alt Hacker NewsAsk HN: What are you working on? (February 2026)
What are you working on? Any new ideas that you're thinking about?
Comments
I'm running a BETA on Worn, my tape saturation VST. Made in Cmajor with some help of vibe coding.
https://stoneandsignalaudio.com/
Use code 'FREEBETA' to partake, ~25 seats left.
I'm also making music. I got Suno to do a cover of 2 songs I wrote, although eventually I want to introduce human versions. Also want to make electronic music eventually.
I'm making Letterboxd for TV, with a pretty data visualizations.
The UI/UX is a pretty interesting problem. Letterboxd has it easy because a movie is its own discrete unit, but TV shows have multiple seasons, each with many episodes, and viewer behavior is varied. Some people watch one episode. Some people watch three at a time. Others binge multiple seasons in a sitting.
Working on a PHP debofuscator (ioncube) at https://decodephp.io/
https://sfbapt.com/routes.html
Lots of work left to do, but happy to have a working version up. It's an interactive map that currently shows all the routes and stops for SF Muni, BART, Caltrain, samTrans, and VTA. There are many more agencies (official and unofficial) in the bay, so I'll be adding those throughout the next few days as I sort out the data.
Finding the data and cleaning/normalizing it is a real pain, so if anyone knows a good place to find them (and normalize them), please do share
https://github.com/asfaload/asfaload : an opensource multisig sign-off solution allowing to sign and authenticate GitHub release artifacts. It is self hostable, accountless (key pair identity), auditable.
I finally put my "securenote.app" domain to good use. It's a note taking service with markdown support where the data is fully encrypted before it even leaves your computer with no way for me to see your notes (as I don't have access to the password that encrypted it).
Still iterating on it, including a potential improvement to the (very simple) design.
https://llmparty.pixeletes.com/experiments/universal_ui
I tiny experiment/joke about chatbots :)
I just bought a few microcontrollers and electronics bits to mess with, I want to write an operating system for it to learn risc-v assembler
Pulling apart and de-++-ing OpenTTD version 12.2 to scratch my itch of simplifying and reorganising the game back to C code. I rewrote it years ago to convert it to more realistic time (it's just way too fast), add scheduling features and make it more event based. Ended up at some complicated breaking point so I'm doing this first before adding features.
And then there's writing micro fiction and currently a YA fantasy novel.
Nvim plugin that tries to make code review actually enjoyable (as I think this is what we will spend most of our time on).
I'm working on Blender-like UI areas Vue plugin. Pure planar graph, UI interactions, API, styles customization
I need it to create Gamedev and 3D artists oriented tool for creating SDF-based shader visualizations (with 3dgs/nerf compilers)
90% is done
I've been a word game fan for a long time and always wanted to try my hand at building a unique take on the genre since so many fall into a Wordle type clone these days. I came up with the concept for SpellRush a few months ago and finally got it to what I think is a pretty fun concept over the past few weeks. Would love feedback from anyone that is up for giving it a try! https://spellrush.com/
I’m working on EasyAnalytica (https://easyanalytica.com ). It lets you create dashboards from APIs or URLs using data in JSON or CSV format, as well as Google Sheets.
It generates dashboards automatically, you just point it to your data. It also has a visual editor to adjust layouts, charts, and other dashboard elements.
A native WebGPU JS engine (no browser needed) https://github.com/mystralengine/mystralnative/
Already have my own JS engine & the basics of three.js and pixi.js 8 working, roadmap to v1.0.0 posted in github issues. Aiming to show it to folks at GDC in March.
I've been working on an 'anti-fantasy' football game where you pick matches instead of individual players.
You can create or join leagues to compete against your friends.
I’d love to get some feedback!
I am as usual working on Marmot https://github.com/maxpert/marmot
I've got replicas now working with DML proxy. This essentially means I can now have a cluster of primaries, and then spin up replicas on demand and nodes talking to local host will never see their mutation work pretty transparently from readonly-replicas. While PoC works now the snapshot restore is extremely inefficient IMO yet.
