PH热榜 | 2026-02-21

Hey Product Hunters 🫶

I'm excited to introduce Rork Max, the best AI agent that builds and publishes real Swift iOS apps right from your browser. No Xcode required.

Every app you love on your iPhone was built with Swift. It's faster, smoother, and unlocks everything iOS has to offer: Widgets, Siri, HealthKit, AR, 3D games, Vision, and on-device AI. Until now, building with Swift meant installing 30GB of Xcode, wrestling with certificates, TestFlight, and paying $120 just to test on your phone.

Rork Max just solved all of that.

Powered by Claude Code and Opus 4.6, it's the most powerful AI agent for IOS mobile apps. Watch it build a Pokémon Go AR game that can be published to the App Store in hours!

What you get:

• Truly native Swift apps that feel premium, not vibecoded

• Test on your iPhone with the Rork Companion app, no Xcode or Apple Dev account needed

• Share with friends and testers by email, no TestFlight setup

• Publish to App Store in 2 clicks

• Build for iPhone, iPad, Apple Watch, Vision Pro, and more

We started Rork because we were building mobile apps since 17yo, but had to spend months and years to learn how to develop them. We built successful apps that reached 2M users and #2 on the App Store, which helped us to immigrate from Eastern Europe and start living the American dream, so now we want to help you do the same.

We built the tool we wish we had 10 years ago. Rork Max is the app we dreamed about as kids.

Try Rork Max at rork.com with 50% off promo RORKMAX (only for Hunters!)

This is one of the best agentic coding products so far!

As iOS Dev I love the general idea of building using all Swift features and the philosophy behind the brand!

Amazing team, amazing product. Congrats on the launch!

Excited to see underdogs beat corporations at their own game, especially when the corporation is Apple and the game is played inside a walled garden where they make all the rules

let's go, you are doing a revolution in mobile apps space

We built an AI therapy app so we know the iOS pain — what you guys did is legendary, congrats on the launch! Quick question does Max handle HealthKit permissions and sensitive data properly out of the box?

Built a small iOS prototype in about 40 minutes today. I don’t have Swift experience. Surprised how smooth the AR part worked on a real device.

I first started using Rork about 6 months ago for an internal app for my small business and in about 2 days we had a working one that we still use to this day. Tried Rork Max today and the jump in quality is unbelievable. The native Swift apps feel so much better than the React Native ones. The publish flow actually works now. You guys have come so far. Congrats on this milestone.

I am reading the story about the launch of Rork and your team with great interest. You are doing a great job! Keep it up!

It is finally here. AFAIK, there are not many tools for smartphone apps :) So looking forward to someone finally filling the space :)

Amazing product. Congrats on the launch!

Just read the story behind Rork Max. Really impressive execution. Respect to the team for pulling this off.

great tool! sound like I finally need to try vibecoding my fist app

Congratulations, it's great

Nice, I was actually looking into working on some IOS open source apps, no mac at hand, this could be really helpful

Good luck guys! 🍀

Nice idea!

This is actually wild 🔥

As someone who’s struggled with Xcode installs, certificates, and TestFlight pain… building real Swift apps from the browser sounds like a huge unlock.

Love that it’s truly native Swift and not some wrapper workaround. Removing all that dev friction lowers the barrier so much.

Big congrats on the launch 🚀 Excited to see what people build with this!

Interesting... have there non-trivial apps already been built with it? Would be really interesting to see what's possible.

Also, what means the name "Rork"?

Looks promising! Do you support Git? I never start a project without it.

As someone who was building iOS apps since 2016, this is truly ground-breaking. Many people tried to launch “XCode killer”, but nobody was able to. Rork + Claude is the first real shot at it. If I was Apple, I would be allocating a few billions for acquisition right now

Congratulations on the launch 🎉

Congrats on the launch 🚀🚀

Most vibe coding tools create more toys while Rork provides ways from concept to a real app business! Has it been connected to any payment getway yet?

I’m excited to hunt something that genuinely expands what “creative tools” mean in 2026.

Meet Gemini with Lyria 3: Google DeepMind’s most advanced generative music model, now built directly into the Gemini app.

