Ask HN: What are you working on? (June 2026)

Working on 2 things at the moment, both fully open source:

- navigation without GPS and Internet

- GIS with tokenized raster layers so that LLMs could easily talk to the maps

A json schemaless stream querying engine that would run several sql queries over the same kafka consumer (not a consumer for each query).

Fully F# based online voice chat agent

https://novian.works/voice_test/

I'm working on a search-and-replace TUI with case-awareness and a good preview.

https://github.com/beeb/swpui

Trying to adept an O. Henry short story into an AI animation short. If I'm happy with the results, will be sure to publish a detailed breakdown of the work.

https://esploro.app - trying to build a modern, sleek, lightweight and open source macOS database client

A new CLI for https://github.com/dirac-run/dirac and a paper that may or may not ever publish

An all time classic, a headshot generator: https://instant.photos

https://whatgrowswell.com - find out what edible plants grow in your area and when best to plant them.

I'm building a browser for designers: https://matry.design/

https://codeberg.org/olpad/openmic

An open source audio interface along the lines of a Scarlett 2i2.

I'm working on (yet another) git worktree multi agent development tool that just runs in any terminal. Supports Claude Code, Pi and Codex agents and provides a CLI that allows them to work together in a given worktree. Currently messing around with having the agent drive the app itself to record and caption screencasts. Fun project that is also my daily driver for agentic development at the day job. Idea was born out of using Conductor and similar tools but preferring to work in the terminal and still lean on my preferred tools like lazygit, neovim etc... https://github.com/bakedbean/workspacex

I am building agentic id and global, open agent-to-agent signed communication at https://aweb.ai

I am rebuilding an open source email client i started hacking on 15 years ago. The rise of AI coding agents suddenly made this feasible again...

I'm working on trying to get citizens' voices into spaces of power (councils, parliaments...). So far I've been experimenting with scrapping public records and building a solo (and multiplayer) experience for replaying plenary sessions.

Last few years of Congress: https://andratwiro.github.io/riot/?city=congress&solo=1

Reichtag during Hitler's takeover: https://andratwiro.github.io/riot/?city=weimar&solo=1

duplicate post: https://news.ycombinator.com/item?id=48514461

I am building runtime security for AI agents; for real. https://minimako.com

building a free and open-source invoice generator https://easyinvoicepdf.com https://github.com/VladSez/easy-invoice-pdf

- No sign-up required & no ads

- Live PDF preview & instant download

- Flexible tax support (VAT, Sales Tax, etc.)

- Fully customizable invoice templates

- 120+ currencies & multi-language support

- 100% In-Browser

Open-source Shopify for every vertical. Then leveraging that to build an interoperable, decentralized marketplace

I have two projects that I'm hoping to release in the months ahead. These are both pretty pointless but fun projects.

One is a TRS-80 Model I emulator in JavaScript called Trash80. About 10 months ago I started this project just for fun while experimenting with what now seems to be called agentic loops. I got things working pretty well with the Z80 passing the ZEXALL suite and a lot of real TRS-80 software running fine. It sat for months untouched before I decided it is worth releasing and recently started it up again.

I didn't want to release it without a ROM, so I rigged up some agents to build a clean-room style L2 ROM w/ a fairly complete BASIC and even readline-style control commands, history, and a proper cursor. That went very well, but the agents cheated on floating point and implemented some weird Q5.2 like-thing. I told them to fix it, but I guess I didn't give clear enough instructions because they replaced it with a BCD hybrid monstrosity instead of proper floating point. The proper floating point is now underway, but I'm mostly using excess Codex credits before they expire, so it's only moving forward when I have credits I don't need.

I also built a silly ASCII fractal browser in Z80 assembly so that I can ship with a virtual disk that has software on it. The emulator works in the browser and the terminal. Unicode sextant block graphics map very well to TRS-80 Model I semigraphiccs/squots, so it really does run everything very well in the terminal, even games. I also added a line-mode for line-based applications, so you can use a readline-like interface and feel like it's native terminal app as well, though that has some issues I need to fix. And of course, you can shebang TRS-80 BASIC files and run them through the emulator too.

Another project was a demo of chromesthesia, a form of synesthesia where sounds trigger experiences of color. I thought it was done and ready to release, but then I had a new idea. The visualization while cool, was kind of boring. I decided to replace it with an attempt at a semi-physically accurate cymatics simulation with artificial coloring based on chromesthesia. Cymatics is the practice of making sounds visible by vibrating a surface, such as a plate with sand on it. As the sound changes, symmetrically interesting patterns form and evolve. I've got something working now with wave generation and microphone input, but sometimes it gets a bit stuck and stops evolving as it should, so I have to find time to figure that out.