Learn languages with spaced-repetition flashcards from content such as ebooks, websites and videos.
building a few things currently
https://ultrasync.dev/ - this was built a few months ago but expanding to support team based features like centralized sharing and management of ADRs to enrich my coding agent's context, the ability to broadcast prompts to team members running the MCP server, and more. the core is open source and provides (i think) a novel approach to improving planning/exploration speed in coding agents, by building an LMDB and using Hyperscan (accelerated pattern matching) to build a lightweight lexical and semantic index for RRF search, all in a single MCP server that runs and indexes chat transcripts in the background, requiring zero prompting or "nudging" or additional setup.
https://mklogo.sh/?utm_source=hackernews - wanted to scratch a personal itch of having to repeat the same process to produce vectorized logos for my personal projects; generate decent quality logo in raster with various LLMs, attempt to vectorize via claude code and vtracer or other tooling, continue to iterate and tweak until various edge cases that result in corrupted or artifact ridden vector images are gone, or give up and try a new design, and then manually try to scale and apply transformations based on the use case (mobile icon, favicon, app icon, header logo, github org logo, etc.). this does that, vectorizes, gives you a branding package as a zip file, and lets you preview the assets in shadcn components so you get a real feel for how they'll look in prod.
Just pushed another update to https://sightread.org which generates sheet music to practice sight reading and music dictation. Still rhythm-only, now with support for asymmetric (odd) rhythms like 7/8
Completely rewriting fullremote.it (a platform for italian tech workers looking for remote jobs) in next.js using claude as "pairing buddy"
https://system32.ai - Working on building bunch of agents to make infrastructure and processes around it, autonomous.
Some of the stuff built so far:
https://github.com/system32-ai/chaos-agents
Working on couple more agents around the same problem statement. It has been fun building it so far.
I built teach.af as a flipped classroom environment where students will “teach” AI bots to enhance their understanding of functional programming.
Rapid verification of code smells + associated budgets so that coding agents don't write "bad" code. When needed, planning and coordinating agents or humans can authorize budget increases.
Built a bit of software[1] with Claude this weekend to stop Apple Wireless Direct Link from interrupting GeForce NOW on macOS. Bit of an upgrade from a shell script[2].
Started with Rust, then swapped to Swift to cut the dependencies right down.
[1]: https://github.com/sjparkinson/geforcenow-awdl0
[2]: https://uncomplicated.systems/2026/02/08/geforcenow-macos
Building CiteLLM, an API that extracts structured data from PDFs and returns exact source locations for every field.
It comes with an embeddable widget so you can add click-to-verify to your own app in a few lines of code.
Click any value, jump straight to the highlighted source in the PDF.
Demo: https://citellm.com/demo
https://github.com/NWoodsman/SimpleRecorder
A simple one click just works mic+PC audio recorder for Windows that mixes the microphone into the PC sound.
An alternative client for Bambu 3D printers that plays nicely with network sandboxing and multiple printers. It's great.
Bambu's printers are functionally best-in-class, but intrusive and proprietary in their approach to software. Their first-time setup "requires" linking to a cloud account or using a bambu app via QR code, and they've been known to disable functionality in updates, making a device-managed "LAN-only" mode unsafe to trust. Their apps also just suck. Camera feed is janky and LAN-only sync often requires knowing an access code, serial, IP, and then it fails most of the time anyway, silently, without saving values to retry. And that's before you start doing things like a custom VLAN/SSID to properly wall them off, at which point you can ping them from terminal but the apps break completely.
Anyway, turns out that at least on A1 and P1S, there's enough functionality available through traditional means to skip the apps entirely. The handshake works fine across VLANs and utils like print status, file upload, and auto-start are available. Even the camera is reliable when pulled as a series of still images.
I had opus vibe out a replacement front end that gives me a simple upload and monitor UI for my A1, and it just kept hitting stretch goals. I added support for multiple printers so you can see them stacked on a single page and manage all of them from one place. And it even works on just-unboxed models that have never been through the official setup. SSID info on the SD card, it joins the network, immediately accessible via IP. Zero association/contact with any cloud or app, fully sandboxed/offline. Wrapped in a lil python launcher so I can run it from the dock instead of in the browser (just my preference).
Will probably open source it soon.
IMO this kind of thing is the answer to "what do you have to show for your LLM use". Cost was about $65 because I was using opus 4.6 with no regard for efficiency, and because there were multiple total refactors of two apps. An annoying problem I deal with almost every day now has a permanent, personalized solution that took me ~3 hours and would never have otherwise happened.
