alt Hacker NewsAsk HN: What are you working on? (August 2026)
What are you working on? What have you been curious about lately?
Comments
https://corvi.careers/reports/technology-stack-trends/
It tracks explicit mentions of ~ 181 languages, technologies, vendors, etc as seen in job postings. The motivation was that GitHub activity and developer surveys describe what people use or enjoy, but not necessarily what employers are requesting.
I'm adding MoE support to the GPT-2 code from Sebastian Raschka's "Build a Large Language Model (From Scratch)". Just the minimal changes. Planning to do (or at least start!) a from-scratch base model training run on my own hardware before the end of the month.
I'm updating Metabase's Podman documentation to reflect using Quadlet instead of "the old way." It's my first open source contribution in quite awhile and while it's tiny I'm excited for it. It's a chance to get to know pi.dev, not to write, but to behave as a copy editor and fact checker. Since it uses Mistral on the back-end it's a slightly insane copy editor and fact checker, but that's almost better. It's forcing me to check everything I say.
I've always ran into an issue running arbitrary processes - whether it be for serious production work, or just toy scripts. So many choices with so many dependencies, featuring so many foot-guns. So I decided to take a stab at solving the problem. Would love any feedback or contributors :)
SystemG - An agent-friendly general process composer.
I have two personal projects at the moment.
First, https://agency.nu/ a personal agent platform for people who aren’t necessarily developers, but still want to connect multiple Gmail, Calendar, and other accounts and automate workflows across them. Spent a lot of time making the interaction easy and natural, so it supports chat, realtime voice and telegram.
Second, https://vinarium.one/ something I primarily built for myself to keep track of the wines in my wine fridge, when to drink them, and what pairs well with a particular dish.
Both are very much scratching my own itch, but I’m curious if either resonates with anyone else here.
https://github.com/backnotprop/plannotator is still very useful for annotating html prototypes and markdown plans (as well as terminal agent messages). Was glad to see codex team pick up the feature requests in the Codex App.
About to release a fun paid version. All contributors get lifetime free access.
Better running agents run longer, they need better plans. (is my bet)
I’ve been playing around with exploiting LLMs having ‘read’ every book ever written to make a chatbot to help people choose library books. You talk to it a bit about things you’ve read, and it uses the llm’s latent knowledge of books to suggest ones you might like.
It’s pretty fun! It might even work on your local library (I got carried away and spent a while making it work on a few thousand round the world - you can see the coverage here: https://leafle.nanosheep.net/coverage).
A music recommender website oriented towards albums.
Tell it your 5 favorite albums, get an immediate suggestions list. No sign up, free to use, integrated with Spotify to hear immediate samples (or the whole album).
Waiting for the remaining broadcast equipment for my LPFM (www.kpbj.fm) to arrive! Then we finally get on the broadcast band. We have over 80 shows at this point. We still need fundraising support. If you are in Los Angeles and want to support freeform community please reach out.
I've been working on a simple multiplayer word game: http://alphabetsoup.club
It's a bit like NYT Spelling Bee, except it's multiplayer and only your best (longest) word counts toward your score. So, instead of trying to find as many words as possible, the game is more about finding one unusually good word.
Funny timing, I just made my first Show HN post for this a few minutes ago: https://news.ycombinator.com/item?id=49235347
I’m working on “nah” [1] an agent hook guard that blocks catastrophic agent actions like filesystem destruction, secrets exfiltration, and git disasters.
All the agent hook guards I’ve seen can be easily removed by agents (and they often do so they can get going with the task). I made mine harder to remove, and I’m working on making it impossible.
I also made “nah” easily extensible. Just point your agent to the docs which ship with the CLI, and ask it to build a custom guard.
I’m working on strong Python and Typescript pseudo-interpreters so I can detect disasters in inline code with less false positives. Bash parser is already very strong.
This is a side-project that I want to be proud off. I spend a lot of time designing, not just coding.
[1] nahguard.ai
So I am working on building a low latency streaming dataflow framework - ala gnuradio but actually usable in production. The idea is to have deterministic latency as a first class objective and let all the other benefits fall out of that.
Additionally:
Live graph reconfiguration Timed events Easy simd support Support for non-mmu based architectures Imperitive configuration management and querying at the single runtime level. Can be compiled to wasm, and run in the browser (w/ coors headers). IO/user interface and any GUI is done via typescript.
As per usual for the last two years I'm working on an open source spreadsheet engine called IronCalc. It is super exciting. We have a proof of concept at
In the last couple of months my partner and myself quit our jobs to work on that. I am pretty sure that in a year from now the world is going to have a fairly competent spreadsheet alternative.
My capacity is fairly limited but I am trying to build a community around it. Join us!
Since January I've been working on a storytelling system that fuses what I think is the best of interactive fiction / MUDs with the strengths of LLMs. The world model is entirely deterministic, but the LLM interprets the player and narrates the game and NPCs.
Also hacking on something similar to YC's QM but designed for small non-profits to ease as much back office work as possible.
I'm working on a painting of coneflowers and black-eyed susans from near where I live in New York City.
