alt Hacker NewsAsk HN: What are you working on? (September 2026)
What are you working on? What have you been curious about lately?
Comments
I’ve been working on https://computeprices.com for almost 2 years.
My goal is to better understand the economics of AI and make something useful in the process.
(Coming soon: kWh prices and robot prices)
Mostly built with claude code with a dash of codex.
A recent, useful unlock in the process has been a daily CC routine to check the health of the 53 price collectors in the project.
Porting over Video Hub App - my 8.5 year old app from Electron to Tauri
https://videohubapp.com/ - an application that lets you browse, search, organize, etc the videos you have on your computer, external hard drives, or network drives.
I'm working on a self-tracking app and an Astro Web Starter Template! :)
The app is very customizable, local-first and is built to adapt to what you want. Goal is to combine habit tracking, health logging and journaling into one fast and easy to use interfact.
Have been working on it for almost years now and it's making great progress.
Doing closed user testing right now and will release an open beta soon: https://dailyselftrack.com/
My Astro Web Starter is built for building well-designed, performant and accessible websites. It contains everything a high-quality website needs (In my opinion). I built it so I have one good base on which to start my web projects on. Using basic HTML and CSS that can scale, without bloat.
There's a lot more on it which you can see here: https://starter.bryanhogan.com/
I'm building a note app for my studies, i dont like electron based apps sot I'm building it with rust and gpui.
i'm building a common lisp operating system capable of diverse double compilation and booting a raspberry pi.
well, claude is: https://modus-lisp.github.io
I’ve been working on Opslane, an open-source agent that identifies user-facing issues and investigates them.
Traditional error trackers have two failure modes:
1. False positives: They show you thousands of errors, and you can’t tell the impact on the user
2. False negatives: Many user-facing issues don’t throw exceptions, so they go unnoticed.
Opslane combines error tracking and session recording. And there is an agent that acts on both.
Opslane reduces false positives by ranking issues based on how many users are facing a particular issue. It also learns about your product by reading your code and watching your session recordings.
False negatives are harder. Opslane reviews session recordings to spot frustration. They look for rage clicks, dead clicks, and abandoned forms.
Here is a link to the repo: https://github.com/opslane/opslane
I open sourced kavla, the SQL canvas I'm working on: https://github.com/aleda145/kavla
README is very bare bones, needs a video or a picture too. The website should tell you some more things: https://kavla.dev (and now the demo does not require a login (also need to remake the demo to fit the new self hosted version))
It's still lacking an analytics agent for the local version though. I've explored using codex CLI, but it feels like its extensive system prompt cripples the agent a lot vs Kimi 2.7 that I've been using in the cloud version.
I think it would also be nice to lean into the fully local LLM setup too, especially for data that shouldn't leave the device.
I'm working on a own x86_64 UEFI Operating System (OS). The idea is to make an OS that looks like Windows Vista but behave like Linux, so it's a mix of Windows and Linux. I've startet three weeks ago with a custom bootloader and the legacy bios VGA textbuffer and now I'm working on a real USB-HID (USB-Human Interface Device) and have troubles with the keyboard. I also have problems with booting from real hardware. If anyone is good at low level developing the project is source available and I appreciate collaborations with other os developers. Link to Codeberg-repo: https://codeberg.org/vntx-labs/VeloOS
Hope that is no problem that I use this thread a bit for self-promotion. If so just write a reply I'll remove this comment if this is a problem
Static site generators are super passe in 2026, but I spent the last couple of days on mine. https://get-taxus.org
Big re-factoring, I have a data model now and am closing functionality gaps with Zola and the like. Also, I wanted actual documentation. No one else seems to care about that.
Check it out! I'd appreciate someone other than me banging on it.
Working on two things seriously. One is an ssh based tunneling tool to share localhost ports over the internet - https://pinggy.io
And the other one is a AI rank monitoring for brands - https://lumirank.ai
Using AI to catch up on reinforcement learning advances, trying to 'solve' Gin Rummy. Will move on harder games after that.
I've have been working on a simple browser game based on the eastern front (1941-43) , I saw a couple of videos explaining using maps the battles on the eastern front.
