Any example of successful vibe-coded product?

Not sure how you would define successful though. I built a Firefox addon almost entirely through vibe coding and I know at least 5 other random souls on the Internet who have used and thanked me for it. But it is by now stretch popular it makes money if those are the measures.

I was trying to test the theory if it's even possible to release something production grade with vibe coding. Wrote about the experience here https://kau.sh/blog/container-traffic-control/

Piece Together is an animated puzzle game that I built with a fairly heavy reliance on agentic coding, especially for scaffolding. I did have to jump in and tweak some things manually (the piece-matching algorithm, responsive design, etc.), but overall I'd wager that LLMs handled about 80% of the work.

I've never seen anything like it since the original days of the game "The Island of Dr. Brain" released in the early 90s.

https://mordenstar.com/projects/piece-together

If by production you mean “done” and used by someone (i.e. by me) then I made https://skidmarks.club to replace my peloton subscription. You can browse and ride at https://app.skidmarks.club.

I’ve done ~10 rides with it so far. Hoping I can convince my wife to use it and save myself $50 a month. That would be my most successful side project by a wide margin.

There are probably a lot of examples like this. Vibe coded software people made for themselves, and other people could use it if they wanted.

All of the code was reviewed by myself, and I’m a programmer, so not sure if that fits the description. I didn’t go through it with a fine-toothed comb, however, and 90% of the review was on my phone. I also did some non-vibed setup for hosting, db, email, etcetera.

To me vibe coding is not looking at any of the code at all, but the definition reads a little loose to me these days, especially on HN, as: did an LLM “type” most of the code or did you? Either way I don’t think the term or definition is a big deal and probably not worth splitting hairs over.

I’ve pushed a full-stack educational platform for parents, My DigitAlly, to production using what we call "Systematic AI Collaboration" (a matured version of vibe-coding). It isn't a static site; it’s a production app with: Full Auth: Google OAuth and email/password. Engagement Engine: A node-cron system that automatically sends weekly tips to 200+ subscribers every Saturday. Dynamic Curriculum: A 5-block lesson flow driven by a JSON-based instructional design framework. Automated Resources: Auth-aware server-side PDF generation for parent checklists.

The "Methodology" that made it work: We moved from initial idea to production in four weekends while I maintained a full-time role. The key was moving past "chaotic vibes" and treating different LLMs like specialized team members: A) Strategic Layer (Gemini Pro): Used for architectural decisions (React/Vite, Node/Express, PostgreSQL/Prisma) and product prioritization.

B) Execution Layer (Claude Code): Used for heavy lifting—implementing the cron jobs, refactoring API patterns, and writing the test suite.

C) TDD as the Guardrail: We never "just coded." Every AI-generated feature followed a strict Test-Driven Development cycle using Vitest. If the tests didn't pass, the code didn't go to production.

The result is a stable system serving 200+ active users with a codebase that doesn't feel "schizophrenic" because we maintained strict cognitive boundaries and context documents for the AI to follow.

Keep in mind that a lot of vibe-coded software is flying under the radar because it’s being built to replace SaaS and bring workflows in-house. We often judge success by public launches or ARR, but the real "killer app" for this methodology right now is internal tooling for small teams. For example, instead of spending developer bandwidth integrating Salesforce into first-party data, teams are increasingly just vibe-coding a bespoke CRM or CMS as an appendage to their existing database. It’s complex software (state, auth, heavy logic), but it will never be on Product Hunt because it's purely for internal utility. The success metric here isn't "did we get 10k users," it's "did we avoid a $50k contract and weeks of integration hell."

I’ve built and launched numerous SaaS products (which have paying customers) which were almost entirely built usibg AI agents including https://securitybot.dev and https://dependencydesk.com.

My experience so far has been if you possess both deep domain-specific experience and significant coding experience then these coding LLMs, and most notably Opus 4.5, are the greatest productivity booster in the world.

I own a small bar and inventory management is either spreadsheets or saas products meant for larger operations. With the exclusion of some very small changes (e.g., deleting dead code) it’s 100% written using Claude Code. Initial design was generated from markdown documentation I wrote, and each change has been careful and incremental. A few blind alleys lead in the wrong direction, but was always easy enough to back up and try a different approach.

Database migrations and anything related to calculations have had a fair bit of hand holding. Beyond tests it writes I do still test by hand for confidence.

It’s coming up to a year of use. Claude Code credits has still not exceeded the cost of a paid product. I don’t count my time here because this doubles as keeping my technical side busy, and it’s been enjoyable.