Oil on canvas, about 28 x 22 in.
Text message reminders and automation.
Send the service number a text message like "call Dave in 2 hours"
and then in 2 hours you get a text back that says "call Dave"
Open in private beta if you're interested email:
Had a problem this week helping a customer troubleshoot some SAML interactions. They couldn't install SAML Tracer in their environment and I got tired of digging through HAR files and manually decoding SAML assertions and the like so I made https://hartosaml.com/.
Just drop in your HAR file and get immediate insights into the SAML related events.
I'm working on a multiplayer stock trading game that was inspired by all my favorite board games. https://www.spellfolio.com/
It's a web-based game for 1-8 players, features a tutorial and bots, plays like a board game, and operates with economy, bluffing, forward-planning, risk-taking, course-correcting mechanics.
Play as an amateur psychic navigating a fictional stock market. Receive premonitions, call in your wizard friend, navigate dividends & earnings releases, and chase the glamorous annual investor awards.
If you try it out, please leave me some feedback :)
Petrichor, a music player for macOS: https://petrichor.page/
This has been my work outside of work, which I spend most of my weekends on. It has gotten enough downloads (23k+) and traction to motivate me to continue.
I'm working on codecast. Something that started as a way to index / search and sync agent sessions from their jsonl files has turned into a high level desktop/mobile orchestration and product / steering layer above agent sessions. It's a huge productivity boon for me and for teams that have adopted it.
My own IDE!
https://github.com/paradise-runner/toast
It has all the parts I want (lsps, syntax highlighting, a file tree) without the parts I don’t (a bundled terminal, tracking, ai)
Just promoting a small utility for others that may need it.
For us MacOS users that use Spaces and want to CMD+Tab only inside that Space, the only alternative was AltTab (that I could find) but it has so many more features and goals, plus I had performance issues with it remotely over HPSS which I use heavily so I've generated the simplest utility that only shrinks the CMD+Tab list per Space and nothing else.
I'm still working on Hackerman recorder. As a programmer, I really enjoy having live coding videos playing in the background while I work. But it's surprisingly difficult to find hour+ long videos of coding without commentary on Youtube.
What I really wanted was an infinite coding video, so I built one. Pick your IDE/monitor/ambience of choice, hit the Screensaver button, put it on a second monitor or TV, and enjoy infinite coding ASMR.
Recently added a Paper Mode which shows an animated quill that scrawls across a parchment for public domain novels.
Finally, after at least 5 years of trying, I've figured out a photo storage engine for myself, backed by a SQLite database and Cloudflare R2.
https://metallian-photos.fly.dev
It's an Actix Web/Tera/Datastar concoction, hosted on `fly.io`. It provides the backing for galleries for my music site: https://crusty-metallian.net
Now, if only I could actually write something for the blog part...
hi! i'm building https://easyinvoicepdf.com - a free and open-source invoice generator.
currently building a backend for recurring invoices, a public API, and an MCP server. recently hit 1k stars on GitHub =)
https://github.com/VladSez/easy-invoice-pdf
features:
- no sign-up required and no ads
- live PDF preview & instant download
- save seller & buyer profiles
- flexible tax support (VAT, GST, sales tax, etc.)
- fully customizable invoice templates
- 120+ currencies and 10 languages supported
- and much more
These are all really good comments and ideas! I created a tool to help facilitate, track and recover lost revenue from Stripe subscriptions for SaaS companies. Called RertyForge, www.retryforge.com It lets a failed payment be seen from a company owner’s perspective. Why things fail, what works best to recover it, what step of the process is most successful, who is most at risk right now. It’s bootstrapped and just getting it off the ground. Love any feedback or questions
A free and open source chrome extension to help people review code - https://guidedreview.dev
It upgrades your GitHub pull request review experience with a guided walkthrough of the PR optimized for reading.
I've been slowly building [MiserablyUnemployed.com](https://miserablyunemployed.com/) for the last four or five months.
It pulls jobs from tens of thousands of company HR pages, and only keeps them for seven days (unless it sees that the job has been filled). No reposts. Only fresh jobs.
Besides that it has a resume builder, matching system, application assistance via an extension, job tracking software, and an interview preparation helper. It turned into some fairly complex software that I ended up learning a lot from!
If any of you try it, let me know what you think.
I'm building Prospex (https://prospex.ch), a lead-generation tool for B2B salespeople in Switzerland. This is just a side-project as I have a full-time job.
Basically, I'm collecting public data (official registries, job boards, company websites, linkedin etc) to surface sales opportunity signals, like leadership change, new branch/market entry, funding rounds, etc.
I love shared daily puzzle games. Wordle, crosswords, that kind of thing.
Swudoku is my take on a daily sudoku puzzle. All the numbers are on the board, you just need to rearrange them to complete the game.
Been running it for over a year now with daily plays from friends and family who enjoy it. Recently took a stab at an iPhone app for it as well.