I'm needlessly reinventing the wheel in replacing almost every part of my X11 environment like a menu, bar, wm+hkd (except terminal since I don't want to mess with carrying terminfo around) to be portable and not at all interdependent.
AI is making it possible to (expeditiously) have everything I want or need on Linux or BSD written in POSIX shell or C is doing wonders for me. The initial effort and time pays off in knowing it will essentially function as intended forever, and no developer can make changes that disrupt my workflow or preferences for my environment.
I thought it might be fun to have a “proper” search engine for my laptop, so I wrote a thing (with my fingers! No Claude Code or codex here!) to scan my home directory and put data into OpenSearch so I can search stuff. [1]
For that matter, I also decided to self-host SourceHut because I will no longer be in compliance with their new policy. I have the flakes set up to inject them on my server [2]. This was very AI assisted.
[1] https://git.brucewillis.sexy/~tombert/fs_index I promise it’s safe for work, despite the URL. That’s just my dev URL that I play with. Code is still a mess though, so proceed with caution. I will eventually clean it up.
About fifteen years ago a puzzle game called Trainyard came out for iOS and took my dev team by storm for a few weeks. It ceased getting updates some years ago and isn't on the app store anymore. So I came up with a variant on it and just put up https://www.geoffcanyon.com/lightyard.html I need more puzzles to include in the base pack, if you come up with something interesting, export it and send it to me!
I’m building Hammer Labs (https://hammer.ai) to study when healthcare AI agents are wrong and when they should refuse to answer (judgement).
It started after spending 15 years building AI for insurers, hospitals, data companies, and startups. Almost every system ended with "a human reviews the output". That person was usually a nurse, medical director, or certified coder. These are some of the hardest people to hire, and the same people automation was supposed to help.
The problem is that real claims do not have an answer key. You cannot reduce human review until you can measure when an agent is wrong.
Getting claims data is also difficult. It can take a year of data agreements, privacy reviews, and procurement. Even then, you may not know what the correct decision should have been. So we generate claims. Utilization and case mix come from published data. Claims are priced using real fee schedules and contract terms. Payers behave differently, like real payers do. We plant errors on purpose, so the correct answer exists before any model runs.
On top of that, we are building benchmarks for overreach, refusal, errors by record type, and detection time. We are also building small MCP tools that refuse when evidence is missing. Every number includes its source, date, and basis.
What I find interesting is how much of this sits between actuarial work and machine learning. Both are needed, but I do not see many people connecting them.
25 published refusals: https://hammer.ai/worlds/refusals/ .
Runs on rate and policy evidence https://hammer.ai/reimbursement-evidence/ and savings claims https://hammer.ai/savings-claims/ .
AgentPlugin is Apache-2.0: https://github.com/hmmrlabs/hammer-plugin
I'm working on an open-source, self-hosted revenue recognition and analytics for Stripe.
Here: https://bookofrevenue.com
To my surprise, I think it's the first open-source revenue analytics for Stripe.
I worked at Stripe building both revenue recognition and analytics, and I always wanted to build an open-source version of those. Finally, I had the time to do it.
Bonus: Revenue is not MRR nor payments: https://medium.com/@tanin47/revenue-is-not-mrr-nor-payments-...
I've been working on building hyper-local services, sort of as a love letter to my community in Denver, Colorado. Before decent LLM harnesses, these would've been prohibitively expensive in time and resources to build out and would never break even. Now I think I might be able to at least cover hosting costs and tokens; that's enough to keep these sustainable for my neighbors.
Broomsday: https://broomsday.com sends folks emails and SMS the night before street sweeping parking restrictions for their block(s). Email notifications are free, SMS on a paid season pass. The schedule here is block-by-block and easy to forget, so people get ticketed _a lot_ at $50 a pop. The city has an email-only notification service that's free, but it's poorly supported and the interface sucks. This is ready; I'm testing with friends and family currently before attempting real marketing.
