alt Hacker NewsAsk HN: What are you working on? (November 2026)
What are you working on? What have you been curious about lately?
Comments
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.
Lipik, a free open-source dictation app for Mac (https://github.com/Gourav2609/lipik). Hold fn, talk, let go, and clean text lands in any app: ums and self-corrections removed, spoken punctuation turned into real punctuation. Speech-to-text and clean-up both run on the Mac. On my 106 English test clips, lines that came out fully right went from 28% to 76% with clean-up on. Right now I'm working on Hinglish (Hindi + English in Roman letters). It gets 7 of 20 test lines fully right, so there's a long way to go.
https://khumbu.im - app to study german language (extract highlighted words from paper, generate anki cards etc)
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.
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.
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
https://skymap.rulkens.com A browser based open source universe explorer. I'm in between jobs currently and finally took time to work on my passion project. It started with just visualizing some galaxy surveys, but it got a little out of hand and now includes everything from hi-res tiled earth/mars, Gaia star field (16M stars), a milky way renderer and much more.
It's so amazing to have the ability to gather and parse publicly available scientific data and actually visualize it in real-time. It's one of those projects I'm learning a lot from and can keep going with (the universe is a big place :)). As a software developer for 20+ years, its been mind-blowing and often also frustrating to have Claude generate code that I deem good enough. About half of my time has actually been spent on refactoring, building quite some skills in guiding LLMs in the process. I guess that part still hasn't changed in a growing codebase.
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.
My son is dyslexic. So I built a Chrome text-to-speech and reading tools extension to make it easier for him to get access to written content online (and also to support him at school). It has support for Google Docs and PDFs as well as the web. There are a few of these, but this one tries to stay out of the way, have better tracking, better voices and lower cost. Still more to do on the reading side - writing is next after that.
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...
Euclase: http://euclase.ai - the creative harness for generative AI
Unifying all the various image/video gen (comfyui for local, api for closed) in one cohesive desktop app, with integrated agents to pilot the whole thing (if you want). It's been fun to build and quite fun to use. Technically out in beta and testable, but working on refining onboarding/docs before I try going wider.
Finding a balance between deep enough to satisfy more technical creatives (like me) and less technical ones. Agent integration helps tremendously with the latter.
I am currently on maternity leave with my first baby have just launched to the app store my first app!
I'm a product designer by trade and learnt to vibe code on Claude about a month ago now. I was weaning my baby and he developed a rash and haven't been able to work out what the pattern was causing it. So I created an app for weaning parents to log the food, add any reactions so when talking to their GP they can start to see a pattern and all advice, like nutrients, food variety, how to serve food all coming from the NHS and FSA.
Currently got 12 mums using the app and would love any feedback to make it even better! <3
https://apps.apple.com/gb/app/niblet-weaning-diary/id6822680...
Generate subtitles and dubs for any video, in the actors' own voices
https://github.com/swax/dub-anything
I use it to watch movies that have never been translated to English. A whole world of previously inaccessible media is opened up.
Meli: A spending tracker for Mac designed with privacy in mind. Turns credit card alert emails into spending insights and budgets. I was in security for 15+ years and I built it because I didn't want to use Plaid or other aggregators and wanted my financial data locally on my device and not in the cloud. Spreadsheets required a lot of work to maintain so I wanted some sort of automation. Connects directly to your email (reads only alerts from supported senders) and all parsing happens on your device.
Works with seven major US banks (AMEX, Capital One, Chase, Citi, Discover, Bank of America and Wells Fargo) plus PayPal and Venmo.
Does this list cover most of your spending? If not, which banks or cards would you need?
https://killswitch-lang.org - a programming language designed to be impossible for LLMs to read/edit/write
Few apps I have originally mainly done for myself; Vaava (https://vaava.app) , been tweaking the e2ee data sync between connected apps, and the webrtc based baby monitor feature stability. Crazy how easily Astra / opus 55 level models create quite complex ad-hoc reproducible (almost automatable) test scenarios with 2 phones, laptop and other tools / peripherals they know they can use, for example for the baby monitor feature Astra did a setup for me which i can reproduce to test that the video + audio works fine between 2 phones for x time.
Also trying to replace own Duolingo usage with Fika Lingo (https://fikalingo.com) basic idea was to first repro the practice of matching words. There is now few other types of language / vocabulary practices. The practice generation works on-device with local LLM, you can give the topic yourself like "Words that relate to Hacker News". Downside at the moment is that English needs to be the counterpart of the practices. Cant guarantee good enough quality with something like germany <-> italy practices. I'm trying to do finetuning with LFM models to see if it would be feasible to improve the local practice generation.
