alt Hacker NewsAsk HN: What are you working on? (September 2026)
What are you working on? What have you been curious about lately?
Comments
A Godot framework for 2D games and (maybe) a new programming language specifically designed for gameplay logic.
A microkernel os https://github.com/corvad/os
Web bluetooth for ios (via safari extension). It's already way better than any 3rd party browser available in appstore.
I study stats and probability
Working on an open source graph of physics equations, quantities, and their connections to each other, to help learners connect concepts: https://anacoda.github.io/OpenFormulaGraph/
Because my work life is mostly LLM promoting, I’ve gotten back into hobby robotics, which I think has a low chance of LLMs taking over anytime soon. Designing and building a robot that can build a wooden hardwood deck using the edge-screw method.
I'm trying to build a tool site that has all the tools you'll ever need. I slowly add some each week.
I got laid off at the beginning of last month so put a little time into some personal projects I thought might be fun.
https://dstld.news - I have always wanted a personalized news site so I built one using a few news APIs with AI summaries.
https://hn.wreet.xyz - I'm a big fan of skeleton.dev and wanted a HN frontend with all the fun themes.
Nothing too exciting, just trying to find the joy in making again.
A few side projects!
- an open source AES67 hardware receiver/decoder - based on my friend Jessie's work [0]. I want speakers to have ethernet ports and to use an open/inexpensive stack. it's hard because physics/timing are brutal (1ms sync is ~not enough), but that's what makes it a great problem.
- an open source embroidery machine - based on my friend Owen's work [1]. Owen found Brother PE-150 machines which are readily available on eBay for ~$100 as they only work with proprietary 90s-era CF cards which nobody has (or sell for more than the machine). he designed a replacement motherboard (!!) and is running a fully open stack. it's wild.
- a ~$20 tiny cute display you can have on the side of your monitor, and display things on - realtime airport view from flightaware? a mini terminal? you can grab a display today [2], all that's missing is a 3d case (email me for firmware/OS code! I'll share it, just haven't had time). friends Frank and Sophie are working on a similar GUD-compatible display as well! [3]
- my friend Antoine has been working on Python bindings to Canonical's dqlite, a distributed sqlite-variant with raft-based failover and transactions (only C and Go clients existed) [4] - this will soon be a structural ("load-bearing"! haha!) part of Disco, a project we've been working on for a few years which lets you run your own PaaS. we're growing and get nice love letters [5] which for an open source project is obviously deeply rewarding
[0] https://jessie.grosen.systems/projects/aes67-receiver
[1] https://owentrueblood.com/blog/2024/12/10/reverse-engineerin...
[2] https://www.waveshare.com/rp2040-touch-lcd-1.69.htm
[3] https://bsky.app/profile/sophie.engineering/post/3muxysxhpck...
All in one platform for hosting agents
- Minimal setup - Any agent harness - A session is an actor - Opinionated infrastructure - Performance on the critical path
I worked on my AI agent that feels like a unix util. This month I changed the way it writes and edits files
a replacement for Octopus deploy https://rolloutrhino.com/ (marketing page is mostly a placeholder). Octopus is super expensive for our company and scales poorly if you have lots of small projects. I've got pretty much everything working really well, and the main thing I'm working on is improving the UX for all the workflows I do most often. It is mostly built around what I wanted from the tool, but before I release it I'm looking at supporting various other ways people use the tool. It's been a fun project so far.
Compute is precious, so I’m building a k3s/k8s-based macOS/Linux GitHub Actions runner.
I’m spending like $25/mo at least in GHA minutes.
Then working on securing and tinkering with my homelab. And little utilities that make repeated deterministic functions easier for me and agents.
Building https://typequicker.com
It's a personalized & data-driven typing application that targets your weak points
Just started:
1) bad apple on my kernel (OS)
2) language model + inference engine from scratch
3) sketchdaily.net, but you give it your own pinterest board of references instead of the preselected ones they have
Still hacking away on Raygum - a nice place to keep your music brain.
I don't even know what that means.
