[HN Gopher] Launch HN: A0.dev (YC W25) - React Native App Generator
___________________________________________________________________
Launch HN: A0.dev (YC W25) - React Native App Generator
Hi HN -- we're Seth and Ayo and we're building a0.dev
(https://a0.dev). a0.dev is a platform built to cut down React
Native development time from weeks to just a few hours. We've been
building mobile apps together for seven years and have had several
successes. One thing that's always bothered us though is how much
harder it is to build a mobile app than a website. If you've built
an app with React Native before you're familiar with the pains of
working with both Xcode and Android Studio, writing tons of
boilerplate before you can even start making the app, setting up
state management, and of course going through the dreaded app
review. We decided to build a platform that would make the app
development process faster. We've seen the success of new code-gen
platforms like v0 and wanted something for React Native that goes
further. We built an AI app generator that takes a user's prompt
and creates a custom React Native app with an instant live preview.
Here's a 5min demo where we recreated the Hacker News UI:
https://youtu.be/f3lzBRBUous a0.dev is great for quickly
prototyping components and screens in React Native and users are
able to copy the code from our generator into their preferred
development environment. Our landing page has a couple of example
prompts, but we encourage you to get creative when trying it out.
We've had success generating not only functional screens like an
Instagram Feed but also 2d games like Minesweeper or Flappy Bird.
Our chat has a "UI Expert" and "Advanced Logic" model users can
switch between depending on the task at hand. Users can upgrade
from working on a single screen to creating a full app by clicking
on the "Need a Full App" button in the top right of the page. This
changes the scope from a standalone chat with a single file to a
full project that can include multiple chats and files. We launched
an IOS app that users can download in order to preview the app on a
physical device. We find that many apps look and feel better on a
physical device so we recommend trying it out. Our goal is to
continue to improve the app generator while adding more features to
help developers get their apps to the app store and make money from
those apps. The main features on our roadmap right now are a
Supabase integration and a "one click submit" button to let
developers publish their app to the App Store. There are a few
limitations to note. We're working on releasing our Android app,
but Android users should be able to preview their app using the
Expo Go App. The app is running React Native Web in the browser so
any dependencies that don't support web won't work with the web
preview but should work on the phone. There are also some
dependencies that our system can't handle because they require
native modules that aren't packaged into our app currently. We
hope you guys will check it out and try making an app with a0.dev.
We're available on Discord around the clock to help developers with
any problems they may face and want to guide people to actually
releasing their app on the App Store. Let us know what features
you'd like to see and any problems you've faced building apps, we'd
love to hear about your experience. Here's the link again to check
it out: (https://a0.dev) We dropped the need to sign up for the
first message so you can just jump in and try it out. Looking
forward to your thoughts!
Author : sethburster
Score : 240 points
Date : 2025-02-11 17:08 UTC (1 days ago)
| martypitt wrote:
| Congrats on shipping.
|
| I'm curious how commodotized the underlying LLM's are for
| generating this type of code? (And thereby, how big the moat is
| for companies like vercel/bolt surrounding v0 et al).
|
| What models are you using to power the code editor? Did it
| require much customization?
|
| Is it likely that enterprises would be able to eventually bring
| their own LLM's, or does the training make that prohibitive?
| cmdtab wrote:
| Bolt is actually open source. You can see how it works
|
| https://github.com/stackblitz/bolt.new
| ayomide321 wrote:
| It takes quite a bit of configuration to add a new LLM, because
| of this I don't believe its in our roadmap
| colesantiago wrote:
| I was just about to sign off on a 6 figure deal for someone to
| make a app for our pest control SaaS, and I just saw this right
| now and now considering trying this out if it gets the cost low
| significantly.
|
| I would imagine for those who want to are agencies / developers
| building apps who charge a fortune doesn't make sense anymore
| with tools like Replit.it, Bolt, Devin and now A0.
|
| Great work Seth and Ayo for making it easier and potentially
| bringing to cost of building an app down close to free as I'm
| assuming this is now free as it is just a sign up.
|
| Is there any pricing on this?
| wouldbecouldbe wrote:
| Have a small saas for apps, probably can help you for less then
| 6 figures. Although custom work is probably required
| alluro2 wrote:
| Depending on what you need in the app, we at eLogii might have
| sufficient configurability to support your workflows out of the
| box, or with little customization. We work with some quite
| large pest control businesses, and you might get more than just
| the app (route optimization etc).