I'm working on Eigakan Guide (https://eigakanguide.jp/en), a cinema showtime aggregator for Japan. Every popular cinema site in Japan only allows for very few filters, making it hard to find exactly what I was looking for. So instead I built a site where it's possible to filter by area, cinema, date, time, features like IMAX, English audio, English subtitles, and more. This allows for searching for stuff like IMAX showtimes with English audio on Friday after 7PM.
Since the last time I posted on HN I've added 100s of cinemas, user features like being able to save search filters, movies, and specific showtimes. Also a ChatGPT plugin which allows for searching for movie showtimes using natural language directly inside of ChatGPT (https://chatgpt.com/plugins/plugin_asdk_app_6abfdc298c208191...).
Finally I've added AI search to the site as well, allowing for natural language search with queries like "English audio showtimes near Shinjuku tomorrow" and so on.
I would really appreciate feedback for things to add, things that are hard to understand, and anything else!
I've been working on trying to be more helpful around the house, and trying to spend more time with my kids. I'm trying to give my partner a little bit of relief so that they can pursue their passions as well.
Column view for hacker news with resizable fonts. It’s just a fun hobby thing for me. I’m not in software, but I can do hobby level programming and that gets leveled up by codex.
A desktop app to easily browse, tag, and rate your images. It doesn't touch your files, it just reads them. Everything is stored in a local SQLite database. Think Eagle app but private, offline, and easy to use.
I'm making a replacement motherboard for the Nokia 1100 that runs Linux and supports LTE. I have the software working well on a MangoPi dev board and I've designed two PCBs: one "test fit" board that just breaks out the phone keypad/LCD to pin headers, and the actual board with everything on it. Now I just need to order the PCBA which is super expensive :)
It uses an allwinner T113-S3 SoC and the Quectel EC25 LTE module, and I've made sure voice calling works over LTE, at least on T-Mobile in the US. (this is tricky bc of carrier rules)
video and photos of MangoPi test setup and my board layout here: https://constcast.org/n1100c/
https://petrosprawl.fyi/ An attempt to map oil infrastructure around the world
https://chord-network.vercel.app/ A tool that helps you build chord progressions
Working on ZShot [1]. I'm about a year in on a local-only browser tuned specifically for CLI and API usage - kinda filling the gap for "geez, I sure wish I had a browser, but not one to look at". You need a webpage as PNG, or an MP4, or a website as a WACZ or SQLite database. There's a Mac app to help with discoverability of options, but I wanted for my local tooling and building services on top of it.
Along the way I ended up adding an internal agent framework to satisfy stuff like "log in, click the button, and then take a screenshot", out of which fell stuff like automatically generating Playwright tests from that. It even runs the Playwright test suite and Puppeteer test suites ( a bit faster, and for a lot less memory ). I kinda love this bit because I can layer in multiple models that will bounce control of the web session between each other, to do stuff like let a Typesafe model choose to escalate to Opus when it needs higher minded behavior. It's fun to watch it happen.
I've mentioned it a few times around here, I'll probably do a Show HN soon when I feel like it's ready for that. Hopefully soon.
I'm working on Zustri (https://zustri.com), booking and scheduling for therapists and salons. My girlfriend is a therapist and didn't like any of the booking/scheduling software she tried, so I built her one.
I finished the basics a long while ago. Since then I've added an AI agent, a public booking page, and support for multiple staff. Hopefully, I'm launching soon. Currently finishing final touches, gathering feedback and trying to figure out how to market this
An audiobook player that plays local audiobooks & librivox books. Also has a curated library of audio drama podcasts.
An opensource personal expense tracker, I was a happy user from an offline expense tracker which wiped my data when playstore decided auto-updating it,
I'm at the point where I'm finally actively using it to register my activity, it is straightforward to register tickets by sending them to a telegram bot, then, reconcile those by uploading my bank statement.
I'm trying to get the lowest possible usage friction so that I keep using it.
So far the better built pieces related to the data ingestion. Once this is good enough I'll build reports + anything coming to my head as a useful piece.
I'm leveraging AWS textract + bedrock + bda to parse bank statements. I expected this would have been easier but it is still a very complex problem which had required me to put many iterations (so far it works nicely with my own statements)
For ticket parsing, AWS textract + parsing rules has been enough.
I wrote a bit more on my blog https://alexitc.com/blog/2026-10-16-opensourcing-my-expense-...
