What are you working on? Any new ideas that you're thinking about?
I recently built a simple JSON schema form builder for my own purposes. I'm going to expand on it with the ability to send forms via email, handle bigger and more complex forms and then tackle document parsing. https://data-atlas.net for anyone into that kind of thing.
OnlineOrNot (https://onlineornot.com)
Planning on wrapping up the year with a year in review post (thankfully I've been writing monthly updates as I go, should save some time).
Apart from that, clearing up tech debt that helped me ship fast, but was ultimately a bad fit for the business (Next.js and GraphQL).
Ever since I tried grok imagine I became obsessed with the idea of re-imagining classical paintings or animating them so I created https://ravaan.art I don't necessarily have a vision for it, so if you think it is cool tell me what you think could be added to it.
Computing entropies of high-dimensional random vectors for a theoretical neuroscience study. The journey is mostly a repetition of (1) almost giving up because it's completely hopeless, (2) taking a hot shower, (3) realizing there might actually be a path forward, (4) almost giving up because it's completely hopeless.
Im developing this spaced repetition plugin for obsidian https://github.com/dscherdi/decks. It was the missing piece for my knowledge repository. Some other people find useful as well.
https://lab.enverge.ai/b200-challenge/ - making high-end compute available to a few researchers, who are conscious about the impact of data centers on climate and local communities.
Skyrim mod manager for the Nintendo Switch version of the game.
It’s mainly for personal use because converting, renaming, and packing mods in bulk can be very tedious. Especially if you're always changing your mod list (which is a given).
However, once I make it more user-friendly and add a proper GUI, I’ll likely release it to the public.
On my weekends I am working on yups. It started as Your Universal Package Straw-boss, but now it is going to Your Universal Prompt Straw-boss :)
It is very stupid for now but I am working on the process and a friend of mine is working to improve the LLM (that's the project Babelfish).
MCP for Open Notebook - oss NotebookLM alternative
still hosted on private GH: https://github.com/PiotrAleksander/open-notebook-mcp We will probably soon merge it to the main repo
Far less interesting than what you lot do, but I'm building a fully custom 18-cell battery pack for my Thinkpad W530 :3
I'm working on Kanji Palace (https://kanjipalace.com).
It's an app to learn Japanese language with AI. It has visual mnemonic images, JLPT progress tracker, Kanji info graphic, etc.
Later, I will add AI-comic creation based on Kanji characters you've selected.
Deploying robots within the next 6 months, not some 6+ years from now.. if anyone is interested in joinin9, DM.
I'm trying to solve the brachistochrone problem by numerical optimization. I started with the minimal surface problem to get a foot in the door: I discretize the integral as a sum of constributions that depend on the function values at specific points, then use autograd libraries for optimizing a non-linear scalar loss function
Fun/Passion-Project: A small advent calendar featuring (weird) Acro-Yoga flows we collected throughout 2025. (Acro-Yoga is a partner sport combining acrobatics and therapeutics, you should try it, it's a really great sport!)
Working on finishing the last 2 books of The Expanse. My boss wants me to write a wrapper around rabbit mq though.
I've been working on a no-code multiplayer game editor. The idea is to let anyone create multiplayer games in a few clicks without writing code—and share them instantly.
The platform handles all what's necessary (and annoying to setup) out of the box: multiplayer, controls, mobile/responsive/ inventories, save/load, leaderboards, quests, dialogue, etc... Users just select what they want and configure it with clicks.
Technically, the engine just reads a config file and renders it for players. I've built all the foundation blocks that interpret the config.
I'll soon be onboarding game designers to stress-test the editor/engine. Still polishing templates so people have a good starting point, but it's functional and I'd love feedback!
- Try a quick game here: https://craftmygame.com/game/proj_1765327918743_cicdnsqgy/r/...
- if you want to signup and try to make a game with one of the template: https://craftmygame.com/
Kenobi / https://kenobi.ai
I’m working on a way to personalize the content of your website to any visitor - with minimal setup (it’s just a script tag). We’ve just launched so if anyone wants to try it and reach out my email is in my profile!
a catalog for all deliverables ever made by consultants so that they can search semantically among slides from differnt projects and more effectively reuse their previous slides in new projects
https://alkemy.devdashlabs.com
It has an ingestion layer where we break apart a project, it's deck and it's slides into relationships like frameworks/visual archetypes, and then save that in a graph database plus a vector database. The user can then query "find me work we've done on geology research that might be relevant to industrial mining"
I'm working on adding an API and WhatsApp integration to my scam / AI detection tool - https://legitornot.co.za
Hi, all! Please check out the Freetracer RC build! It is a FOSS, native, privacy-focused ISO/BIN/other common bootable image formats flasher to removable media, written in Zig!
At work I'm implementing new 3D map geometry stuff for my employer (Mapbox) and as a a sideproject I'm building a simple 3D modeling software that gets you from idea to reliable, solid parts fast (https://www.adashape.com/).
I am busy with my AI personalized storybook maker https://storybookai.art/
and also I am trying to find some time to improve the minimal month planner https://printcalendar.top/
I’m very been trying to get into hardware more. This years project was a speaker which is nearly done (with a few weeks to spare).
