I built a free multilingual AI nutrition tracker solo — launching on Product Hunt today!

For a free mobile app launch, I’d make the trust cues painfully explicit before the feature list gets long. With Kinetic Override, the phrases that matter are Android 15+, no root, local profiles, no ads, and exactly what permission is used for. Small wording, big drop in hesitation.

Congrats on the launch. I came at the site from the performance and page side, since the most useful thing I can do today is flag what might be costing you conversions while traffic is high. Three things, all quick fixes.

First, your hero headline is half invisible, and I think I can see why. It reads "Your nutrition, simple & smart," but only the second line got a colour. "simple & smart" is in your green, while "Your nutrition," has no colour of its own, so it falls back to a faint cream on the near-white background and almost disappears. The first thing a visitor should read is half gone. Lighthouse doesn't even catch it (it only flagged two other contrast spots), because the heading is styled in a way the automated checker can't read, but the eye can't read it either. Looks like a one-line fix: give the first line a real colour, same as the second. On launch day I'd do that one first.

Second, the "see it in action" section. Good instinct to show the product, but the screenshots are scaled down so far I can't read any of them. That section exists to let me feel what the app is like before I commit, and right now it's a row of thumbnails I have to squint at. Let them be bigger, and crop each one to the single thing it's showing instead of the whole screen shrunk. Related catch: the page disables pinch-zoom (user-scalable is turned off in the viewport tag), so people can't even zoom in to read the small stuff. Worth turning back on, especially on a page that already has tiny text.

Third, an SEO and first-impression one. Your title and description are entirely in Greek, even though you're launching to an English crowd today and the product speaks five languages. So the browser tab, the Google result and the Product Hunt preview all show in Greek for most of your visitors. Lighthouse gives SEO a 100, but that only checks that a title exists, not that it's in your audience's language. If multilingual is your edge, serve a localised title per language with hreflang, or at least default to English for the global launch. Right now you get the narrow version of both.

The build itself is fast and clean, so none of this is deep. It's mostly about making the page show as well as the product works. One question: is the Greek title a deliberate bet on the Greek market, or just the default that shipped?

Smart choice splitting the AI work between Haiku and Sonnet to save on cost/latency. The recipe analyzer feature sounds like a lifesaver. Dropping an upvote on PH now!

Congrats on the launch! The multilingual-from-day-1 decision is underrated — I made the mistake of adding 18 languages after the fact on my own solo project and it was genuinely painful. How did you handle i18n in React/Vite? Static JSON files or something like i18next?

Also curious about the Cloudflare Workers setup — did you run into any cold start issues with the Claude API calls, or does Workers' V8 isolate model keep that fast?

Upvoted. Good luck today!

Nice launch. One metric I would add beyond signups/PH clicks is “edited after AI guess” by input type: photo, voice, recipe, barcode. In food logging, trust is built less by perfect first guesses and more by making corrections obvious, fast, and remembered the next time. I’m working in the same AI food logging space, and that correction loop feels like the real retention lever after the novelty fades.

Nice work — the multilingual angle is underrated, most solo apps ship English-only and lose half the world. I'm building a multilingual app too (budget + safety for travelers) and the i18n upkeep is real once you add features.

Quick q: did you go PWA over native specifically to dodge the app-store friction? I went React Native + APK and the distribution side has been the hardest part. Curious how Product Hunt is converting for you so far — good luck with the launch!

This is a solid scope for a solo build — especially combining food logging, voice input, and coaching in one system.

What stands out most is the multimodal angle (photo + voice + text). That’s usually where these apps start to feel “sticky,” because logging effort drops significantly compared to traditional nutrition trackers.

The main challenge I’d watch is retention vs novelty. A lot of AI nutrition tools get initial excitement, but long-term usage depends on how accurate the tracking feels and how frictionless daily logging becomes after the first week.

Also interesting stack choice with Haiku vs Sonnet split — that’s a smart way to balance cost and performance for different tasks.

Overall, the value proposition is clear: reducing friction in tracking + making it conversational instead of manual logging. That’s usually what actually changes user behavior.

Tried the guest experience for a few minutes and one thing that stood out is that the homepage doesn't immediately communicate the product's strongest differentiator.
After landing on the dashboard, I mostly saw empty nutrition metrics and tracking controls, but the AI photo logging / voice logging capabilities that make the product unique weren't immediately obvious.

As a first-time user, I found myself wondering:
"What's the first thing you want me to do?"

A stronger first-run experience that guides users toward logging their first meal (especially with AI) might help users reach the "aha" moment faster.
The multilingual positioning is interesting though — that's not something you see very often in this category.

Interesting build.

What I'd be most curious about isn't the food recognition itself, but which part users come back for after the novelty wears off.

A lot of health products get initial engagement. The harder part is figuring out what creates the second and third week of usage.