This isn’t just another “type a prompt, get a beat” tool. It’s a full-stack AI music collaborator.

How Lyria 3 works?

Lyria 3 is a high-fidelity music generation model that lets anyone create 30-second custom tracks using:

• Text prompts

• Photos

• Videos

Describe a vibe like: “A comical R&B slow jam about a sock finding their match” …and Gemini generates a polished, structured, catchy track, complete with lyrics and vocals.

Upload a hiking photo of your dog? It composes a song inspired by it.

This is music as expression, not production complexity.

Core features and capabilities

1️⃣ Text → Full Track

• Genre, mood, tempo control

• Lyrics auto-generated (or bring your own)

• Realistic, nuanced vocals

• Instrumental-only options

2️⃣ Image/Video → Soundtrack

• Turn visuals into high-fidelity music

• Mood-aware lyric writing

• Perfect for social content

3️⃣ Creative Control

• Direct vocal style

• Specify acoustic preferences

• Adjust complexity and arrangement

4️⃣ Professional-Grade Output

• Clean, structured tracks

• Export-ready audio

• Custom AI-generated cover art

5️⃣ Built-In Safety & Watermarking

• All tracks embedded with SynthID

• AI content verification inside Gemini

Why Lyria 3 is different?

There are plenty of AI music tools out there. Here’s where this feels distinct:

1. Musicality, not just loop generation

2. No lyrics required

3. Multi-language support

4. Visual-to-Music pipeline

5. Responsible AI Layer

Use cases I am excited about:

• Personalized birthday songs in seconds

• Instant background music for Shorts/Reels

• Community creators generating meme music

• Emotional gifts (parents, partners, inside jokes)

• Indie creators prototyping soundtrack ideas

• Marketers testing vibe-based audio branding

This lowers the barrier between idea → emotional artifact.

My personal take: What’s powerful here isn’t that AI can “make music.” It’s that this removes friction between feeling something and expressing it musically.

Over to you!

Would you use this for content? For fun? Or as a serious creative tool? Let me know in the comments. :)

Already thinking about how we can use this for CoreSight. Amazing achievement, congrats!

Has anyone gotten some good results with this they'd like to share? The generations feels pretty good, but still a bit slop-y.

music is a very interesting field. i was experimenting with elevenlabs and i am exited to see how googles compares to this.

Not bad at all. Gave it a spin and I love that it’s missing that subtle 'AI hum' you usually get with competitors. Perfect for creating chill, low-stakes background music like smooth jazz.

The last thing the world needs right now.

git-lrc started from a practical observation within my own team.

As our usage of AI coding tools like Copilot, Cursor, etc., increased, our velocity seemingly went up—but careful checking of the AI-generated code went down.

Engineers were committing code they hadn’t truly examined.

Reviews were happening later, sometimes too late, and often superficially (because AI generates tons of code)

This led to abstruse bugs and long debugging at prod.

Clearly, we needed a solution.

I didn’t want another dashboard. I wanted a strong nudge to review code at the right place—exactly where responsibility is bound to exist: git commit.

I prototyped git-lrc such that AI helps the developer work through diffs faster, acquire an understanding of what's going on, and fix issues on a commit-by-commit basis.

git-lrc was built with the idea that review shouldn’t be an afterthought. It should be structurally encouraged while putting the developer in control.

So in git-lrc, while a review is triggered automatically, the dev can still consciously skip the review.

Or they can manually review and "vouch" for the change they are making.

All these micro review decisions get recorded in git log—for future analysis so that the team could operate at higher engineering standards.

As to git-lrc, it takes 60 seconds to set up and is completely free for any number of reviews—thanks to Google Gemini's Free tier.

I encourage you to give git-lrc a try and see the difference in the quality of your code as well as concrete outcomes such as reduced production bugs.

Github: https://github.com/HexmosTech/git-lrc

Landing Page: https://hexmos.com/livereview/git-lrc/

Congratulations, very good idea, there are a lot of tools for Ai programming, but testing and review is really rare, thank you for your need awareness, I really worried about the safety of the code with Cursor

Congratulations on the launch, super cool idea! Pre-commit code review sounds like the perfect time to catch the bugs from AI-gen code.