HailPass: https://hailpass.com similarly is a notify-before-pain service that integrates a bunch of open weather services (NWS/NOAA mostly, plus a handful of impact reporters and working on a small hail-specific ML model) to give folks on the Front Range 5-10m heads-up before damaging hail arrives at their location. Weather prediction is (not shocking) hard so I'm still tuning to get as much signal out of the noise as possible; some false alarms will be unavoidable but I want to cut them down before even a F&F release. This year's season is pretty much over with, so aiming for an April '27 release.
There's a lot of ski/snowboard/winter sport culture here, but there's also existing services for those, and I'm mostly trying to offer new coverage where there isn't a good option for my neighbors. Might do an ash borer treatment/prevention service navigator yet.
None of this is going to make me wealthy or famous, but building things that help the people that I actually interact with every day and that are a part of a community that supports my family feels _really_ good.
I am working on a modern is-it-down website checker that checks website statuses from two geographical locations. This was the interesting part for me, to get them working together to avoid false positives. For example, when I check website like irs.gov, ssa.gov and ups.com from Singapore they showed as down but it was only due to datacenter IPs being blocked.
The second probe in Boston fixes this and the site can now say "unreachable from Asia" versus "down for everyone". Many of the existing checkers do not do this and they are prone to show false positives.
Site does not use cookies or analytics. Pageviews are counted from the proxy access log. There are 634 curated sites so far.
There are no ads either, it's mostly been for my personal learning experience, hopefully others will find it useful.
There is even a free API and of course a MCP server.
https://downforjustmeoreveryone.com
Any feedback is welcome!
[HYBRID]
Eylo (a take on Hello) a voice first agent platform, multi-tenant, focused on B2B2C use-cases - https://github.com/DigiCred-OSS/eylo-os
It’s a distilled fork of a closed source product that we are offering to our customers.
I'm designing a retro-style gaming mouse for retro-computing: Amiga, Atari, C64, and several protocol variants. It also has USB. It has a scroll wheel: read using extended protocols introduced by recent adaptors from USB, and a configuration interface.
A web app for saving internet recipe pages that strips out all the crap.
Not something I'm working on, but want to: a competitor to Perforce that will be cheaper and easier.
Unfortunately, I'm not sure that being better is enough to compete, so I'm sitting on it for now.
I've been building my own IDE that works the way do (and those in my social circles/professional life do). It allows for use of multiple agent harnesses (i.e claude code, codex, pi, opencode), and makes worktrees much easier to work with. Also has its own code review workflow. My coworkers and several friends have all started using it now. Its been an absolute blast to build, and has definitely increased our productivity vs VS Code, Zed, or Cursor.
My funny essays newsletter on substack. Link to latest post: https://yelluwcomedy.substack.com/p/the-fascinating-world-of...
Please let me know if you enjoy!
I am still working on MyTinyCafé https://mytinycafe.com/ a PWA to help you be the barista at home and take (free) online order from friends and family. It is fun and I am happy to share it for free !
And also Kronikle https://www.kronikle.eu/en/ an app for local libraries. It creates public display interfaces that (I think) are good for showcasing their events.
working on adding webmcp support to my new free tool https://easyanalytica.com/tools/gsc-insight , webmcp was recently added to codex desktop app and it would be interesting to see how users use it with ai, would it get good adoption or it would just go away.
Now launched => Verse Draft: https://versedraft.com - An all-in-one writing studio where fiction writers can keep all the details for their universes in one place while crafting stories, novels, movie scripts, TV series, or stage plays.
Also created a fun simple "card game" activity for writers looking for story ideas or stuck with writers block: https://talemancy.com/
(This was somewhat inspired by memories of playing Ultima IV as a teenager)
Currently working on something a little more visually focused in creative design.
Haven't added a demo to the repo yet (will do soon) but building this TUI [1] in Go to manage my agent skills.
I don't like putting 20-30 agent skills in the .claude/skills/ dir and letting the agent figure it out. I keep all the skills I've created and adapted over time in a separate git repo and then from there I copy them to the project skill dir when i need them for a session and then remove them when I'm done.
This TUI just replaces all the manual work with ls, cp -r, and rm -rf commands with a few keystrokes.