I spent some with reverse-engineering a neural network accelerator (NNA) inside a Chinese WiFi camera SoC: https://github.com/inoop/t41-pluto. I used Claude to reverse-engineer the hardware, and then implement an ONNX compiler and runtime so I can run my own models. Basically I now have a $20 AI smart camera.
I'm working on a p2p streaming/sharing app called bubbleBASED. Its here https://bubblebased.com/ its based! on bubbles! But it uses Webtorrent to stream and share content in context bubbles. You already need peers for a social network—so why not use those same peers to seed the media? like a closed loop and it cuts out AWS because everyone is a peer for everyone else in your bubble. There is an assist from Heroku and Pinata. There is no algo. Its just whatever you post. Also you can add an affiliate link (from cj.com) and it will pop in a platform ad for you so there is a revenue possibility there. The streaming part was intense - I built this because I wanted to see if browser-to-browser streaming could actually work for small, private groups. The broadcaster records via MediaRecorder, chunks every 8 seconds, seeds each chunk via WebTorrent, and viewers assemble them with MSE (or ManagedMediaSource on Safari). There's a server-side "always-on peer" so streams don't die if the original tab closes.
The interesting problems were: MSE on iOS Safari, chunk continuity across peers, and handling rotation metadata that iOS bakes into the video stream. Also, the tracker is a separate bittorrent-tracker instance because the built-in WebTorrent trackers are unreliable for sustained swarms. Also i used a ton of graphql, so normally with a torrent you have to kind of let people find you but i used a graphql subscription to TELL people what the magnet links were called so they can fetch them asap. Lots of shortcuts like that, its been interesting!!
I've been working on https://pronto.stream/, I wanted to mess around with MCP and building a world news system to power the decision making and surveillance of other systems I would likely curate.
I was curious about formats more efficient for agent communication than JSON and also proving if the framework I curated could handle the load and traffic.
It's been really fun to observe.
Contributing larger PRs to terraform-provider-aws because apparently my contributions so far do not have enough lines of code as a metric. Getting familiar with Floci for usage with Terraform over LocalStack since it is a true open source project rather than freemium. Also getting my AAS from Maestro. Ride or die since I can not afford college anywhere else despite their current accreditation issues with COE.
I’m working on a 52-part series about retention.
Each week I research one part of retention, teach it, and apply it to two real-world products I built.
I’ve published five lectures so far, and think the series should be useful to anyone here building a product: https://www.youtube.com/playlist?list=PLFp5nmjrQeug
I am working on a code forge that can work offline for the collaborative stuff. https://juju.bi
An analytics store for Postgres on S3 using DuckDB as the query engine
I am building OtaKit.app, a cheap, fast, and simple CDN-based over-the-air updating tool for Capacitor apps (and soon for React Native too)
A local AI-adoption consultancy business for SMBs where the differentiator is I physically show up at your office and actually talk to your team. With the slopification of cold outreach and social posting, I think the future of business development is going to be very personal.
Online container planner in 3d
I'm learning on how to move away from computing into violin making and repairs.
we are building https://www.d5s.tech, using our own software to automate our own company (the boring bits)! having a blast doing it and steadily automating more and more
and... whenever i have some spare gpt-6 astra left i am working on a R.U.S.E reimplementation alongside some other threejs experiments
I'm building editor and flasher for BMW engines maps (n13, n20, n55, s55, b58, s58) and TCU maps (ZF8HP45 and ZF8HP50) as well as a remote access ENET IOS and Android app.
I've been working on https://searchforjobs.app/ I'm trying to add the resume creator for using the right keywords for a job posting. I'm also trying to add more data visualizations are more job posting sources to scrape.
Build one of the best emoji sites there is.
- i dropped a neural net jane street puzzle (https://huggingface.co/spaces/jane-street/droppedaneuralnet) very good mindbreaker, learned a lot of new things on the way
RSS Bot for Telegram: learns what you like, searchable, using free models (vibe-coded): https://github.com/amb007/rss-bot
The 2026-27 soccer season just started.