| siquick wrote:
| Building a RN app without any features (authentication,
| notifications) is easy - but adding those features and then
| navigating the outside-app ecosystem isn't. It's definitely not
| like the web.
| ayomide321 wrote:
| We have a subscription for $20/mo which comes with unlimited
| messages
| sirjaz wrote:
| Congrats, but you should add support for Windows and macos apps.
| https://microsoft.github.io/react-native-windows/
| jhsvsmyself wrote:
| Just signed up. Are you guys going to provide some scaffolding
| code that I can download as a zip for Android or iOS? This would
| really make it a killer for my workflow.
| ayomide321 wrote:
| We do plan to have github support and zip export pretty soon!
| chaosprint wrote:
| Your title is honest, and your description of the limitations is
| honest. It is also pragmatic to allow you to try it without
| registering. This is the way to success.
| sethburster wrote:
| Thankyou!
| zitterbewegung wrote:
| This is pretty cool. Is it possible to add a stop button similar
| to other apps?
| sethburster wrote:
| what would the stop button do?
| langitbiru wrote:
| Generating code takes some time. Sometimes when we look at
| the generated code half way, we know that it's not what we
| want. Better to stop and edit the prompt.
| sethburster wrote:
| Ah gotcha, I thought you meant for the app. We'll add this.
| johnisgood wrote:
| I just tried this one out, the generated code is blurred
| out as it is generating, which I think is not desirable.
| new_user_final wrote:
| https://a0.dev/chat/36310f55-923c-4ec7-97ee-263f7460049c
|
| How do I share chat? I tried to build public bus tracker as a
| test but there are issues using external libraries.
| ayomide321 wrote:
| There should be an add import button above the code, whats the
| library?
| twism wrote:
| Saw the demo video no sound didnt read the post and was like bet
| this guy is Nigerian. Congrats. No carry last
| awaseem wrote:
| This is awesome for RN devs, any chance to build something like
| this for Swift UI? I know it might be kind hard to get native
| components rendering in a webui like this. Anyway super cool!
| fuddle wrote:
| The chess game it generated is pretty sad:
| https://ibb.co/5Xk57m5k
| kristopolous wrote:
| That's a great design.
| solardev wrote:
| Looks like a fun mix between chess and a tower defense game
| like Orcs Must Die[1]. I'd play that!
|
| [1]
| https://store.steampowered.com/app/2273980/Orcs_Must_Die_Dea...
| Kiro wrote:
| I agree and people downvoting you are dumb. Chess + Orcs Must
| Die would be a fantastic concept!
| fuddle wrote:
| I wanted it to generate a standard Chess game though.
| redeux wrote:
| Cool, I'll play black
| growthwtf wrote:
| So, I use a lot of AI tools. I would say that baseline for
| 'coding agents' today to make it usable is that you need to
| recover from error messages and lints automatically. Once you can
| do that it will be a lot easier to use.
| instagary wrote:
| Congrats on the launch!
|
| This kinda reminds me of Expo snacks (https://snack.expo.dev/),
| but with a chat.
| rushingcreek wrote:
| This is an awesome demo and I hope you succeed.
|
| I've dabbled in building a tool of this type and something I've
| learned is that making single-task demo apps (like chess or snake
| game) is much faster and simpler than making production-grade
| apps that could make a real business. In fact, the process of
| making these demo apps production ready (polishing the UI, adding
| features, etc.) would usually result in the user giving up. In
| our implementation, it was much trickier for the system to
| understand the nuances of polishing than getting the broad
| strokes of the initial demo. I'd love to know if you've ran into
| this and what your thoughts are on getting around it.
| aylmao wrote:
| The UI is very well built! Love the details too-- from the line
| additions/deletions live counter while the AI is generating code,
| to the logo that points towards your cursor.
| sethburster wrote:
| thanks! the pointing logo is my favorite.
| hansonkd wrote:
| I had the opposite reaction. seems like a cheap knockoff of v0,
| just styled worse. Even the name. (at least the name v0 makes
| sense).
|
| Kind of put me off of using the product because it seemed like
| they just put "Build me a v0 clone with distracting animations"
| into v0.dev
| preaching5271 wrote:
| How is this different from just using Cursor on my react-native
| codebase? Cursor in agent mode means: no copy paste, implements
| features and fixes errors iteratively, knows my codebase and
| adheres to existing patterns. If I need changes, I just ask
| Cursor and preview live app changes locally
| justchad wrote:
| Cursor is quite a bit better as well at not adding erroneous
| code. Was testing a0 and it kept getting stuck in endless loops
| of errors. I'm sure they'll improve but it's pretty rough right
| now.
