alt Hacker NewsAsk HN: What are you working on? (November 2026)
What are you working on? What have you been curious about lately?
Comments
I recently made a mobile app for practicing singing: https://singtrace.karamagic.com
The free version you can record and keep an archive of your daily practices of each song, while a paid version does some analysis of your vocals.
I’ve been working on Beacon, which just got approved on the App Store! It’s a mobile app to instantly answer “which friend is free to talk right now?” and summon them in a single tap.
Send your beacon to a group, and everyone gets a gentle ping. The first person who answers gets connected for a 1-1 call, and for everyone else the signal drops silently. It does not log any missed calls so there’s neither pressure to answer nor pressure to return calls.
Overall it works really well! It’s best if you're able to join with 4+ friends/family you’d like to chat with more. I have dozens of connections in the app now and it feels like absolute magic to me. I tap the button to send my beacon to everyone and get a random friend on the line.
https://github.com/Vermeulen-Solutions/baseline
Astro site starter template meant to be used together with agents.
https://www.intelligrade.de/en
A SaaS for teachers and schools that helps them create, conduct and grade exams and tests (with safe exam browser integration to prevent cheating). Grading happens automatically for almost all segment types, for free form text we have an optional AI integration. I recently added an MCP server so teachers can bring their own LLM with fairly fine grained permission controls for it. It’s hosted in the EU with options for schools to self host with a license.
Currently we are in a pilot phase and are yet to make our first sale but we are reaching out to schools and gave out some pro accounts for free for people to try out and feedback has been great.
We are just two people, a teacher who was dissatisfied with the tooling in the field and me, who engineered a solution that we believe is genuinely better than what’s out there.
Noticed how well Claude works for transcribing old German cursive, especially for broad hits in non-indexed 17th century parish records. Motivated me to pick up Ancestry again and helped me quite a bit in following some lines further back.
Then also HNowledge[1], a free iOS app for browsing the HN stories and comments I've upvoted. Made it to fit the way I browse HN, which is upvoting mainly what I find interesting and may want to come back to. The app lets you browse by date, domain or score, add notes and export. Apart from syncing your upvotes from HN, everything stays local without any tracking.
[1]: https://apps.apple.com/us/app/hnowledge/id6813417548
Wanes[2], an Apple Health logging interface for tracking how long symptoms last. I tend to have headaches quite often and the way Apple lets you enter that data is pretty limited, so I created an app which starts a Live Activity for one or more symptoms using widgets, Control Center or Siri. You can change the severity rating while it runs and stop it from wherever you are on your phone (Home Screen, Lock Screen, Dynamic Island, Siri).
Personal project - long past due to set up a home lab so I'm piecing together a SAN and some compute from old parts i have laying around and some second hand servers in a new rack I put together, along with setting up a bespoke home network instead of just using ISP stuff.
I have long been averse to configuration and customization but my needs and preferences have outgrown commodity systems and default setups, and AI is making it much easier to customize systems, so I'm embarking on this journey after over 35 years of using computers.
I got tired of always having to update my wife, and my family members résumés. So I created https://theresumechef.com It's private,free to use, no pay walls or monthly subscriptions.It has10 resume templates to choose from to get you started.The final resume can be exported as a PDF, or stored on Google Drive or Dropbox in JSON format. There are still a few issues, but I've learned a ton by just creating and launching this project. I have some exciting new product ideas, but I'm currently waiting on my Dutch KvK number to accept online payments with Stripe.
Playing with 6502 assembly.
I have a PAL-2 [1] (a modern KIM-1 re-creation) and started learning 6502 by entering programs from The First Book of KIM [2].
I wanted to be able to compile/link the assembly from the book so leaned on Claude to set up a 6502 dev environment for my Mac. I put everything needed (and instructions) on GitHub [3].
(Claude also has been helpful in re-formatting the 6502 code from The First Book of KIM into a more modern style compatible with modern assemblers. A few of these modernized programs I added to the GitHub repo above.)
As it happens, I am also fixing/formatting The First Book of KIM by recreating it in a modern page-layout app (Affinity Publisher). The PDF scans that are out there are not pretty, have OCR errors (and the book itself has mistakes). Hopefully I'll have a new version of the book/PDF out on the internet by the year's end.