If you love catching up on highlights, check https://thepelota.tv/
It’s like Netflix but for soccer highlights, with all the major leagues in one place as soon as they are available on YouTube, all free and no ads.
I'm further along in my funemployment project:
https://github.com/mcdirmid/cleanroom
So far I have bazel macros up that can produce tested code with a ~30GB MoE model (Jundot/Qwen3.6-35B-A3B-oQ6-mtp, I can get ~90 toks/sec on a M3 Max!) using cleanroom separate implementation and test development (and then comparing them until both are correct). Over the last month, however, I found that my bottleneck is in the specifications: as I further divided my components into separate parts (since smaller components are easier to write and test), I started hitting problems with specifications becoming badly ungrounded (code depending on knowledge they cannot access, so something is just hallucinated).
So I redid the format, e.g.
https://github.com/mcdirmid/cleanroom/blob/main/update_with_...
The spec format is designed to be declarative and very modular, and ya, an LLM is primarily writing the specs as well, so I hope to create some sort of formal reasoning framework that the specification can be translated into (by an LLM) so that ungroundness feedback can help the LLM write better specs. Also, I found that it really is much more robust to change/refactor/add features via the spec first and then align changes down to test and code, then to make changes to the code directly (even without using the system, just asking a frontier model to look at the guides and do the alignment itself directly).
I think I'll be ready to do a release over this next month, which means:
- Supporting a build system other than Bazel to express DAGs. Honestly, this could be anything, I just chose Bazel for convenience (easy to express graphs in Starlark), but it assumes a monorepo world that I don't think many developers use.
- How do I even package this? The advance of using Starlark is that I can generate python code to call into the generated python code directly. If I move away from that, I need to figure out what this really looks like as a binary.
- More demos. Right now my only project is the code for the system itself (the classic "the first program of a language is the compiler for the language"). I just can't think of many interesting things to do in Python that aren't agent related (I can support other languages, like Java, Typescript, or even C++, but I'm hitting choice paralysis).
An Openclaw, Hermes Agent type system that is meant to be ran on a home server, built in Rails with a Tauri 2 front-end.
Don, a work companion.
Don helps you set goals.
Don reminds you to take breaks.
Don checks in how you fell.
Don judges you when you go off track.
Don celebrates you when you get stuff done.
I haven't been working on it as of late, mostly because i'm a bit deflated from software in general, but I started working on a programming language I called Grasp.
If lisp is a list processing language, grasp is a graph programming language.
The idea was that most other data structures can be represented with a graph ( adjacency matrices are matrices, a tree is a type of directed acyclic graph, a list is a graph where each node connects to at most two nodes, etc) and so if you designed a programming language where the language is itself a graph, much like how lisp is itself a list, you could get other esoteric programming languages like APL, forth, lisp, and so on as DSLs of Grasp. Also any program you write would be its own CFG.
I started it but honestly its mostly a hot mess of vibe-coded garbage. But I may get back on it and try to clean it up.
Keyboard pants https://mastodon.pirateparty.be/@utopiah/117157231799845118
TL;DR: magnets.
i am working on a really cool word game that has a TUI graphical style, it looks like a roguelike but has a bit more going on. i also seem to have figured out a way to do automated "fun factor" testing and get bugs/frs that sound like real player feedback, as a little bonus treat. doesn't seem like anybody is attempting that kind of thing with agents, might try to codify it. trying to spend a lot longer thinking about a game's systems/meta and developing slowly vs. hypersprinting which is fun but exhausting.
I just released an open-source AI pipeline that turns GitHub issues into merged PR's. It uses your Claude Code CLI subscription.
Looking for feedback from people who already run Claude Code and are testing out new AI software factories or tools.
Try it here https://github.com/Team1-dev/Team1-Factory
Please only run this on a VPS or isolated environment and not on your personal machine as it runs with full permissions.
Optimem, a spaced repetition learning app that aims to be a user-friendly alternative to Anki. Or a more effective version of Duolingo.