| sethburster wrote:
| We know Cursor is very good at code-gen and are improving our
| system to catch up. Our goal is to make the entire app
| development process faster and easier which involves alot of
| stuff outside of code-gen that we're working on and Cursor
| likely won't.
| boole1854 wrote:
| > which involves alot of stuff outside of code-gen that we're
| working on
|
| Could you elaborate on what extra stuff you are working on
| that will be a value-add over standalone Cursor?
| sethburster wrote:
| Yeah, integrations like Supabase, In-App
| Purchases/Subscriptions setup, Notifications, and App Store
| submission
| richardw wrote:
| I would guess Replit-like (or Vercel-like) automation of
| aspects that are RN-specific. Eg typical mobile
| integrations, databases, more focus on UI (design screens
| with drag and drop + LLM chat), secrets. Focusing means
| they're able to make features work better for just one type
| of developer, and can move faster. Cursor would need to
| solve for all types of development since their users
| probably do everything in all languages from web to mobile
| to backend etc.
| petrbela wrote:
| Cursor is for programmers. Ultimately, you decide what the code
| should be.
|
| v0/lovable/a0 will replace drag-and-drop "no-code" tools for
| non-programmers who don't care about code and only decide what
| the product should do. The tool will likely also manage
| hosting, either directly or through service providers, to
| ensure a seamless e2e experience, automatically fix runtime
| issues etc.
|
| The question remains, will there be a need for Cursor and
| programmers in the future at all.
| teaearlgraycold wrote:
| Far enough into the future - of course not.
|
| But keep in mind any point where programmers are obsolete is
| also the point where any job that can be done from a computer
| is obsolete. Including WYSIWYGing an app.
| PKop wrote:
| >Android users should be able to preview their app using the Expo
| Go App
|
| Can't get the QR Code to scan on my Pixel 8 in Expo Go. Camera
| just sits there staring at it. Could be unique to my phone not
| sure if working for others.
|
| Got it to use an API I'm working with that requires JSONP to get
| around CORS. But this causes error to show about using browser
| APIS. Thought I could insert platform checks to determine web vs
| / android and whether to use JSON/JSONP but it still wants to
| remove any logic referring to web. Just FYI about the impedance
| mismatch of testing in browser assuming native environment.
| sputknick wrote:
| I'm a fan, and this is something I would use, but I would prefer
| a per-use or per-token payment option. That would get me to use
| it more often. As it stands, I might sign up for one or two
| months a year.
| wg0 wrote:
| Have watched video. But haven'tried yet.
|
| Tons of work work to package everything in minimal decent
| functional product.
|
| Great work, looking forward to use (and possibly subscribe)
| later.
| mdolon wrote:
| This is one of the most impressive demos I've seen in a while.
| Really nice job!
| gardenhedge wrote:
| Is there anything stopping you, a0, from just seeing the best
| apps users make and then taking that idea and launching it
| yourself?
| ripped_britches wrote:
| Only the massive amount of effort it takes to start a company
| jc4p wrote:
| This is super cool (i do a LOT of react native after years of
| doing native development) -- one thing I'd love: Adding easy
| upgrades, right now if I leave a RN app for a while getting it to
| compile on latest iOS/Android again requires a lot of manual
| labor and reviewing rn-diff-purge. Good luck on the project!
| rahimnathwani wrote:
| The black border around the QR code prevents it from scanning on
| my Pixel 9 Pro.
|
| If I screenshot it, crop it and paste it into a blank doc, I can
| scan it.
| enisberk wrote:
| The demo looks great, congrats on the launch! I also appreciate
| your response regarding the Cursor comment. Is Onlook[1] a
| competitor at some level, or do you think it's different enough?
|
| [1]https://www.ycombinator.com/launches/Mkl-onlook-cursor-
| for-d...
| hslee16 wrote:
| congrats on the launch!
| kundi wrote:
| This looks like a shameless copy of v0 and Bolt.
|
| It's crazy to see that VCs companies would throw money for
| forking and copying an open-source project, and adjusting the
| prompt.