Vibe coded this with my son. Something I always wanted since we often record sporting events and want to know if it’s worth watching. So, successful in that sense and works in real time.

https://www.donttellmethescore.com/nfl

Not sure this counts as "successful" yet (invite-only beta, still rough), but I'm building a full product almost entirely via LLM-assisted coding.

Tangents (https://tangents.chat) is an Angular/Nest/Postgres app for thinking-with-LLMs without losing the thread.

- Branch: select any span (user or assistant) and branch it into a tangent thread so the main thread stays coherent.

- Collector: collect spans across messages/threads into curated context, then prompt with it.

- You can inspect a "what the model will see" preview and keep a stored context-assembly manifest.

Vibe-coding aspect: about 600 commits and about 120k LOC (tests included) and I have not handwritten the implementation code. I do write specs/docs/checklists and I run tests/CI like normal.

What made it workable for something larger than a static page:

- Treat the model like a junior dev: explicit requirements plus acceptance criteria, thin slices, one change at a time.

- Keep "project truth" in versioned docs (design system plus interface spec) so the model does not drift.

- Enforce guardrails: types, lint, tests, and a strict definition of "done."

- The bottleneck is not generating code, it is preventing context/spec drift and keeping invariants stable across hundreds of changes.

If you define "vibe coding" as "I never look at the code," I do not think serious production apps fit that. But if you define it as "the LLM writes the code and you steer via specs/tests," it is possible to build something non-trivial.

Happy to answer specifics if anyone cares (workflow, tooling, what breaks first, etc.).

Here is an web app that tracks the grocery prices of my shopping at Aldi. It is meant to track grocery price inflation over time. It is obviously limited and incomplete since it is just based on my haphazard Aldi shopping. It includes a "basket of goods" total for each quarter, graphs, product pages, etc. It is coded by an LLM (except for maybe the initial commit). I don't write or edit the code, but I do sometimes "look" at the code, and ask for changes based on what code I see, so purists might question it as being 100% vibe coded.

https://aldi-prices.lawruk.com/ https://github.com/jimlawruk/aldi-prices

I once created a pomodoro multiplayer application after being frustrated by https://cuckoo.team (although good software, nothing against the team) just not working/actively glitching

spocklet-pomodo.hf.space/

I created it as a single main.go with just a single main dependency (gorilla websockets iirc) and I think It's pretty successfull between me and my friends and I am not thinking of monetizing it ever

There is also https://spocklet-beta-pomodo.hf.space/ which has some more features to make it more user friendly that I got suggestion for so yeah

I made it out of complete frustration and the first prototype was built in <30 minutes but I guess I won't really take credit of it because I am just pleasant that I can now use such a software and perhaps other might too.

I don't know but I am very gloomy about AI mostly but prototyping in domains I don't know too much about to create a "just good enough" for my own use case is the only valid use case I find of it I guess.

Windows 11 is quite popular.

https://www.pixelhook.app/

My friend vibe coded the entire app to generate thumbnails for YouTube videos.

I vibe coded a windows shell extension that renders thumbnails for 10-bit videos. Windows does not do this out of the box.

I also built a Preview Pane Handler for 10-bit videos.

The installers (WIX) were vibe coded as well.

So was the product website and stripe integration. I created a bespoke license generation system on checkout.

I don’t think I wrote a single line of C++ code although the WIX installers and website did receive minimal manual adjustments.

Started with Claude but then at some point during development Codex got really good so I used only that.

https://ruptureware.com

A lightweight GTK Linux chat client that is not based on any web tech and supports most of the features offered by the various API's out there such as audio and image gen.

https://github.com/rabfulton/ChatGTK

I'm sure the code can be critisized, but I'm happily using the application I wanted that did not exist having never programmed python in my life.

I vibe coded Pantry Recipes as an experiment (and to fill a personal need), and it has paying subscribers. Certainly not commercially successful though. https://apps.apple.com/us/app/pantry-recipes/id6744589753

https://spaceword.org - a daily word game inspired by banana grams, where you need to arrange 21 letters in a tight square. Has around 400 daily active players.

I'm pretty familiar with the underlying stack, which helped a lot since I knew the pitfalls. But pretty much all of the code is written by an LLM.

https://behavior.today

I cloned Paddle's NextJS starter kit[1] and incorporated my previous reporting code built with Observable Framework[2].

It actually took longer to get the website (domain, terms, privacy) approved by Paddle and my identity verified by its 3rd party than to vibe code the site with Claude Code.

