Built a 1.3M-line agent-native OS in Rust while homeless. What now?
My dad was diagnosed with cancer. While he was in hospital, the council emptied his house. Everything I owned was in that house. £20,000+ of equipment, years of research, a server with thousands of hours of work. Locks of my kids’ hair. Photos. All thrown in a tip.
My family turned my dying dad against me. I ended up living with someone suffering from paranoid psychosis. That’s where I built most of what I’m about to describe. Three days ago, 24 hours of abuse, and now I’m in a tent with my dog. 5°C weather. No money.
The council refused housing. The government won’t recognise my autism. They want me job hunting 35 hours a week from a tent.
I’m not incapable. I’ve raised a family. I’ve worked my whole adult life. Supervising teams, tattooing, freelance programming, building proprietary backend systems across 20 years of working with Linux. My autism isn’t a disability here. It’s the reason I can hold an entire OS architecture in my head and see how every component connects. When I point this brain at a problem, it produces systems that work, at a speed that doesn’t make sense to most people.
Over the past 4 months, I’ve been building OctantOS. An operating system for autonomous AI agents. Not a framework. Not a container wrapper. An actual OS with its own kernel (OctantCore, from-scratch Rust), its own hypervisor (OctantVMM), a single-binary Rust userspace, and a 10-layer security stack enforcing agent permissions at the kernel level.
~1.3M total lines of code. ~800K Rust. 50 crates, ~25 satellite projects. 3,900+ tests. Solo developer. No CS degree. 4 months.
The thesis: application-layer trust is insufficient for autonomous agents. OctantCore makes agent identity, capability boundaries, TTL enforcement, and audit first-class kernel primitives. Manifests compile to kernel enforcement policies. The agent doesn’t decide what it can do. The kernel does.
Rust LSM patches reviewed on lore.kernel.org by Google’s Rust-for-Linux team and the LSM maintainer. OctantCore boots on OctantVMM with memory manager, interrupts, syscall interface, Agent Descriptor Table, and capability enforcer initializing at boot. Built by orchestrating 10-12 parallel AI coding sessions simultaneously.
It goes beyond isolation. Agents identify gaps in their own knowledge and seek out what they don’t know (curiosity subsystem, implemented). Background inference consolidates learned patterns (dreaming). A 7-stage self-evolution pipeline within constitutional safety boundaries. New skills propagate across every OctantOS instance globally via the mesh layer. All kernel-constrained.
Nothing like this has existed before. That’s what dies if I can’t keep going.
I need stability. A place to live and enough to cover basics for 3 months to get OctantOS investment-ready. An angel willing to back me for that runway. A company that says “come work here, we have a place.” I’ll relocate anywhere, tomorrow, with my dog. Or just advice from someone who’s been here.
I just need someone to take a bet on what this brain can do when it’s not freezing in a tent.
https://github.com/MatrixForgeLabs/OctantOS https://octant-os.com https://gofund.me/f554a86ee
12 comments
[ 3.3 ms ] story [ 44.6 ms ] threadThere’s a lot of big projects posted these days, hard to find traction. You built it all? or AI coded it and you orchestrated? I think look for IT work and get money for housing until the SWE market improves.
Best of luck to you, it’s a brutal job market in tech right now. Try to find local people and help them with tech, I think there are probably enough huge new projects being made for no one specific and no specific use case.
Have you spoken to https://www.citizensadvice.org.uk/ you should be able to get some help and advocacy. And they will help you find accomodation and apply for the benefits you are entitled to.
If you can get a proper diagnosis you can also claim PIP for more support: https://www.benefitsandwork.co.uk/personal-independence-paym...
You're obviously smart and probably present as high functioning to someone working in the job centre who is not motivated to help you and frankly anything they give you, you will be massively underemployed.
---
I will say something feels off with the project itself just by looking at the stats.
Obviously an LLM is doing the heavy lifting to write 1.3m lines in 4 months, but 3,900+ tests seems an order of magnitude too small to me.
What LLM are you using to generate this much code? Priority 1 right now is to get accomodation, not pay for expensive LLM API costs or subscriptions!
Best of luck!
https://news.ycombinator.com/item?id=47340079
Sometimes I can come across as rude or arrogant or a bit "in ya face" so sometimes I do ask Claude etc to review and rewrite my posts and comments.