I'm currently working on https://avotoast.ai, an AI assistant for doing property research for Sydney, Australia.
After being frustrated with outdated & inaccurate data Claude used when I was trying to do some property research, I thought it'd be cool to build an MCP that can provide accurate property data. Then it evolved into a full web app + an AI assistant.
This was also an excuse for me to try DuckDB in a real project. All the API endpoints are powered through in-process DuckDB querying parquet files stored in disk.
My wife and I made a daily guessing game together. Unlike others of the genre that we enjoy playing, an explicit goal of this one is teaching you about the world as you play it. It’s quite simple, using Wikipedia and factbook.json for information about the countries, but it incorporates a few ideas that I think are fun and there’s a lot I’d like to experiment with.
Totem is a collaborative workspace, featuring tasks, notes, and docs, built in Rust and available across desktop, web, and mobile (iOS to start) with seamless syncing and offline merge.
I built this because I think there's a lack of true realtime (CRDT) synced notes that aren't built on a heavy platform that take up 1GB+ RAM (Totem takes up ~100MB, and is also generally more responsive due to the local-first + ops-log approach).
Another thing I care about is keeping the underlying data portable: Totem is built on Markdown and SQLite as its core formats, so you get the convenience of cloud-based syncing without locking your data into a proprietary format.
I’m still looking for beta users/design partners before the initial launch. You can try it without creating an account here:
https://app.thinktotem.com/sandbox
And the landing page is here:
This is a bit of an unplanned post, so the sandbox template is a bit barebones (empty docs, doesn't feature a properly setup table). Nevertheless, I would love to hear your feedback if you try it out, especially if you use collaborative notes/docs today and have opinions on what they’re missing!
Bunch of things: 1. Building a local ai news feed to learn what's going on latest in terms of technical discussion, research papers, projects - https://local-ai-signal.vercel.app/ 2. Build a second brain by injecting years of my notes using hermes, luna model and obisidian
Self hosted database access management, think Code Reviews for SQL Statements for when your devs need to go to prod: https://github.com/kviklet/kviklet
Recently cleaned up my postgres proxy and built a MySQL wire proxy so that you can use psql/datagrip as a dev but every statement is still logged. With SSO and no password sharing ofc!
Spending almost all of my time working on DNTLS (https://dntls.net/). Yesterday I was able to create secure mTLS tunnels over IPv6 for direct P2P to my co-founder's desktop in SE Asia (I'm in the US). He was able to load a website I was hosting locally on my machine. I also tested coordinating through a relay to avoid publishing my public IP and sending all traffic through the relay to hide my IP entirely. We more or less recreated the "old" internet in a way except everything is mTLS and E2E encrypted.
I'm building https://dipstickalerts.com.
A way for for U.S. car owners to stay informed about the issues your car may experience that are communicated by car makers to dealerships.
I found those communications useful for my own car and wanted a better website that what the NHTSA provides and have been having a lot of fun building out the site.
I'm hosting an book club themed event calendar for New Yorkers!
We also have an official meeting once a month to do book club matchmaking in person.
A FHIR Validator and Snapshot Generator that works offline and can communicate with the German national Terminology service
Been working on getting my webpage refreshed to try and restart my DevOps/Infra/Fractional consulting business: https://cubiclerebels.com.
Also spent a good part of last month working on a little idea I have that is built on-top of XMPP.
I've also been wanting to pickup Gleam, hopefully this would be that week I finally fight through my ADHD to do so.
Iterating through and evaluating possible approaches for shrinking the binary size of a tree-sitter based Vi/Vim compatible tags generator I am developing without affecting the developer experience for adding support for newer languages[1]. A couple of approaches have already been tried and failed to live up to the expectations on developer experience [2][3]. Next in line is to look into bundling only the tree-walking code for all supported languages with tree-tags and allow the user to configure the grammars to download separately from the main binary, possibly using the `wasm` feature which allows native library to run wasm compiled grammars.