I'm working on SpecPilot (https://specpilot.dev), a spec-driven development layer that sits in front of Claude Code, Cursor, Copilot and the rest. It deliberately doesn't generate code. It scaffolds a .specs/ folder and hands the actual writing off to whatever agent you already use, so the specs become the thing the agent is held to instead of a prompt you retype every session.
Open source, free, no login, nothing to sell. I'm not trying to build a business on this. I just want agents to write better code, and that only happens when they have something firmer than a chat prompt to work against. CLI is here: https://github.com/girishr/SpecPilot
It started as a TypeScript CLI in January. Enough people told me they either didn't want a CLI or didn't know how to use one that I rebuilt the front door as a guided chat: 27 questions, runs fully offline in the browser, outputs the .specs/ tree plus an onboarding prompt for your IDE.
Recently shipped an MCP server so the agent can run the questionnaire itself rather than the human doing it, published to the official MCP registry and Smithery. Next is brownfield: point it at an existing repo and backfill specs from the code. Honest state of things: the Product Hunt launch got 4 votes and around 100 visitors, and I had no event tracking wired up, so I couldn't even tell how many of those generated anything. Fixed since. Usage is small but real, and it's coming through MCP rather than the web app, which I did not expect.
The part I keep circling back to is that spec generation is easy to copy. Spec enforcement is where the value is: checking a diff against the spec and failing loudly. Feedback welcome, especially from anyone who tried SDD on an existing codebase and gave up.
Writing an article about compacting garbage collection for my website.
On a mission to prove you don't need YC to be successful.
Lots of things really:
1. Aetheris: geometry CAD kernel, https://github.com/yuechen-li-dev/Aetheris/.
Full code CAD capability with big coverage already and some functionalities that even OpenCascade/Parasolid/ACIS doesn't have, full sheet metal module, programmable part assembly, analytical fillets/chamfers, mathematical knots, auto-route for piping, built-in finite element analysis, etc. Had Astra make an improved version of the V8 demo that was going around on LinkedIn, so it can do general hard surface modeling pretty well too, turn all the Astra demo prowess into reusable capabilities/templates. The DSL is human writable too, so give it a try if you want. https://aetheris-editable-v8.yuechenli.workers.dev/
2. Concept language: https://github.com/yuechen-li-dev/Concept
I've said before that Carbon isn't a real programming language, never mind a successor to C++, so I decided to put my money where my mouth is. The idea of it is to be more TypeScript to C++'s JavaScript and to generalize C++20 concepts from template constraints to what C++26 is doing with contracts, and bring the equivalent of Rust's borrow checker to be opt-in by default instead of opt-out, fast compile time, in a syntax that C++ users are already familiar with (`const auto` instead of `let` for example) as well as templates and comptime. Language is done-ish, not self hosted yet, still compiles to C11, kernel and allocator libraries are finished, currently working on the scheduler right now.
3. Copeland TS, https://github.com/yuechen-li-dev/copeland
TypeScript for .NET without all the weirdness of Javascript, with full Nuget and NPM inter-op, Rust style exhaustive `match`, templates, etc. It's actually weird how much cleaned up TypeScript ended up looking like cleaned up C++. Compiles to JS, C#, WASM via Blazor WebAssembly, and SPIR-V via HLSL/DXC, and runs on V8 for JS and RyuJIT/NativeAOT for C#. The conclusion is that RyuJIT ended up being ~2x faster than V8 JS in hot loops but the cold startup time is higher, so replacing JS for UI really isn't worth it. Comes with full UI layout system, Vulkan renderer, and game/app runtime, but those are still pretty rough.
Trying to reduce my doomscrolling IG and FB usage
I created https://getnoloop.com to block the feed on iOS
I have been working on cost models and coupon ladders for businesses.
If either of those are interesting to you, please reach out!
For example, I am helping some restaurants learn exactly how much each item on the menu costs, what the margins are, and how much profit each dish is bringing in because I integrate with their PoS system.
https://imgur.com/a/C127GOY
It's all a part of GetSetReply which is turning into a small suite of tools for SMBs
https://GetSetReply.com