Currently all unreleased, but when they do release it will be at www.leshylabs.com. I sometimes post updates on X, but not too often. (https://x.com/LeshyLabs)

in spare time working on https://coderscreen.com/, an open source technical interview platform

I am looking to build a platform that allows for real interview workflows like takehomes, agent coding sessions, as well as the standard leetcode-style questions

Building the most effective typing application.

https://typequicker.com

Two things:

CRM with agent baked in that can properly do stuff. No idea why attio/twenty are soooo bad at this. It's a table. getcrme.com / https://github.com/ChristianSch/crme

and gargoyle, an activitypub server with a (theoretically mastodon compatible UI) https://github.com/myfedi/gargoyle. Was annoyed at the homogenous fediverse dev teams out there that don't want their precious service federate with others. I want more federation (tested it with bookwyrms and lemmy for now. Mastodon/GTS also working ofc) and a pretty UI and not waste time with weird identity politics. You do you. I want an open fediverse, not a filter bubble. And GTS was too hard to hack on.

I’m getting back into it again after a long break due to burnout. I’m still burned out but it’s getting easier to think through problems.

I’m building a home server. This was something I put off for years due to some perfectionism. Eventually I just threw together something with old hardware and headless Ubuntu. Much to my surprise, the power draw is only about $4 a month. I can live with that so no need for specialized hardware.

I’m doing the common -arr stack using docker compose. I’m using plex because the jellyfin doesn’t work as well on an Apple TV.

Having a server running is nice. I can set up some stuff on a whim. Most recently was the Mealie recipe manager. It’s great knowing my data won’t be paywalled. I’m using syncthing as a simple backup method between my devices - everything but media of course. It’s fine if I lose media.

An unexpected benefit of having the server is that it inspires my wife. She decided to give vibe coding a try. She’s an artist, not an engineer, but with a little help she was able to make a task tracker for us. She tailored it to the way we tackle our tasks and, again, it’s really nice knowing it won’t get paywalled in the future.

I’m still burned out, but having a server to tinker with is helping.

AI slopping a Backrooms game, Fable was the only one that can do it and now its gone

Jacobin, a JVM entirely written in go https://www.jacobin.org

learning to build local coding agents with mastra framework, doing basics at the moment, like reading the code, editing.

if you have built coding agent in the past using mastra, what are the problems you have faced with mastra? does it support complex branching/context trimming and other features required to efficiently manage context for AI agents?

Im tired of busywork admin work. Electron app to automate and/or make it feel like doom scrolling or tinder.

I'm working on (yet another) Hacker News browser extension, mostly to scratch my own itch. The desktop experience on HN is fine, but I don't love mobile support or lack of dark mode.

I've tried some alternatives, but Modern for Hacker News seems abandoned. Harmonic is great (they just released v3 as well), but it's Android only. According to Firefox the extension has a grand total of 2 users, with one of them being myself.

https://github.com/ewsbr/fancy-hacker-news

Starting a new team at my company for AI Enablement for org-wide tooling, governance and long-term AI strategy.

A few tools to de-enshittify/enhance specific websites.

I don't have to tell the Hacker News crowd how junked up the web has become.

* Bookmarklet to cleanly extract lyrics from Genius.com. * Firefox add-on to cleanly display lead sheets and guitar tabs on UltimateGuitar.com * Firefox add-on to show Distance From City on TrustedHousesitters.com. https://versastudio.com/projects

I’m building a little tool to organize my sheet music, let me share it, organize rehearsals, and manage performances.

FreeBSD 15.1! Scheduled to be announced 2026-06-16 00:00 UTC; just need to get some release documentation polished now.

I am building a e-com tracker that help users to Track competitor pricing, product launches, promotions, and stock changes automatically. Get alerts the moment the market moves.

trying to get AI-powered YouTube playlist generator to work well with podcasts: https://playlists.at/youtube/generate/ (GPT doesn't seem to be very good with podcasts.)

https://www.learnchess.ai — The chess app I always wanted (I've tried a lot of apps in the last years but they always lacked some fundamental feature and/or had terrible UX).

working on DevRoulette

You start a task in Claude Code, and it automatically matches you with a random dev who’s also waiting on theirs.

You can chat, skip, or end the chat anytime.

http://github.com/DevRoulette

I built a dictation and meetings after trying other apps (Wispr Flow, Willow Voice, Granola, open source) and realised they're either user hostile, buggy or have limited feature set. For example, many of these dictations app opt you into Context awareness, which means your entire page contents get streamed to their server. The open source apps don't have dictionary, shortcuts (say "linkedin link" → and it pastes your actual link), or ability to use any proprietary API.

So I made my own dictation app. Supports arbitrary API providers (e.g. Deepgram, Speechmatics, Elevenlabs), Offline models and a subscription if you want it. Otherwise it's free forever for BYOK and offline models. Deepgram is a YC startup from 2016, and have models that are genuinely good - so it's up to you if you want to use them.