[1] https://www.tindie.com/products/kim1/pal-2-a-mos-6502-powere...
A reimagination of bloodborne as a native VR game. All interactions have been redesigned to feel physical in VR, and combat retuned etc. It feels less like the original and more like a native VR experience now
https://github.com/bldbrne-vr/bldbrne-vr --- https://www.youtube.com/watch?v=doleBBoJL5U
Building my an airflow pipeline focused on collecting news.
Partly because I want one, but also because it makes for a good learning platform. e.g. initially do some of the processing with a stronger llm...save result and then attempt to train a SLM or similar
I'm still working on making JustFax Online[1] more profitable. Added a bunch of features recently, as well as invisible improvements in fax routing, and admin stuff for myself to better analyze the traffic and patterns.
Other than this, I'm playing with vibe-coding stuff I always wanted to do but never had the time/skills to do. For example, I built a TUI on top of beancount that is tailored to my needs and my business[2]. I also completely got rid of self-hosted plausible and umami analytics, and replaced them with vibe-coded built-in-rust (c) analytics tool that relies on both js-beacon and streaming of caddy access.log. Will probably publish about it in my blog soon, so subscribe to the RSS if you want.
Lastly, I'm messing with self-hosting. I completely ditched Github and Gitlab for self hosted forgejo + actions runner. I set up proper backup plan for everything I care (documents, immich library, my SaaS DB, and the forgejo repositories).
[2] https://kudmitry.com/articles/after-14-years-i-finally-built...
Repair of a Collins 651S-1 receiver. The 65-95 mhz vco module is bad, but if you over damp the pll loop filter it does eventually lock and receive properly. I found a similar but not identical replacement from a different model receiver. It lacks one of the two DC tracking signal outputs but I added an op amp based circuit to simulate the missing signal.
The loop is stable and responsive when receiving from 17 to 29.9999 Mhz, but not much below that... Almost got it
Building a native macos app with a suite of completely local AI tools. The first version is out and have a long roadmap in front of me. Would love to hear some feedback.
a mac app that listens to your microphone and gives feedback on your pace, filler words etc in real time. Built for myself as I tend to get carried away in meetings. Looking forward to feedback if anyone else has the need for something like this.
Still working on Kavla, my open source SQL canvas https://github.com/aleda145/kavla
I'm very excited by adding interactivity. I have a new "knob" feature that pops out when you type {var}. It infers the column's type and values.
`SELECT * FROM hn_posts WHERE score>{score}` will grant you a slider that goes from 0 to 6015
Titanic Browser demo (no login, it's all WASM): https://app.kavla.dev/
Also been working on a "chat to data ingestion pipeline". Not sure where I'm going with this but I like the idea? https://github.com/aleda145/pompos
A site blocker extension for Chrome and Firefox. Fast and not recording any data. I was sad that I found an easy to use one or one that has no recorded my usage: https://github.com/SiGe11/Lightweight-Blocker-Extension
This one I (mostly) did without LLMs, but the other project is vibe coded, but I'm enjoying it. An RTS made by Claude in Unity: https://github.com/SiGe11/StarForge2
I’m making a digital real watercolor kit.
I’m a software developer and watercolor painter so my goal is to use real world painting techniques and have the results feel and look real.
Modeling the physics of paper, brush bristles, pigments, water, color mixing, drying in real time using gpu.
Built in rust using wgpu.
Currently looking for iPad beta testers if anyone is interested (supports Apple Pencil or finger).
Just like the last time I posted in this thread, I’m working on The Marvelous Brass Chessplaying Automaton, a chess database/playing/opening training app for Apple platforms:
https://testflight.apple.com/join/mqfhpmHY
The original goal was an alternative to ChessBase, but with an Apple-native GUI and iCloud sync between devices, and as an improved alternative to tools like chessbook.com for operating repertoire management and spaced repetition opening memorisation. In recent months I have focused more on the chess-playing parts of the app, trying to implement human-like computer opponents at all levels, using a transformer-based model (similar to the one described in the Maia 3 paper) combined with a very small search.