| adi4213 wrote:
| Hey Seth and Ayo - congrats on this launch. While I think there's
| certainly room for improvement, which I'll address below - this
| demo makes me feel that you both can keep grinding and succeed
| with this. The main feedback I have is similar to others who
| asked how this is better than Cursor running with a react native
| codebase and iOS simulator running on the side. I read your
| response about being better at iOS/android specific things could
| be the case (for example, making it really nail payments and
| subscriptions could be useful) - but it is definitely going to be
| a tough battle. If someone can only use your platform and
| reliably have a react native codebase (version controlled on
| GitHub), with working Supabase auth, and fully synced with Expo
| (so basically almost ready to go)- that would be pretty cool! I
| also think there's room for you guys to add value around some of
| the other annoying parts of launching a native app. If your app
| was able to automatically make App Store creatives and
| essentially publish the app for me with some user-promoting -
| that would be sick
| sgtwompwomp wrote:
| I hard agree. Seth, Ayo, I think you guys should be honest with
| yourself and ask whether you want to go toe to toe with Cursor,
| Windsurf, Microsoft, etc.
|
| If not, take the other route. Go deep into the vertical of
| React Native. Help people with no experience run an ENTIRE
| BUSINESS just with your chatbot as the AI cofounder - you build
| the entire app and backend, handle marketing, publish it, all
| with AI agents. How sick would that be.
| philjw wrote:
| Looks like a great addition to v0. Great to get a headstart and
| do quick iterations. My process at the moment is using v0 to get
| a functional prototype, then import the code to cursor and build
| and iterate it with my custom styling / language of choice /
| create components from scratch but instruct Cursor to "for
| component.vue take xyz from component.tsx) - (v0 basically limits
| you to React, Tailwind and shadcn)
|
| Recently came across this article where Gergely describes those 2
| camps of "bootstrappers and iterators" - and that's basically
| what it is: v0/a0 for bootstrapping, cursor/copilot for actual
| coding https://newsletter.pragmaticengineer.com/p/how-ai-will-
| chang...
| cchance wrote:
| I did it from the webpage, got something cool tried to add a
| card, and it had me signup, did google, but then my project was
| gone! That sucks ... losing the project during signup process is
| not nice UX hope you can fix that.
| jmpavlec wrote:
| I had the same experience, hitting back a couple times and
| refreshing the page allowed me to continue... But I imagine
| this would be a steep dropoff in engagement if you aren't taken
| back to the same page.
| nextworddev wrote:
| Can Bolt.new not generate react native code?
| tasn wrote:
| A bit meta, but I love how the AI code generation tools show you
| the code being live-edited rather than just having a loading
| indicator. It's very visually pleasing.
| blacksoil wrote:
| Wow this is very easy to use. I've been using Github Co-Pilot for
| a while to do web dev, this is way way way more convenient :)
| ripped_britches wrote:
| Please make one for flutter, tnx
| w-ll wrote:
| I've been out the mobile work for a while, but looking for a
| cross platform eco, ive spent time in a lot of stuff, from
| react, to unity, xmarian, and uno, all these with a c# backend.
| But once I found dart/flutter it was a game changer. I stil
| like my JS/TS, I still love c#, dart is interesting, but their
| cross platform workflow is imho the best.
| chirag-ai wrote:
| Try Tiram.AI that can generate full fledged flutter mobile
| app with just your voice.
|
| Check This Out :
|
| https://news.ycombinator.com/item?id=43023103
| chirag-ai wrote:
| Try Tiram.AI that can generate full fledged flutter mobile app
| with just your voice.
|
| https://news.ycombinator.com/item?id=43023103
| Mickymi2 wrote:
| I tried it, it works well in the beginning, but ended with bug
| when I try to add more functions, maybe iterate some more to make
| it stable? I'll say A0 has great potential, if cursor or bolt can
| be popular, why can't A0?
| misiti3780 wrote:
| These tools are cool but can someone explain what is the
| technological edge of windsurf vs cursor, vs this product, vs V0
| varcel. Are they fine tuning LLMs or are they just advanced
| prompting wrapped around the foundational models?
| nsonha wrote:
| Anything like this but for cordova?
| erickerr wrote:
| Opening this on desktop.. I'm not reading any of this.
|
| Glancing in more I see react-native mentioned, and expo+expo go
| mentioned, but like... it's been proven time and time again that
| Hacker News isn't your ideal feedback loop (ie: Dropbox, AirBNB).