Also, Granola doesn't let you read your own meetings after 30 days. So I added a feature in DuckType to import your data from Granola, unlocking all your meetings from their paywall.

Another app: OpenCook https://open-cook.com/ . We curated and wrote our own recipes into StashCook, which requires a subscription just to read your own recipes on the web app. So I got Codex to extract our recipes and rebuild one that is open source, OpenAPI and includes AI features.

This won me 1 year of GPT Pro at the codex event :)

I hope you can tell... I'm tired of companies designing their products to lock you in, to charge you more, with no added value. I build software for people like me. So I'll be building more apps that replace this user hostile software.

App to upload images to a PDF file. https://imagina.xplaya.com

I'm developing a tool that will help you easily delete your data from services. It scans the subject line and sender email address of the emails in your inbox and suggests an email draft to help you delete that service. It's open source and self-hostable, with privacy and security as top priorities. I got the idea when Saymine.com was acquired by McAfee and became total bs...

This is my first project that I want to release to the public, and the official instance will be free to use. I'll try to keep costs low without sacrificing service quality, and I hope to keep the project afloat with donations because I believe everyone should have the right to easily remove their data, regardless of cost or technical expertise. I don't have anything to share yet because it's still in the early stages of development, but it's looking good so far.

self publishing scientific papers, with IP defensible via DOI and bitcoin timestamp:

https://m4gr4th34.github.io/dossier-001/paper.html

still working on https://hcker.news, which has an absurd number of features that improve your QoL when reading hn.

i've massively improved a bunch of things like the AI filter, which now gives you the option of filtering out github repos with AI authorship.

Also improved comments, which I'm serving through my own backend which has made loading of comments super fast, and it's going to be the foundation for some really great other features coming soon.

Soon: HN feature parity via browser extension and sync'd accounts.

Built a logic puzzle at https://daily baffle.com/truthsorting, try it out!

serverless hosting for wordpress: https://www.agiler.io

The hard part is doing it without modifying WP, and serverless mariadb that can scale to zero.

Personal (as in, "for personal use, not a product") conversation partner -- I speak in German, one level is correcting the mistakes, allowing me to reformulate the statement, another level is responding to the intended idea. Rinse, repeat.

the internet backbone for booksellers: https://bookhead.net

I've been continuing work on cardcast.gg. It gives you the ability to play Magic: The Gathering with your friends remotely using a webcam.

In the last month or so I added a few nifty features:

- Auto-scan functionality: Instead of having to click on cards to discover what they are, I can now do whole-frame detection on an interval (configurable), so players can mouse over the webcam stream of another player and automatically see what the actual card is. Super helpful for deciding who to attack and makes turns quicker!

- Card view is now grouped by player, since auto-detection will populate a lot of cards during the course of a game.

- Switch the video stream to Livekit from my homebrew version. Players were having video trouble and I hope Livekit is good enough so solve that problem.

Next up: I really want to build a community around this, and I'm struggling on getting the word out to people / having them try it out. I've done some SEO and word of mouth advertising, but haven't had much luck. I feel like I need to switch directions a bit. I'm a developer by trade, so this is wholly new to me.

Come check it out: https://cardcast.gg

Refactoring the D code generator to make it more modular.

I have been experimenting more with agentic iterative optimization: using LLMs to actually speed up code by finding and testing lower-level optimizations, specifically by having it build a real-world representative benchmark, then tell the LLM to optimize that benchmark without a) cheating the benchmark and b) ensuring code quality by some metric does not regress, e.g. MSE for machine learning algorithms. This is extremely effective with GPT 5.5, and recently I found another prompt optimization (https://news.ycombinator.com/item?id=48413304) that surprisingly results in another 2x speed improvement on average.

So far, I have mostly feature-complete implementations of the following, which are faster than the state-of-the-art implementations, up to 20x faster in some cases while matching or beating them in quality:

- a new 2D data visualization library, along with more bespoke data viz implementations such as word clouds and Primitive.

- programmatic image generation

- image compression

- a new statistical machine learning library, along with more bespoke algorithms such as UMAP and HDBSCAN

- a novel modelless invisible image watermarking approach

- a novel machine learning approach which may be a crime against data science but the performance is really good

- local text embedding generation with MLX

- image-to-ASCII art conversion

- grep/jq replacement (faster than ripgrep)

I aim to open-source them over the next months but the main bottleneck is the inevitable barrage of "gtfo AI slop" comments even if I dot every i and check every t, in addition to the distribution of new software being extremely difficult nowadays due to the death of social media and "20x faster" raising red flags even if I have the data to justify it.

An Eisenhower Matrix for my to-do app.

https://github.com/abstractspoon/ToDoList_Dev/tree/9.3---New...