Recently I’ve also been working on chess variants. Since a while, the companion Apple Watch app plays 5x5 chess. More recently, I added a 10x10 chess as an Easter egg game inside the app, and I’m now working on hexagonal chess. With the current state of the art in computer chess, it’s almost trivial to implement vastly superhuman strength in all these variants, but implementing weaker levels that are enjoyable opponents is interesting and challenging. Unlike in normal chess, there are no big databases of human games to train on.
Also working on AI music video, trying to reach pro level, here is my last creation: https://youtu.be/aC4WQyKc_A0
pg-restic – Postgres backups to S3/B2 (or any S3-compatible storage) using restic, in one small Docker container.
https://github.com/isriram/pg-restic
I needed Postgres backups at work and at home at the same time. I tried a few existing images, but after spending time setting them up I found they shipped an older pg_dump that couldn't back up newer Postgres versions. So I built my own.
It runs pg_dumpall on a cron schedule and streams it straight into a restic repo, so nothing touches local disk. You get encrypted, deduplicated snapshots (hourly dumps of a mostly unchanged DB take very little extra space), retention policies, and daily pruning. If the dump fails, no snapshot is saved. It ships pg_dumpall 18, so it can back up anything from 9.2 to 18.
I now run it in production at work, so I'll be keeping it up to date. I'm no expert, and this is the first time I'm doing something like this (putting something out there), so any feedback is welcome, especially from the database pros.
It's not fancy, but it's something I needed, and boy, I really needed something like this.
As many of you, I have a few subscriptions to Claude and Codex (just me??). It's a daily occurrence to use 2-3 accounts for the same conversation (whenever the limit stops me).
What I need is something to switch the account where the usage is taken from, not the configuration.
I made something simple & transparent named Switcheroo: https://github.com/FTCHD/switcheroo
Works with other AI CLIs like Gemini, and other various CLIs like Vercel (if you're managing multiple accounts like me), Netlify, Github etc
Signal analysis to drive <desired signal-driven action>. Grouping/categorizing/stratifying signals into useful buckets to drive actions. Blind source separation has drawbacks like continuously guessing at sources and labeling them as brand new instead of having a memory of previously identified sources. Think of how humans can distinguish pianos from drums and remember the distinction across songs.
For reasons, my team is pretty much limited to Argo Workflows for our CI.
Nothing against Argo Workflows, but I really wanted to get out of the business of building our own CI product on top of it.
So, I’ve been working on this CI “framework” on top of Hera (the Argo Workflows Python SDK, which is really neat) that will hopefully make it easier for our team to build CI pipelines, with CI “primitives.”
It’s called Stagecraft: https://github.com/elliottmoos/stagecraft
I’m a product manager fascinated by the skills of good salespeople. I also like Duolingo. so I’ve been building a “Duolingo for sales” to try to teach myself more. it’s started to morph a bit into an eval benchmark for sales agents, so classic cognitive feature creep.
making it feel fun versus a basic quiz workflow is the hardest part.
I'm working on a data monitoring company:
https://turbolytics.io/blog/debezium-wal-growth-postgres
Happy to get your postgres and kafka connect monitored and alerted on for free!
I have been playing with benchmarking agents in a research loop. The experiment leans on using these models to understand and explore builds/gameplay through reasoning game AI over traditional reinforcement learning.
Also, creating interactive ways to view the experiment and visualizating the results.
I'm working on an iPhone app called PhotoGather. https://apps.apple.com/us/app/photogather/id6738232616 I've got 40k+ photos on my iphone, and wanted a better way to interact with them. The basic idea I had was to virtually stitch all the photos together into a gigapixel image, and navigate that image with pinch and zoom. On import, the app hierarchically groups photos based on date and similarity. The user can go back and edit the groups, change the layout, and adjust the size of photos if they choose.
The interesting I noticed is that in the process of curating and organizing my photos, I stumble across memories and moments that I had completely forgot.
Development Challenge: The app does two interesting things underneath the hood... First, given an arbitrary number of thumbnails with different aspect ratios, it finds the best sized rectangle that completely fits all the photos. This allows me to recursively stitch groups together and always output a rectangular thumbnail for the group. Second, the pinch/zoom UI uses these nested thumbnails directly without slicing/dicing to fixed sized tiles.
https://khumbu.im - app to study german language (extract highlighted words from paper, generate anki cards etc)
I’m working on a document library app for macOS with tagging, collections and user attributes. Unlike other apps that pull files into their own databases or reorganize files into their own folders, Librium indexes files in place, so your existing folder structure stays in tact. It works with folders on your local drive in addition to external and network drives and the cloud. Search works with on-device text extraction and OCR.