RainbowSay https://rainbowsay.ai/
I used to watch K-drama on Netflix and pause it to copy paste subtitles in AI chat to do vocabulary breakdown, translation and grammar. So I automated it in an app which auto pauses video when it detects a sentence and gives translation, vocabulary (for every word) and grammar.
I also added same to voice from microphone, for deliberate practice speaking what was learned. To help with spaced repetition.
For about 10 months or so I've been working on this FOSS hobby project to get more practice at Linux packaging, cargo utilities, and migrating to Nix and NixOS (as well as solve some personal pain points in using a HDMI TVs and projectors with PCs).
https://tisvlay.readthedocs.io/
> TisVlay brings TV Display control for Linux, including: power, volume, backlight, AV mute, input switching plus more, with per-device profile automation via desktop session integration (idle/lock, boot/suspend, remote login/streaming, etc), and in reverse, letting the TV lock, sleep or wake the PC and its remote drive the desktop, while supporting various vendor interface protocols for multi-display setups, mitigating energy usage and OLED panel burn-in or projector bulb burn-out.
Disclosure: this project includes AI assisted coding, documentation and research, and has been a great help given physical disabilities in typing. After programming by hand well over a decade, using voice dictation scene the '90s (IBM ViaVoice or Dragon NaturallySpeaking anyone?), and worsening hands over after my CSE doctorate, this was also a bit of an individual research experiment to explore how effective LLMs could augment my personal approach to spec & test driven development.
While still beta (pre v1.0), its already daily drivable and fully documented. Being largely feature-complete, my current focus has shifted towards distro packaging, and custom ATmega firmware in Rust for HDMI CEC USB adapters to solve a few TV firmware bugs. If you'd like to give it a try, the installation guide and docs are linked below. Or if not, and you already use something else, I'd like to give a shout-out to netflector, especially for privacy-conscious home-automation users, given how common spyware is in smart TVs and projectors these days. The docs cover using it to keep displays on an isolated network.
https://github.com/netflector/netflector
https://tisvlay.readthedocs.io/en/latest/operations/isolated...
https://buzzpot.app — a shared canvas for agents and projects, which I am evolving into a multiplayer environment for teams.
https://leaflo.app — a CBT journal that I am developing into a library of CBT techniques and mini-courses.
https://plainline.app — an AI presentation service with a focus on text and data, rather than visuals.
I try to 'vibe code' a product every 2 weeks. Most of them go unpublished, I just build it for the sake of building it. Most recent project is Unmute Party (https://unmuteparty.com) - multiplayer party games for remote teams, played in the browser during a Zoom or Teams call. The server is EU-only for now, and I plan to add US servers next week. Most of it is free, the paid tiers aren't even working yet. The paid tiers can be unlocked by using code HNWHATAREYOUWORKINGON.
Apart from that, running a travel agency I'd never be able to without agents (they manage my ads, social media, website content etc.). Started with boa.ba and it went quite well, now preparing dobosnia.com
A private, paid, ad-free and personally customizable search engine: Uruky [1]. It was launched earlier this year and reached 400 MAUs and €2k MRR last month.
A simple EU static and app hosting service: PodBy [2]. It was launched last week, and is at €10 MRR.
Thank you for asking and for your suggestions!
[1]: https://uruky.com
[2]: https://podby.com
I'm working on a better way to design longer scrolling pages with multiple sections, while preserving the visual look/feel and drastically speeding up the experience.
Here's a demo: https://non.io/video/linen-demo.mp4
As a disclaimer I cut 32 seconds of generation time out of that video, but still I'm quite happy with the speed. Not launched yet, but it's been fun to work on / wanted to show off progress :)
Writing. I'm going to start an MFA next fall at LSU New Orleans. My latest piece, Three Black and Milds, a night in Juarez. No commentary, no lesson, just the city and the people in it, what it sells and what is bought.
https://www.metanoia-research.com/dispatch-007-three-black-a...
Ive been blogging about learning how LLM services work. Just finished the 2nd part and hoping to do the last part this week. https://matthewtejo.substack.com/p/designing-an-llm-chat-ser...
I am building a tandem, reverse-trike halftrack, using the front end of an ATV and the back end of a snowmobile.
Replacing snowmobile skis with wheels is not a novel idea, but I wanted something which rides more like a motorcycle, with extra length for a passenger and a cargo basket.
It should end up looking like it came out of Mad Max; I plan to cruise around at festivals, running an ad-hoc taxi service, as a way of meeting people and striking up conversations.