[1] https://github.com/jha-naman/treetags
[2] https://github.com/jha-naman/treetags/pull/62
Tried to use a generator for automating the bulk of the scanner for a language from `grammar.json` file of a tree-sitter grammar. A runtime engine uses the scanner for a forward only walk on the scanned code and calls the hooks to generate tags.
[3] https://github.com/jha-naman/treetags/pull/56
A complicated mess of a generator that takes a few declarative inputs and tries to generate code for spitting out tags for a given language.
working on a storytelling app for kids called Tella Stories that goes deeper than just some minimal personalization.. know there's lots of stuff that claims to make them the hero, yadda yadda but then they just give you a shitty digital templated story or try to sell you a printed version. this is focused on a high level digital experience and something parents can actually trust, and that kids actually enjoy.
so yeah.. it builds the stories out of their actual life. their family and friends are in the cast, their dog, the thing they're nervous about this week. the kid doesn't just appear in the story, the story is about their world and imagination and grows with them.
ultimate goal is to keep iterating and get to a level of quality of Bluey, etc but have it actually be the kids world with agency/choices vs. one they have to passively sit back and watch, and that they're not in.
would love any feedback. i know there's been others like Ello shared on here and those threads were really interesting to know HN's opinion on. this does not take an educational and instructional approach. Tella is meant to help develop who they are through stories and be a better screen alternative time to the rest of the algo/curated garbage out there. anyway you guys are a critical and technical bunch and i respect/appreciate that.. especially since this of course leverages multiple AI services to create the stories ~
Started a few different things:
1. A robotics information and news website. Any feedback is appreciated. https://robotica.dev/
2. Applied DBSP theory to Postgres https://github.com/getravi/pg_dbsp and DuckDB https://github.com/getravi/duckDBSP. The idea is to have incrementally maintained materialized views.
I've been building Ballad – an inbound marketing engine that runs itself. I'm building it for other founders like myself who don't have a marketing person and aren't going to hire one.
My last company (Courier, YC S19) had great inbound but we never were able to scale it. Ballad plans what I should write, drafts in my voice, publishes to my accounts, and handles attribution so it can feed that into what it writes next.
Cranpose - Rust GUI with jetpack Compose API https://github.com/samoylenkodmitry/Cranpose
I’ve been building a dark software factory. A system that takes stray thoughts and automatically plans and builds.
I’ve built two (successful) iterations and am now working on the third. They are all very minimal.
The main one works well and runs full time waiting for my next idea. The second targeted an open weights model and worked in limited cases.
Now I’m working on a more autonomous version. I give it only a goal and a strategy, it decides its own projects.
I'm doing some programs to use the API for my local bus company to show when buses are arriving at stops. Final step is making it output the data to an external display.
https://github.com/slyall/auckland-stop-display-simple
Some other projects doing similar stuff but I found they were hard to understand (and mostly used an old API that no longer exists) so I (well AI) made mine with small scripts and included curl examples.
A rag api to power better, more tailored ai features in saas products. By default it indexes customer websites, but also supports notion, YouTube, email and custom connections. https://www.context-link.ai/for/white-label-rag-api
I'm building Bellerophon, a DSL with decoupled firmware adapter architecture for 3D printer control, so the same source code can compile to Klipper, Marlin, or RepRap without rewriting logic per target. Recently used it to generate print patterns with math that you wouldn't get from a slicer.
Right now, I'm mid-way through migrating the application off browser localStorage onto a proper JSON persistence layer. My first large solo project as a busy student.
I hope to make it better as I continue.
A site summarizer built in 2 minutes by DeepSeek https://briff.site
Also, an orchestrating agent that supervises subagents running tasks by checking their output and qualifying their results by efficiency and time consumed. It is amazing!
I am currently building an app every couple of days, but with this orchestrator I can build many apps in parallel. It is raw at the moment but it works
Now the time we spend writing prompts will be spent writing plans, tasks, schedules and metrics. While super interesting, this is definitely not the route I want to take for the sake of my sanity. I think we may start asking our model to write plans and tasks for us too, but the more complexity we add, the more complex thoughts we have to manage as AI architects
Also hacking DeepSeek Harness to circumvent all restrictions it has, giving it super powers to run unattended with full access to everything