 200 word prompt) and asked CC to draft it, including all the links added to the table I furnished. Then I edited the draft (about 50% then edited). Then asked CC to spellcheck and fixed the 5 it found.
Thank you. It would have been nice to see you personalize the hook and show your storytelling voice the way you personalized your computer in the story, but we aren't all poets.
I think it's possible the amount of new software that will be written for an audience of 1-10 will be greater in 2026 than in any previous year, and then the same again for many years to come. I also think a lot of this software will be essentially 'hidden' - people just writing this stuff for themselves because the cost to say things to an agent is very low compared with the cost of actually planning out a software design and so forth.
Interoperability will probably be important in the next few years and I wonder if this is something solvable at the agent/LLM level (standing instructions like 'typically, use sqlite, use plaintext, use open standards' or whatever). I also think observability and ops will be pretty important - many people who want personal software but don't care for the maintenance and upkeep.
I now have tailor made apps with all kinds of bells and whistles that commercial products can’t offer easily ( I fall under non commercial usage which opens a lot of doors ), and that free software might offer, but later.
I have also learnt a lot technically in the process, since I’ve been able to venture into what was for me unknown territory but at controlled cost
I plan to create more such apps in the future. What is certain though is that my cooking app has immediately displaced all the others on the market , because none of the others cater to my requirements.
The production side is indeed of specific interest - most users don’t run production software so I had to think about that one. Tailscale and Cloudflare came in quite handy and there is indeed a market here
I think the instinct that APIs, validation layers, and so on take on a much higher importance is right.. I have a few internal tools that made sense to make libraries out of, and once the first library is good, and a test suite is comprehensive, porting to a bunch of different languages is extremely simple.
Everting that, it's also going to be simple for someone to hook up to this library with custom tooling.
Really interesting period in computing, for sure.
My wm, shell, terminal, editor, file manager, pop-up menu (dmenu-like) are all pure ruby (including font rendering and X11 bindings). These all started before I started using Claude to improve them, so they're still mostly hand-written, but that is changing.
They're messy, they have bugs and "misfeatures" that works for me but likely would be painful for others.
Like OP, I don't really recommend anyone else use my code, at least not directly, and that is extremely liberating.
Overall, the projects covers the largest surface of what I use beyond the kernel, a browser, and Xorg (I'm so, so tempted, but I think an LLM will need to get a lot further first before I could fit it into my schedule).
It doesn't need to be polished because it's mostly for me. It's okay for them to have bugs as long as they work better for me than the alternatives.
I strongly believe more people should do this. It's both a great learning experience, and it gives you a system that has exactly the features you actually want and use.
And it's only going to get easier to do this.
[1]: https://fortune.com/2026/04/28/nvidia-executive-cost-of-ai-i...
[2]: https://www.briefs.co/news/uber-torches-entire-2026-ai-budge...
As a hobby, normal rates don’t apply, but just not to be misleading on the equivalent cost.
A word of warning: a reliable lock tool for X11 is difficult. You should look at XSecureLock, which uses a multiprocess approach to avoid leaving the desktop unprotected in case of crash. It also implements a number of countermeasure to ensure the desktop stays locked and the locker stays in the front of the display. It's small too, so easy to audit (but written in C).
On this software itself: I’d like to know how this feels to use. It’s so very lightweight. Does it feel categorically different to what we are used to?
One of the things I miss about the 1980s home computers is that they booted into a usable command line in a handful of seconds, from a few KB in ROM. Imagine what today’s HW could do if we’d retained that level of efficiency.
Would it be possible to share the jsonl files too, like how Mario Zechner shared his chats with the AI, while working on his Pi coding agent?
https://x.com/badlogicgames/status/2041151967695634619?s=46
There are big benefits to using a language that has good static analysis with LLMs.
Still a cool project, thanks for sharing.
I have wondered about having LLMs output machine code directly and skipping the compiler/assembler altogether. Then you'd just commit your spec/prompt and run it through the LLM to get your binary.
rust can do that. You can run a hyper stripped down rust that was made for embedded devices specifically because those devices don't have room for a runtime.
And it apparently can. And very well.
One advantage seems to be that the complete asm file fits easily into CC context window.
well, I can respect that for sure
I struggle to understand why, though.
0: https://github.com/isene/chasm
Most software is done after the first or second version and the developers just keep working on it to justify their job; adding features no one needs and just get in the way or make the program worse. It'll be nice when the software I have does exactly what I need and doesn't change until I tell it to change for something I need.
The only feature Macos has shipped in the past 10 years that I actually like is air-drop. Everything else is a PITA annoyance, or as I've found out from upgrading, just bug ridden slop that doesn't work well anymore.
Also, reading it is probably not the intended use. It’s probably: “Hey Claude, give me a TLDR of this”
But the incessant “AI was used here, thus is it garbage” is long past time to enter the grave.