Hey Product Hunt

I'm Mauro, a solo traveler and maker from Argentina. Over the years I got burned more than once by "surprise" costs on trips a resort fee that wasn't in the booking, a rental car insurance that duplicated what I already had, a connection that was technically legal but impossible to make on foot.

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.

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?

There is a massive gap in the everyday decisions we make. Google gives us star averages from strangers. Yelp gives you whoever paid. TikTok gives you a video from someone who was there eight months ago.
None of them can answer the actual question, which is live: what should I do, here, right now?

So we take the workaround: 20 to 30 minutes of scrolling, being unsure, and then finally a text goes to a friend who knows the area. The friend answers in one line, and it's better than everything else. But what if you are new to the area?

What drives me crazy is that the moment of intent is the most valuable in any local decision, and no platform is built for it. Everything is built for browsing the past, nothing for answering the present.

I ran restaurants for years and watched this failure from both sides of the counter, which is why it won't leave me alone. I am now building Cravlr, which lets you post a craving and real locals answer in minutes. It's early, and a lot of hidden things are broken. I want to have an open discussion on how we can solve this problem and build a platform that saves your time and makes a decision best suited for you.
Feel free to try: www.cravlr.com

Been thinking about this after a few good conversations here lately: there's a real tension between building something that flags "this looks off" for you automatically, versus just surfacing the raw signal and trusting the human to interpret it.

Too much automation and you risk false confidence, the tool says everything's fine, so nobody looks closer. Too little, and you're back to relying entirely on someone's attention, which doesn't scale past a certain team size or number of ventures.

With Trackly, I've mostly leaned toward showing the raw signal (check-ins, timing, patterns) rather than making a judgment call for the manager. Partly because I don't fully trust automated judgment yet, and partly because I think the "is this actually a problem" call still needs a human who knows the context.

But I'm genuinely unsure that's the right call long-term. Curious what this community thinks:

BEDIZ APP-My whole closet is in my phone now.

Every piece I own, cataloged from one photo dump I didn't type in a single shirt. And when I want to know if an outfit works, I don't guess in front of a mirror. Bediz shows it on ME, on my actual photo. Not an avatar with my haircut.

The part that changed how I shop: it works on clothes you don't own yet. See something in a store? Screenshot an outfit idea at 2am? Wishlist it, try it on your photo, and find out before you pay instead of after, standing at the returns counter because it looked great on the model.

It'll even tell you what a piece really costs. That $90 jacket you wore twice? That's a $45-per-wear jacket. The $30 tee you live in costs pennies. Bediz runs that math on your whole closet, and its stylist builds outfits from what's actually hanging in it and tells you why they work.

I know sellers who list food, skincare, medicine, and supplements some of the most regulated categories on Amazon and EU marketplaces.

Here's the thing that surprised me most: most of these platforms check structure, not law. Schema, required fields, image specs that's what gets validated at upload. A listing missing its GPSR responsible person, a health claim that isn't supported, a lithium battery attribute left blank a lot of it uploads clean anyway, and doesn't get caught until an enforcement bot finds it after the fact. Then the listing's down while you wait through a compliance review that can take 15 business days.

That gap is what I've been building against v1 is a tool that runs deterministic rules against your own listings export, in your browser, before any of that happens.
If you're a seller or just interested, feel free to leave any questions or feedback.

Hey Product Hunt

I m a solo developer and I ve been building NovaCapture, a native screen recorder for Mac.

I started building it because I kept finding that recording a good product demo takes more work than the actual demo. You record the screen, move the cursor around, and then spend more time editing everything to make it easier to follow.

That led me to build NovaCapture around automatic zoom, smooth cursor movement, webcam, and audio with the goal of making a clean demo straight from the recording.

Hey everyone

I m building BrainOS, and honestly, I started it because I could relate to the problem myself.

Sometimes you have a million things you need to do, but getting them out of your head and turning them into an actual plan is somehow the hardest part.

So I built BrainOS to take those messy brain dumps and turn them into something you can actually follow.

As a Content Marketing Manager, I ve worked with video content for quite a few years, and there s one limitation I keep coming back to: a video can only answer the questions you thought of while making it.

As soon as someone wonders, What does this mean for my situation? or Can you explain that part again? , they re usually on their own.