[1] https://github.com/PaddleHQ/paddle-nextjs-starter-kit

[2] https://github.com/observablehq/framework

i'm vibe coding vibium, a test automation tool in the spirit of playwright and selenium. (was #1 on hn last week for a little bit with a lively discussion.)

I built https://www.agentsfordata.com entirely in Cursor agent mode

I have rebuilt it a few times in agent mode while trying to get pmf. I used about 22B tokens this year

My friend created an iPhone app that controls a set of MCP servers that will control all the smart things in his house. Completely vibe coded. The servers are in Python, which he can read but not really write, and the app is in Swift, which he doesn't understand at all.

https://github.com/adrianco/c11s-house-ios

If by production you accept a new programming language than yes:

https://github.com/pannous/goo (1% handwritten go extensions)

Here's one: https://markshot.dev and a writeup at https://senkorasic.com/articles/mvp-vibe-code

It's not commercially successful (it's a side project), but still represents a complete project.

Busy coding up a variety of MCP server. Not a saas but I’d consider them success in that they do what I want

Nostr web client https://github.com/lucianmarin/subnostr

An easy to use pickleball game schedule creation tool: https://www.pickleballdinking.com/resources/schedule.html

Yes, Jmail.

It’s a suite of tools to navigate the Epstein files—it even made it into the news!

Here’s the HackerNews discussion: https://news.ycombinator.com/item?id=46339600

This probably doesn't count as an "app" in terms of what you're looking for, but was a fun little project

https://alexjacobs08.github.io/lobsters-graph/

(i built this in search of a lobste.rs invite if anyone willing and able sees this--email in my bio :)

With all the AI hype lately, if a product like that actually existed, you would’ve heard about it by now.

You define ‘successful’ as ‘managed to push to production’? I think that is a disappointing low barrier.

Why do I read about all the vibe coders claiming to be 20X engineers in LLM threads and replacing many departments. Yet here is not a fking single commercially successful thing here?

Funny also how Loveable and the like are hiring engineers like crazy, yet think engineers are not needed anymore. Why not just vibecode Loveable itself? Oh wait I can tell you why.

I produced https://lynxprompt.com as an IDE/tool-agnostic AI config rules generator & catalog, via CLI & WebUI. There is a lot of love (and $$$) put in the Wizard generator, you can check it both via CLI or WebUI.

I've got some users and the stuff I can do each time I start doing vibecoding is astounding. Obviously 50% the work is just fixing what the AI didn't understood or imagined too much, but having a good AGENTS.md is key (and patience from me) - so that's why I'm buidling LynxPrompt indeed, for having an easy way to own a good AGENTS.md file for my next projects... and hopefully you too.

FWIW, I am building a market place app in rails and trying to vibe code the majority of it. Mostly with Gemini CLI + Cursor.

Its been very decent so far. Time will tell if the PMF is there for the MVP, but thats on the product, not the AI generated code slop.

FYI, this was more of a hobby horse + learning project than an "enterprise SaaS requiring SOC2 compliance." I am basically building a toy. So far, I have learned that you can ship code toys very quickly to test a market demand with an MVP.

I'm not sure how you would define "successfully," but I've created 3 different Windows apps using nothing but vibe coding (I'm not a coder) that I use for work and one app I use for exercise (a basic, browser based Tabata program that for whatever reason does more than any android app I've been able to find, and for free). They're fairly simple things, but they get the job done in ways that did not exist for me before.

And, again, I'm not a coder and only know the absolute basics of programming. This is not something I would have been able to do without AI assistance.

There's also the fact that many programmers working on software today both big and small use AI to one degree or another, maybe not to program the whole thing from scratch, but definitely to help ease the process. It's an invaluable tool.

i am about to incorporate my first business, https://querypanel.io. I vibe coded it, but i reviewed every line of code. I created the architecture on my own so i would say it was spec driven. I have 15+ years of experience in engineering and i think AI is a good thing if you consider your self as an engineer. It speeds things up. Specially opus 4.5 or gemini 3 pro.

Not sure about success - but I vibe-coded a Chrome extension that uses your fal.ai API key to create/edit AI images/videos in a visual workflow:

https://chromewebstore.google.com/detail/ai-slop-canvas/dogg...

I think it's decent complexity for something where I didn't even write one line of code. (all Claude Code)

I've made a few small projects that were built almost exclusively with Cursor (if that's considered vibe coding, I'm not sure). They don't have many users.

https://spikelog.com

https://runnem.com

https://leveloh.com

https://thefudgesisters.com

https://hop.coffee

I'm write a few articles here about tricks that work for me when it comes to AI assisted coding: https://foundinglean.substack.com

https://www.linkedin.com/posts/jorgevaras_i-cave-in-and-i-tr...

https://apps.apple.com/us/app/nosync-dj/id6752585119

Equilateral.ai is GLIDE coded. Governed vibes with standards and security baked in.