|
| Why make 4 paragraphs of text when you could just say:
|
| - We obliterated X problem: (link)
|
| - We demonstrate why that problem is significant here: (public
| link or private deck)
|
| - We are growing at X->(timeframe or whatever impressive metric)
|
| Reach out if interested. Thanks. [contact@info.com]
| yard2010 wrote:
| Personally, I prefer the text and most importantly the story.
| Your textbook solution is a great method IMO, but there's less
| fun in this.
| atymic wrote:
| This looks good! Unfortunately I only made it a few prompts
| before it introduced an issue that it couldn't fix (back button
| not working). Kinda broke the whole process, what model does this
| use on the backend? Even after 5+ tries it couldn't fix the bug.
| ayomide321 wrote:
| Sorry about that; this is an issue with react-native-web and
| its likely that it works on your mobile device. We're trying to
| get a solution out for this!
| gregjw wrote:
| No way. A startup called A0, founded by a guy named Ayo.
|
| Congrats on the launch Seth/Ayo!
| yard2010 wrote:
| In a parallel world they would name it 6th
| lawgimenez wrote:
| I hope you can provide a way to delete the user account.
| zxilly wrote:
| It doesn't seem like a good idea to come up with a name that is
| directly reminiscent of v0.dev.
| pj_mukh wrote:
| Super cool. I'd love a multi-modal loop between code gen and app
| results. As an AI engineer who's forced to do react-native,
| getting stuff pixel perfect is pretty much the bane of my
| existence. This is probably something cursor won't build but
| y'all can?
| Oras wrote:
| While it looks nice and I like the niche, I don't see how this
| product will survive when the same thing is doable with Cursor
| and Github Copilot.
|
| Are you planning to offer your own backend, auth, notifications
| .. etc? Using Supabase will not keep users on your platform.
| RamblingCTO wrote:
| I'd like to suggest more contrast on the landing page, really
| hard to read!
| adltereturn wrote:
| That's pretty cool!
| TiredOfLife wrote:
| As is tradition it will be followed by two other YC startups: A1
| and B0
| cbhl wrote:
| Personally, I'd love to see you optimize for people who start and
| iterate upon an app from a mobile device and preview/use the app
| on the same device. Since the messages are just English text, the
| extra presses to type curly/square braces don't constrain you on
| mobile. Sometimes I get writer's block at my computer in a way
| that I don't get on my phone.
|
| In particular, I'd hide/disable the sign-in-with-Google pop-up on
| phone-size screens (it takes a third of the screen for me), and
| make sure that CSS/styling makes everything fit on the code and
| preview screens on a phone, even in mWeb.
| vessenes wrote:
| This is a great idea. LLM workflows are not nailing native apps
| right now; given Apple's slow movement, it seems like you might
| have a little bit of a window here.
|
| Couple comments - have you played with Aider's architecture mode?
| I think your workflows would benefit from it.
|
| Right now it looks like the UI expert specs something and builds
| it, and then it asks for follow up.
|
| I think the right dev flow working with a product dreamer
| involves UI mockups, then follow up questions, then
| implementation, with checkins -- combining the idea of the
| architect with a "Product Manager" role is what most people
| _need_ to get an app out.
|
| Second thought is that I think you could see value with a bunch
| of custom prompted flows later in the app process: "do you want
| to take stripe payments?" "Do you want to add referral tracking
| support?" I'm not a native app dev, but I imagine there's a bunch
| of CI, Firebase, other integrations that are best practice type
| things. Automating this as well would be really useful, and
| provide value and some lock in for your customers. To expand on
| this, you might make the basic option use your API access to
| these providers, and upcharge them. They could always implement
| their own if they want to move away, but the default path would
| get you some billing off every app that grows.
|
| Another random idea would be 'appifying' a web site as a simple
| flow for the user. This feels like it might be even faster for
| the average person as a way to explain what they want, and would
| feed a lot of technical and visual direction straight into your
| workflow at the same time.
|
| Anyway, good luck! I hope you guys get traction.
| lowkey_ wrote:
| First, this looks great and congrats on the launch!
|
| Is it possible to use Figma designs with this?
|
| It's really hard to get something great through just a chat
| interface, and I've seen a lot of these AI tools don't allow me
| to actually give it _more_ to work with like Figma designs.
___________________________________________________________________
(page generated 2025-02-12 23:01 UTC)