I’ve been gearing up for launching Todone, a CLI / GitHub Action that can scan comments with URLs to GitHub issues, Figma comments, or browser support pages, and more (plugin system available); and open an issue when the issue or comment is resolved, or your target browser has that feature, etc
It’s still in flux and a bit slow as I have to juggle it with my day job, but pretty excited to launch it once it’s good enough for a 1.0!
I've continued to work on a modal text editor, which has a server-client architecture that supports multiple clients (terminal, native, web) with consistent UI/bindings. I'm not using an editor as I used to, so this is more oriented around viewing/navigating code. I've recently been working on adding a Markdown viewer. The process of being able to use the editor and then get Claude to quickly make changes has been very satisfying.
I've also revived a project to design/implement a programming language. I'm slowing converging on a (keyword-less) syntax and (Beam-like) architecture that's starting to feel good.
I have had fun building a small test-framework in Gleam recently.
https://github.com/eliasson/garanti/
Just this friday I wrote an article that took a look under the hood.
https://markuseliasson.se/article/under-the-hood-of-a-gleam-...
A workflow orchestration engine built for agent harnesses e.g. Hermes:
I recently got a Magic Keyboard and Magic Trackpad and have been using them on two different Macbooks (work and non-work).
I couldn't find a good way switch them between different Macs, so I made https://github.com/MegaManSec/magic-switch. It's a small application which allows you to basically share the peripherals between Macs, and send them back-and-forth either manually or automatically.
A new transformers architecture based on relational data instead of text. Been exploring search reranking based on graph data and customer prediction.
https://github.com/relativedb/relational-transformers
https://relationaltransformers.com/
You can read more about the architecture here: https://relativedb.com/blog/relational-transformer
Audion, interpreted scripting language that is fun to write and lets you make interactive music, a/v installations using supercollider or any daw and hardware. BPM synchronization between real OS threads and Ableton sync is built in as well. https://github.com/audion-lang/audion
hack music
I had a lot of chats in OpenRouter, google AI Studio and lm studio and no good way to view/search/combine them together. ThreadShelf started as a local archive with semantic search/MCP, and later grew support for continuing conversations through llama.cpp or OpenRouter. https://github.com/ChrystianSchutz/ThreadShelf It is my first time creating oss so please be gentle.
Finishing up the IDE (Chord Writer) for my new Interactive Fiction modeling language (Chord) for web+parser based games.
I'm working my way through "Improving Heuristics for A* Pathfinding". Thank you so much, HN!
Orchestrating an AI agent built in native Object Pascal for Free Pascal Compiler and Delphi. Runs in less than 10MB of RAM. Besides being very Windows forward and local first; doing some fun things with it like incorporating WebLLM and running it in the browser inside a WASM Linux.
Https://pasclaw.dev/
A writing app.
The overall idea is to work/write at an higher level of abstraction where you work with "ideas" (just small paragraphs).
You can move them around and basically restructure many/whole paragraphs by simply changing few words.
The final text is generated by an LLM.
LLM that has the whole context so you can ask it questions, but more importantly it can provide you feedback
Working on making an old Nokia 3210 use 4G because 2G is being shut down within the next two years in most European countries.
As it currently looks I need to design my own PCB with a modern LTE module and make it connect to all the peripherals. Thought it would be a nice project to get into electronics, soldering etc. Also really enjoying the constraints of an 84x48 LCD screen and how to implement "modern" technology like GPS navigation or design the UI for a music player.
neely (https://neely.app) - club & team management for amateur sports clubs in the DACH region, starting with youth handball. I coach youth handball myself. The incumbent here is SpielerPlus - practically every handball team in Germany uses it, and I've yet to meet a coach who's happy with it. That gap is the whole opportunity.
Most inventions are just better versions of things that already exist - I'm building the Google Workspace for clubs.
I'm building a photo book system that respects privacy via no tracking, not sending anything to the server until you go to print (all stored in indexeddb until then) and even then requires as few details as possible (eg email address optional), and no sign up at all. Then everything deleted within a month. It's at https://www.rgbloom.com/ and UK only for now.
I am experimenting with using A.I. to see an image, and generate TinyScheme code to draw it on Gimp. As soon as I got the code for a 2D representation, then I bring out the heavy weaponry, Rust and Freecad, and with some more information added I generate the 3D representation of a building.
A.I. generally shines when the steps are small and incremental. I would add that, when A.I. is used properly, generating code and hopping from one code to another, it should be better than any human already.
I've been working on a cross platform screenshot/screen recording tool with a built in editor:
https://github.com/joswayski/captures
Managed to snag a cool domain for it too!
Would love any feedback from anyone that tries it
Recently completed GearPix https://www.gearpix.app/
Which is an app and audio plugin to take and send pictures to a DAW tracks and have them stored in the project file.
Not vibecoded but I must say Claude was a big help to finish and debug my C++ code (which I didn't know before this).
I am working on Amber.jl an acausal analog electronics simulation tool driven by Julia code. Just like in PyTorch, the neural network is the code, here the circuit is the code as well.
Because SPICE wasn't built for programmers in mind. The code in 0.1.0 is almost ready and I'll put the github repo public soon.