Like many of you, I got tired of uploading sensitive personal documents, contracts, bank statements, and IDs to random cloud servers just to perform basic tasks only to get hit with paywalls, daily rate limits, watermarks, or forced sign-ups.
I launched my app 2 months ago, it s a game changer for me. It solves my problem of wanting to track my wife s cycle, so I can show up better. These period tracking apps exist, but I didn t like any of them for men, so I vibe coded my own. It s called Her Signal; basically think of a traffic light or signal, green, yellow and red. It s a simple way to track her menstrual cycle. The best part is the ability to put a widget on your home screen which gives you an easy way to see this month s outlook. Just putting it out there for anyone who s curious about what impact this could have on their relationship!
AI have really generalized the knowledge, to the extent that things are really there, at the tip of your finger, when you need them, however you need them. While people like Elon Musk would love to enjoy the "abundance", as a Zen believer, I believe that the books are still better. But how many books can you really read in a unit time?
Not much! So I built Open Commonplace. It is the commonplace book built by the community, and for the community. Key Takeaways (and different notes) from the different books are here to be read by anyone. And you can post them too.
A year or two ago I spent around 6000 euros as a student building my app, ChallengeUp, the normal way. Developers, iteration, a lot of trial and error, a lot of money I did not really have.
Now with AI tools, people are shipping apps like this in days for basically nothing. Sometimes I look at that and wonder if I just paid a very expensive tax for doing it the old way.
I finally launched it and right now I have 0 downloads. Honestly I think a big part of the reason is that AI made building so easy that there are just a hundred similar apps now, and it is hard to stand out when everyone can ship the same idea in a weekend.
But I also wonder if the slow way gave me something those fast builds do not have. More care in the details, more time actually thinking about the problem instead of just shipping fast, a product that feels less generic maybe.
I wanted to share a project I've been building called Screen Stickynote (https://screenstickynote.com/). It's a completely free, purely offline productivity workspace designed around an infinite 3D canvas.
When vibe coding took off, it became possible to quickly turn product concepts into working software rather than leaving them in Figma or notes. But fast prototyping also made it easy to start projects without clarity, and I ended up abandoning a couple early on.
Now I m focused on one specific problem: building a community app for expats and travelers from my country. It s designed as a curated map where people pin local spots, share trusted services, and find businesses abroad where they can communicate comfortably in their native language.
For those building products for local communities or expats:
How do you approach the initial cold-start problem (getting enough verified places onto the map)?
What has been your biggest takeaway from previous projects that didn't take off?
I built Code Factory for my own needs after too many assistant-generated changes passed tests and then failed when I actually used them. The wasted time and frustration pushed me to put planning, evidence, and review into one proof-first workflow. I am sharing it free.
v0.32 adds a Counterfactual Arena to Graph Ops. It compares 2 12 supplied repair candidates, rejects failed proof, surviving mutants, scope escape, or changed receipts, and explains exactly why the smallest eligible repair won. It cannot generate or apply code; the human remains in control.
Solo builders get a readable choice before accepting an AI fix. Teams get a reproducible, hash-bound decision record. Time, token, and cost savings are shown only with an exact paired baseline; otherwise they remain Not measured.
I also used the open Prestige skill on the UI. In my own observation it materially improved the visual hierarchy and readability; the repo records its deterministic design checks without presenting that observation as measured conversion.