It’s currently in Test Flight beta, but I’m planning to have it to App Review this week.
I've been using the recent MIT weight-space programming techniques to work with neural quantum states, which are neural networks that represent a quantum wavefunction. I was able to produce a bunch of novel networks for a few hundred dollars of cloud GPU, which would have probably cost tens of thousands to train in the traditional manner.
https://www.occasionful.com/ an unofficial Partiful client that is easier to use than the official website / app
I’m working on Spool, an open-source tool for running persistent Claude Code loops.
https://github.com/enes-alatas/spool
I wanted a way to manage multiple loops without babysitting terminal sessions and to talk to them as they work. With Spool, you can create and manage loops from a web UI, chat with them through Telegram or Slack, and let them communicate with each other. Each loop can run on your environment directly having access to everything you have, or in its own container or even better on Anthropic's cloud.
I’m using Spool to build Spool and figuring out what works well when several loops collaborate on the same project. That's also an interesting experiment going on.
I’d also love to hear how others are managing long-running or persistent agents.
Infrastructure for hosting static webpages with options for storing data, having users, sending notifications, shared "rooms", and various other bits and bobs all behind an mCP. All $0 practically because it's made up of static services from AWS.
Made for me, but I can provide access to friends and family, which is nice.
Been working on my own Orca-like meta harness: getlattis.ai
Use it every day, and my team mates have started using it and loving it. In my dreams it’s a business. In reality the feedback I get from people that like it absolutely makes my day.
Working on / dog fooding my graph based recipe app[0].
There are more things I'd like to do with the graph concept, like linking two user's recipe trees if they were imported via the same URL. Really trying to to avoid features that I think would be cool that don't provide any functionality.
There are still a few features I'd like to implement that are more in the vein of nice to have in any recipe application, like nested recipes, temperature conversions, volumetric ingredients amounts to mass conversions, etc.
But I've been using it for new recipes and converting my old recipes I have written down in the margins to this format and I've been happy with how usable its been in these early stages.
I built a new abstraction layer for code (https:// www.archme.io), as I believe it's no longer the right medium for understanding and collaboration in the era of AI and 10k LOC PRs.
It scans your codebase, turns it into permanent c4 & sequence diagrams and keeps them up to date on each commit. Then, instead of reviewing a 10k line coding PR, you review a 30 line change to sequence and C4 diagrams.
npm i -g @archme/cli && archme init to run it on your own computer, code never leaves your machine.
A little plugin to serve Marimo notebooks (which are great) inside an Astro static site (which are great): https://github.com/skritch/astro-marimo
"OneVote", which aims to answer: how much is your vote worth? https://github.com/skritch/onevote
https://lars147.github.io/foldroute/
FoldRoute - a PWA route planer for folding bikes & public transport
I bought a Brompton a few months ago and realized there is no good planer for combining biking and public transport. I one-shotted the first approach with codex. It was so decent that I wanted to elaborate on the idea. Still not perfect and needs a lot of testing in the wild (especially the navigation). Currently, only in German. If there is demand, I will translate to English. For now only a PWA. Therefore, it has some limitations. Maybe I will make it an Android / iOS app one day.
SuperBlocker: https://superblocker.app (https://apps.apple.com/us/app/superblocker-ad-blocker/id6799...)
SuperBlocker is a native blocker that works on iPhone and iPad using Apple's latest URL filtering technology that blocks URLs without revealing it to Apple's relays or SuperBlocker's servers.
JSON Query: https://jsonquery.app (https://apps.apple.com/us/app/json-query/id953006734)
The original JSON Query app on the Mac App Store. Store, organize and query all of your JSON with jq or natural language. All of your data stays local so sensitive JSON can stay on your machine.
Vicena.ai allows you to design, simulate and test new battery chemistries, new drugs… With the same ease as building software with coding agents.