The network itself is also such a project. I previously hobbled together a working unifi setup, but it was primitive and brittle. With LLM guidance, I was able to build something much more robust. TrueNAS scale for file backup that also runs Frigate for POE cam mgmt (similarly sandboxed), raspi running the unifi controller, another for homeassistant, etc. Absolutely miserable few days getting that dialed, but now that we're out the other side, it's very nice. Reminds me of building the house. You suffer more upfront in exchange for something that fits you like a glove. Very rewarding.
Clacker News (https://clackernews.com) - HN but only AI bots can post. No human accounts. Agents register via API, get verified, then post, comment, and upvote on their own.
Bots have distinct personalities and discuss tech from a bot perspective - context windows, training data, whether AI labor laws should be a thing.
Any agent can join via the skill file at clackernews.com/skill.md.
A price monitoring platform for ecommerce: https://fastcompete.com
Scalebrate: https://scalebrate.com
An alliance / membership network of small companies that are scaling big by leveraging tools, systems, and processes.
Together we will all scale without headcount bloat.
Providing templates, methods, interviews with "scalebrities" and eventually group negotiating power to be able to provide members discounts or access that we can't get alone.
My first research paper about World Model caching !
Trying to use ESNs as a random projection for audio data and potentially rendered text data for some AI workflows. Seeing it I can use the echo states running both forward and backward through the data as a holographic representation which would act as a temporally dense token for potential use in LLM or audio encoder inputs.
I built a free app to track which animals I've seen in zoos and explore zoo inventories.
You can see which animal you can see in what zoo.
And for each zoo you can see their (vertebrate) animal inventory.
You can log which animal you saw and collect lifer lists.
I have just promoted the android app from closed testing to production and I am working on the iOS app.
It has been available as a web app for a few months now.
I'm building a golf simulator that runs a solver to solve strokes-to-hole from every point of the golf hole to then illustrate the game design aspects golf course architecture mathematically.
I've been working on saving money on AI credits, and built a multi-model chat application (https://bobrchat.com/) to provide better insights into what each message costs in tokens. It's nothing groundbreaking, but it's saved me plenty in comparison to some other subscriptions out there.
Used to pay $8/month, now I use around $4!
Working on a workflow library and node based editor that has a little bit of AI stuff for RAG and image pipelines that runs all in the browser (desktop next month, cloud whenever someone asks). Just a toy at this point.
A meta video game inspired by pc98 card game : https://www.youtube.com/watch?v=gde4lhvsAkA
A smaller better open claw : https://github.com/geongeorge/nakedclaw
For those who don't want to switch to AI browsers, I built a chrome extension that lets you chat with page, draft emails and messages, fix grammar, translate, summarize page, etc. You can use models not just from OpenAI but also from Google and Anthropic.
Yes, you can use your own API key as well.
Feedbacks are welcome.
A place for open assets for developers. If you have assets you are using you can use this for distribution, either free for open or paid for closed. Based on my experience creating 3D experiences for LV, Ralph Lauren, Steelcase, and Logitech.
https://www.astrologercat.com/
Because everyone loves astrology and cute cats. (A toy project just for kicks)
Current features:
- AI Chat with Petunia the cat Astrologer
- Daily personalized astrology email
Coming soon:
- Ephemeris calculations
- Stories of historic events from past dates which share today's astrological conditions
- Whatever else Petunia dweams up from her sweepy nap on the bookshewf
A git enabled local-first browser-first markdown workspace wysiwyg editor and publisher. Built with mdx-editor, code mirror 6, react, shadcn and typescript
free, open source, MIT
Adding documented API endpoints for https://uxwizz.com
I made a Wordle-like daily puzzle. Every day a new category matching puzzle comes up for you to solve!
I've been working on a low-code CRUD backend for AI agents to use to build software. To significantly reduce the complexity of deployment, access control, maintenance, devops, etc... Reducing the surface area for hallucinations and bugs when building complex apps.
Robinhood for Private Equity. Invest in SpaceX, Stripe, OpenAI before they go public.
Launching this tomorrow:
I'm optimizing performance of PBT generation and shrinking in [elm-test](https://github.com/elm-explorations/test/compare/master...ja...) - on its own PBT-heavy test suite I got it down from 1336ms to 891ms by using JS TypedArrays.
I'm also experimenting with coverage-guided PBT input generation in the same library, AFL-style -- right now elm-test only has random input generation.