I wrote Sum Buddy using a variety of AIs. Its a full featured AI spreadsheet. It started in Gemini's web interface and moved over to claude (which was a huge increase in capability). It has a bunch of paying customers now.

https://sumbuddy.net

AI-assisted programming IS NOT "vibe coding" Yes, I have three big webistes (more than 10 million pages) in production, made with AI-assistance.

calmshows - discover and organise shows and movies:

https://apps.apple.com/au/app/calmshows/id6749471333

ios and web app and openapi spec

I built an iptv proxy that supports scheduled recordings, as well as proxying playlist and binary protocol streaming. Containerized I run this for my wife who watches a lot of foreign tv. This last weekend I built from scratch a event driven design simulator for visualizing my system design work with a godot gamified presentation so I can step thru event impact with people rather than looking at static diagrams. I wrote none of the code. Spent maybe 2 hours refactoring some things, but nothing significant. Passed my reviews, was very pleased with results. Quite liking codex models, though still get faster iterations and good results with sonnet.

Qwen3-Coder on 20gb of vram was able to do 90% of this: https://gist.github.com/gatlin/4bee9645b96e8b9e733960453b972...

Problem statement: given a start date and a bible book / chapter, produce a reading schedule for the remainder of the bible assuming one will read 3 chapters every day and 2 extra on Sunday.

So assuming an input of "2025-07-06 Genesis 1," the list would read "Saturday, June 6, 2025: Genesis 1 (3 chapters) \n Sunday, June 7, 2025: Genesis 4 (5 chapters)..." etc.

It created the types, data structures, and utility functions required, and even isolated the schedule generation to a function that used all of them ... and that function was busted. It printed the same book and chapter and date every line.

With a little elbow grease I was able to bring it home. Saved me an hour.

There's two main apps that I've built. It's been a hell of a journey but a fun one, I'll list them below, but the most fun was actually adding an "explore" feature to my site to make it a bit more fun and interactive over the christmas break - https://blazingbanana.com/ - I might keep it, might not but was cool to see what can be done in browser with WebGL.

https://blazingbanana.com/work/whistle - Whistle, which is a complete offline voice transcription app using whisper, available on all platforms, Linux, Mac, Windows (with CUDA builds), Android (and iOS as soon as my dev account goes through, who knew paying Apple £79 would be so hard!). To be honest the packaging part was probably the toughest bit and all the different ways each platform needs to build. - Probably my most "successful" one, at 450+ downloads on the Play store.

https://formait.app/ - Offline document formatting using LLMs to take a load of unstructured notes and give you a nice PDF output. Could actually load any GGUF model you throw at it as it's implementing llama.cpp. It's actually quite a useful combination with Whistle, so thinking of integrating voice to text in at some point. This is available on all platforms (except mobile) with CUDA builds available too.

I built https://screenshot2charts.com, a tool that turns screenshots or CSV/JSON into editable charts. It solves the annoying problem of re-creating messy charts for reports and presentations, especially when all you have is a blurry screenshot of either a chart or some numbers.

From my experience, the biggest difference between vibe-coded projects that go somewhere and the ones that don’t isn’t code quality, it’s whether the builder keeps talking to users after the first version. The “vibe” gets you to ship, but iteration discipline is what turns it into something real.

I think it depends on what you call successful.

I've built products that solve my problems and have released one, Intraview.ai -- it's functional, solves a real problem for me and my customers.

That said, as a business goes, it's not a sensation but it's gone from idea to customers using it in less than 6 months. Is it a VC hit, no -- am I happy with where it is and how fast I'm learning -- absolutely!

This has become a pretty pointless thing to clarify now but

"Vibe coding" and "AI-assisted coding" are NOT the same.

There's a spectrum of AI use from none to full (vibe coding).

Claude Code is probably the best known example of a product claimed to be coded with AI-assistance to the point of much of it being autonomous now guided by experts. My experience is that is now the norm for many senior engineers and it's certainly the future. I don't know any that are truly vibe-coded but I would imagine plenty of mobile apps.

I've wondered this myself, are tools like lovable/bolt used mainly for prototypes or can you ship, maintain, and scale, actual products with it?

Is it different for Claude?

vibecoded for moar vibecoding: https://h0p3.nekoweb.org/#sandworm