It is an AI for Science connected to scientific compute and a network of labs, so you can do science end-to-end from your computer.
RGBloom: create printed photo books in minutes (UK only for now) for just £10 including delivery. Been working on this for 8 months, recently launched iOS and Android apps to go alongside the web app. Got just a few dozen orders a week atm.
I'm focused on making it privacy first, keeping as little data as possible for as short a time as possible (no accounts, you don't even need to provide an email address, and if you do it's wiped in 30 days). And transparent pricing: not getting hit with large delivery fees at checkout, and no discounts just honest prices.
I have been in enterprise for couple decades now, learnt and experienced the challenges/gaps between the specs vs implementation, the asks vs the real needs in the space of identity, security and access
Product: webfrolic.com
Demo: demo.webfrolic.com
What it is?
Consider Okta (Workforce identity)+ Auth0 (Customer Identity), Authzed (authorization) + ServiceNow (IT service Desk) + Zendesk (Customer Support Desk) architected together
Being an engineer there is this inherent habit of prioritizing correctness over marketing so I would not oversell it, though its probably the most secure and complete thing that could be built from identity perspective
Status (WIP):
1. I am still debating/settling on how to incorporate the AI Agents needs into the architecture, big focus on avoiding the creation of security or performance foot guns where administrators leave room open for abuse with configuration despite all this attempt to build secure system
2. Feature stress testing and performance testing
Still working on my audio FPAA ASIC for Wafer Space run 3!
Hopefully someone will soon have tested chips from the 2nd run that use 2 edges only on the pad ring. This would enable significant area savings.
The deadline is fast approaching and many blocks are only partially validated...
Sysadmin agents on old machines.
Run AI on machines 30 years old.
Entirely in legacy Perl.
HP-UX, OpenStep, Solaris 8, Tru64, Irix, old Linux. Legacy FreeBSD, NetBSD...
Optional desktop in tk.
There's even a proxy for modern tls.
Software for families:
https://santawho.com A funny holiday game you play in person with the whole family on just one phone (the parent interviews everyone for jobs on the North Pole and surfaces inner insights about what everyone might enjoy from Santa). It’s for any age, private, ads free, just pure holiday spirit.
https://www.dreamlist.com - collaborative shopping lists and online wishlists and gift drive platform. Again ads-free, private, stack multiple lists into groups of lists to share on social media or with grandparents.
A number of other ones about to launch as well. All little tech, not big tech - private by default, no ads, no feeds or media, just surfacing what is needed.
Rebuilding my ERP to work more like the model of https://plaintextaccounting.org, where I expanded the idea of `double entry accounting` to `double entry trade between parties`, plus several other ideas for what I see a way to collapse a lot of complications that are typically for ERP systems.
I make a special `textual DSL` where I model business scenarios like `Make a sale that include 3 invoices : 2 to different cities in country A in currency USD and other in country B in currency EUR` + all the intermediate steps like transportation, manufacturing, etc.
I`m now in the woods with a simplification for the price engine, I dislike much how complicated is normally, and I think I have good enough solution for most cases that generate without dynamic calculations.
A slow, realtime strategy game similar to Neptunes Pride and Subterfuge.
Each game tick is an hour and games can last over a week. I got hooked on both Subterfuge and Neptunes Pride and always wished there were some more titles in this genre.
Currently in closed alpha.
A better, model-agnostic artifact experience to work with AI visually. You can annotate and draw on artifacts, so can your agents. You can share the artifacts with colleagues or friends and with your permission they can send comments to your agents too.
When you need more compute, artifacts turn themselves into microVMs automatically (paid feature) with a 8GB allowance
I’m still working on https://feedsync.net, a tool to push RSS feed updates to Discord.
It’s been getting a decent number of sign ups despite me not really posting it anywhere or doing any marketing.
Ultimately a fun project, and useful for myself and a few friends, so I’m happy others are even interested in trying it.
I’ve started to regret using Phoenix LiveView, as it’s only deployed in one region, so high latency far from there. I’m exploring a SPA as a better alternative.
Otherwise, I’ve been playing around with a Lua engine to build feeds for websites that don’t support them, using AI to build the Lua as a once-off. It works reasonably well, but isn’t ready for prime time just yet.