I have a service that crunches public filings in the financial sector: https://embarc.com
There is a lot of data for browsing, though it doesn’t aim to solve specific user problems as of yet (I did take a stab with RTOs in the logged in dashboard).
I'm working on 3 products now:
1. FormBeep(https://formbeep.com) at $38 MRR now - A form to Whatsapp tool. Stack is mainly CF workers with Clerk Auth.
2. SlashLink(https://slashlink.app) $0 - A simple pay as you go amazon link localizer. Great for affiliate folks and a cheaper alternative to Genius. Stack is same, CF workers with SQLite(D1)
3. StackStats(https://stackstats.app) $791 - A better advanced analytics app for Substack writers, fully local. I have been writing on Substack for a while now and their analytics suck!
Outside of my day job, I've been working on:
- hermitator, a tool to run multiple isolated AI agents for WhatsApp on a single machine, with idle agents using no RAM: https://www.encona.com/posts/hermitator/
- showntell, which allows your coding agent to explain things to you with a video that starts playing within a few seconds of you asking: https://www.encona.com/posts/showntell/
- a philosophy tutor (testing in private for now) that does 2:1 live philosophy lessons, each exploring a single topic (aimed at ~10yo kids). I've tested this successfully (i.e. two kids did an hour and they want to do it again), and am trying to make improvements.
- some other education-related things
- a jmail-style mailbox viewer: https://www.encona.com/posts/mailbox-viewer/
Audion https://github.com/audion-lang/audion
I needed a code-first approach for making installations and interactive art. MaxMsp gets messy with very big projects. Python didn't really work well for music making and Tidal/Pi/Sclang are only meant for sound. So I needed something that has bpm synchronized threads, but can draw and do anything else like file IO, networking, hardware control etc. It works quite well now.
I'm creating an IDE for founders to run their operations. Create automations (deterministic), dashboards, and soon notification systems. It's a desktop app, and the whole IDE runs in pair with claude/codex through local mcp.
It was developed as an internal tool at my other startup, Ipek helped us to run the whole thing smoother and with all the context I need.
My main projects are still Grasshopper https://addons.mozilla.org/en-US/firefox/addon/grasshopper-u...
And Meltdown https://meltdown.merkoba.com/
Grasshopper is a tab manager for Firefox.
Meltdown is a an AI harness made in python and tkinter.
You can check screenshots of it and descriptions in the link.
Also I've been blogging a lot recently on a weight loss blog. I like asking Kimi for reviews on what I write.
Serverless Wordpress + MariaDB without requiring plugins or any modifications to customer code: https://www.agiler.io
The serverless MariaDB is important because it can scale to zero, so you have dev sites that cost less than $0.50/mo.
Also added MCP and CLI tooling that exposes all of the infrastructure + WP CLI + DB so agents can develop WP sites... which is nice because you can still use the WP admin interface, while using AI to develop the site, debug it, change pages and posts, etc.
Hunting bugs in the Python ecosystem using fuzzers and AI tools I develop. If you have a Python package or extension you'd like analyzed, just let me know.
https://github.com/ReviewToolkits
ColliePWA[1] a mobile interface to continue working with your agents when you're on the. Trying to meet devs where they work on the desktop in multiplexers (herdr/tmux/zellij). Remote access can be set up with any front door like tailscale.
Still not sure where this is going as the space is super crowded and moving fast, but it's solving a lot of my own problems and doesn't rely on third parties to run.
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.
APIKulture. An alternative to Postman/Insomnia/Bruno.
To be honest, I started this because Postman and Insomnia became forced-corporate-cloud not usable for me anymore, and Bruno lacked a feature I considered fundamental for my workflow.
The feature is to remember the JSONPath expressions between requests, a feature that Bruno has implemented already.
But I created this thing and I'm using it daily since then. C++ and wxWidgets, it uses 40MB of RAM, and it is super fast, instead of the 400MB used by the above mentioned programs.
This month I'm working on several projects:
1. Broadcast (https://sendbroadcast.net) - Self hosted email marketing software. Been working on this since 2024 and positive revenue. Releasing v3 this week! :)
2. Render Screenshot (https://renderscreenshot.com) - Screenshot API (very much a scratch my own itch project)
3. Widgetful (https://widgetful.com) - A menubar app for managing multiple Claude Code agent sessions
As a self hoster whos paranoid about backups. I wanted to cheat a bit and use s3. With growing resentment on big tech, who I worked for earlier, I'm now building tools that empower myself and other users and decrease reliance of big tech. Arkel is an object store I've been building and testing for the past few months. https://arkeldata.com
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.