Next years (and probably a couple years after) is an electro-mechanical smart watch. Sourced some Ronda GB22 gearbox motors and tritium tubes and planning on using a pcb for the face. What could go wrong.
I’m working on an open-source thing that lets you co-draw diagrams with an LLM inside draw.io/diagrams.net.
You can ask the model to rough out an AWS/GCP/Azure architecture, but the key part is the loop: you still have the normal editor, so you drag boxes, rename stuff, add your own bits, and then say things like “clean this up”, “split this service out”, “add a read replica here”. The AI edits the real draw.io XML, it’s not just generating a picture, so you and the model are basically sharing the same canvas.
It can also try to rebuild a diagram from a screenshot/PDF and then you keep iterating together in chat + manual edits.
Recently I added “bring your own API key” for a bunch of providers and support for uploading PDFs/text to turn existing docs into diagrams.
Repo (just crossed ~10.2k): https://github.com/DayuanJiang/next-ai-draw-io Demo: https://next-ai-drawio.jiang.jp/
If you live in drawio a lot, I’d be curious where this breaks down or feels more annoying than just doing it by hand.
I’m tinkering with a small TCO estimator for internal apps.
It compares different approaches and makes some assumptions explicit. Mostly a rough tool to sanity-check effort and tradeoffs.
Ready-to-use 'field kits' for the jetson orin nano which include a dual imx219 camera, bootable m.2 nvme ssd, and a 3d printed case with camera mount.
Working on https://myco.com/ - AI Employee for small business owners.
Currently it's mostly useful as an executive assistant, but I plan on making it useful on multiple fronts (e.g. social media, invoicing, etc).
An instant remote control! Lots of fun and brain damage. :D
Working on a blog post about default behaviour in ONNX Runtime when using the CoreML execution provider. Basically the default args lead to your model being ran in FP16 not FP32.
You can find more details at my site soon: https://ym2132.github.io
I am redesigning how I blog and create content with https://lakyai.com
I am also writing an "indie book" on getting to $100k revenue (and I write it inside LakyAI, no less!).
https://bid-euchre.com Bid Euchre PWA Play with friends or against robots. Couldn’t find a single deck version online like I used to play growing up. Good resume project. Would love to know your thoughts about the UI!
Making local running dictations transcribe faster than cloud tools even for longer dictations. Yes its possible.
I have always wanted a super simple local startup job board for my country. No calls, no AI chat bots, no fancy matching. Spending 1-2 hours a week on this
II’m currently working on Focusflows.eu, a tool I’m building to help people improve their focus while working or studying. At the same time, I’m exploring new ideas around productivity and digital well-being, and experimenting with features that make it easier to stay focused without feeling overwhelmed.
building out a simpler way for users to report bugs and provide developers with a context-rich environment (console/network logs) that makes fixing bugs easier.
eagerly looking for beta testers, join our waitlist
https://codepathfinder.dev Currently working on AI-Native Static code analysis and currently it's open-source.
https://bookspace.app I’m building a simple direct booking link for hospitality businesses that already have demand and want to avoid marketplace booking fees.
PostgreSQL extension providing big speedups on COUNT/SUM/DISTINCT and GROUP BY for the most common data types.
I'm looking for people who have pain around slow analytics, avoiding migration from PostgreSQL, delaying pg upgrades or other big reasons to adopt something like this.
A bookmarks assistant. A simple place to save all your links, find them with chat. The app automatically adds summaries to all links and send you an update of what you saved every Sunday morning. More features coming.
An Android live wallpaper that shows your local weather radar (US only, for now):
https://play.google.com/store/apps/details?id=app.radarlove....
I'm building a specialized web app for temporary chat sessions. It is an open-source, privacy-first solution featuring Zero Persistence. Right now, the focus is on the image messaging system.
I'm working on https://github.com/dinoki-ai/osaurus, Native macOS LLM server with MCP support. Looking for more feedback!
QEMU device that exposes a vfio-user socket for a PCI endpoint controller, Linux PCI endpoint controller driver and a userspace endpoint function.
It's very unstable at the moment but plan to have it fully implemented and working by the end of next month.
Using it to build a virtualized computational storage device for research.
I created this spaced repetition obsidian plugin I semi vibe coded. https://github.com/dscherdi/decks
Helps me with uni stuff. Some others find it useful as well
I'm working on https://kavla.dev/
It's an infinite canvas for analytics teams, like Figma + data
I'm currently working on making a better landing page, it's really hard to make a good one!
Using ML to make SQL queries more efficient.
This is what my company does (https://espresso.ai/), I'm taking advantage of the end of year quiet time to hack on some more R&D-style projects we have.
https://niyoseris.github.io/photoprompt/
Photo Prompt Generator which helps you to give LLM detailed prompts and get output as TOON, TONL, JSON or natural format.
I am building a free poker training web app, specifically aimed my friend JG who wants to place sufficiently high enough in a WSOP or WPT satellite tournament to qualify for the main tournaments: https://holdempuzzles.com/
Other folks can use it too.