It's the autism creeping out and I think it's better to use AI to rewrite a comment than come across as a d*k unintentionally.
I assume nobody is particularly bothered by an autistic person using AI to make sure he's not a d*k by accident?
It's still my comment, just with the miscommunication removed.
Your priorities are completely wrong. You need to redirect the time and energy you're spending on this project towards getting back to stable ground, starting with utilizing the safety nets that your government and community make available to you. You need to find psychiatric care and shelter immediately, and eventually, gainful employment of any kind.
Your GoFundMe is still at $0. Putting myself in your shoes, to say that's probably demoralizing is an understatement.
I noticed that donating requires a real surname that matches the card info provided, which is then available to the organizer. That might be giving people here cold feet since you're a new account; the anonymous donation option just removes the name from public visibility.
Beyond that, having spent the better part of my day yesterday vetting this, I'd say the other items are:
a) Lack of source code that essentially proves you've got it working.
In a nutshell: imagine if the OpenClaw author took your approach, under your circumstances. I highly doubt it would've went anywhere. The way it went however, he ended up joining OpenAI.
Point being: from that same position, he could've instead raised funds no problem. That's the position you could be in if you take the OSS route, and indeed most startups these days begin as open source since proprietary is losing favor rapidly.
That said, myself being a fan of monolithic Rust binaries that do crazy stuff and having authored several professionally to great effect, I know precisely what you're building and indeed some of your competitors in the agentic isolation space are getting large funding rounds right now.
The point there being: you're not wrong that it could work, it's just that from your current position this is by far the riskiest path. With velocity what it is right now, witholding source might not matter all that much; you already have a project architecture description up that makes it easy enough unfortunately.
Please understand I'm not trying to trivialize your work here; I read all of your kernel.org correspondence. Nor am I trying to pressure you in bad faith into something you're not comfortable with. What I'm saying that if you take the OSS route, while you might not necessarily end up a rock star, you open up a hell of a lot of doors you otherwise wouldn't because you have people actually using it and going "Hey, this is pretty cool."
That moves your moat from technical (withholding source) to a social one.
If your project is as good as you say, even if it's alpha quality, there's a chance your project ends up the de-facto agentic isolation choice that people reach for. In the midst of a gold rush, that's an enviable position that might even exceed the best outcome on your current [proprietary] course.
b) A perceived attitude issue. Let me explain: I understand where you're coming from there, and were I an angel I'd personally select for a level of belief that borders on irresponsible and crazy. Most people don't think like that, so: respect.
However, it can come across as you saying you're too good for drudgery, essentially. I get that, you want to use your potential to its fullest and not doing so feels maddening. I had to bite the bullet and get a job in a similar situation that fell just short of total financial ruin, but what made that palatable to my belief system at the time (which was eerily similar to your current one), is this: the job was an instrumental objective in ensuring startup success. It's the same thing.
Regarding dead-end jobs, those might be what you want. If you're accustomed to working 18 hours a day recently, working one for 8 hours to put a roof over your head that has a lot of [safe] downtime—where most people aimlessly scroll on their phone—sounds like it'd work out pretty well for you relative to your current situation.
---
OK, now that I've had my turn at being insufferable and heaping on a bunch of unsolicited advice, some questions:
1. Has anyone reached out privately to help, or is the situation radio silence right now?
2. How is your food security? Shelter isn't doing great right now obviously, but I'm worried things might get truly dire.
3. Do you have any friends that can help? It doe...
I will come later today and get back to you.
I will say I appreciate you though.
1. You are supposedly some super intelligent autistic person… but you can’t even properly format the last lines of your post , so someone would have to struggle to copy / paste the link to your websites . That’s going to be a barrier for most people in a competitive landscape for attention.
2. You have only been on hacker news for 40 days. Or at least this account. Interesting. I’m not sure when an account crosses the “new account” threshold and stops being green.
3. No contact information in your profile. If someone wanted to help you , they would want to reach out directly and privately , you don’t give them a way to do that. Again, you’re supposedly some super smart autistic but you failed at a very basic thing.
I say all the above as gently and respectfully as possible. I’m trying to reconcile your supposedly genius level of intelligence with some fairly basic major gaffes.
Not sure if this is some kind of guerrilla marketing / feel bad for me approach to stand out from the crowd or what.