A few questions that come to mind:
- how configurable are the checks? (can team introduce some specific domains to handle in certain way?)
- do you have any metrics yet on false positivie rates?
- and what happens when teams ship huge diffs?

congrats!

🚀🚀🚀

🚀🚀🚀

Congratulations on the launch 🎉 🎉 !!

Spot on. Lack of control is the biggest bottleneck for vibe coding. IMHO, whichever tool nails this part will completely dominate the market.

So do I understand it correctly, that it's sending my commits to your backend and you provide with code review on those?

Hi Product Hunt 👋 — I’m Alex (with Rajit and Land).

We built Prism (https://www.prismvideos.com) because making an AI video still feels like stitching together a bunch of separate tools (generation, editing, assets, audio), and the workflow breaks down as soon as you’re doing more than a single clip.

Prism keeps everything in one place: generate assets and assemble them directly in our timeline editor. No downloading files or juggling tools. Under the hood we integrate multiple models (Veo, Sora, Kling, Hailuo, Wan, SeedDream, Flux, etc.), so you can choose the best model per shot and keep everything organized inside the same project.

Here are some real-world video workflows people are using Prism for (that we’re also building templates around):
1. Cinematic scenes for short films, music videos, product launches, or advertisements.
2. Short explainers that mix generated scenes with stock B-roll and voiceover scripts
3. Meme formats that reuse the same structure but change the generated subject
4. Multi-scene character clips where you need consistent pacing and quick shot replacement during iteration
5. UGC-style ads to promote a product and to iterate on multiple hook variations

And so much more!

Question for the community: what’s the most annoying part of your current video creation workflow that you wish AI could handle end-to-end?

Try it here → https://prismvideos.com

Also here are the prompts from the video!

Image:
Recreate the scene in claymation: both the main person and the person in the background are made of colored clay with visible fingerprints, smudges, and handmade imperfections. Keep faces recognizable.

Video:
Turn the motion and detailed mouth movement of the video to the setting of the provided images

This is an awesome product, truly game-changer for any video creation workflow.

this is really good

emmm, very interesting, but I feel that the recognition of prompt is not very accurate, but the interface is very clear and simple

Absolutely wonderful product that’s becoming my daily driver for video workflow. Great team and everyone should be using this. Congrats on this launch guys ❤️

looks amazing! congrats on launching!

congrats guys!!!

How many credits are usually needed for a generation of 30-seconds long video? Or how much does one prompt cost?

How would you differentiate Prism with Veed io or Capcut?

Completely switched off higgsfield for this - i love prism

Pretty useful

thanks for building this, looks amazing!

Congrats and all the best for this re-launch!

Whatsapp bans cold outreach so it's still the same pipeline.

Perfect. I came to create a listing for my product but found the exact product I need. My Twilio Whatsapp got blocked while testing AI integration without any reason and they have been identifying the issue for 2 days now. I don't feel confident to provide Twilio as an option to get reliable message delivery.

Here's my use case. Users link their whastapp to my AI and they'll interact with it just like a chatbot directly in whatsapp. Is this possible without getting blocked?

Love the WhatsApp-first focus. Excited to see this grow

Love it!

The copywriting got me and then I just noticed the photo in the carousel 😹

The tool itself is awesome, there's not anything else out there like this and you pulled it off - fucking cool 🙌

What is the core advantage of being able to use terminal from your phone? Just wanted to think of more usecases.

As someone who’s too comfortable once I sit down this would save me so many unnecessary walks back to my desk Smart and simple idea.

Wow that's a cool app!

Cool concept. Widgets are powerful, but home screens are already noisy. How do you balance visibility with avoiding metric fatigue?

Hey @samesh13, capturing user feedback can be a real pain point, especially when vague requests lead to wasted time. By allowing users to record their screen and voice, you're addressing a crucial gap in communication and making the process seamless. What strategies are you considering to ensure users adopt this feature and keep coming back to it?

Yeah, totally get the frustration with those paywalls. It's like you just finished a masterpiece and can't even keep it. KraftCV seems like a no-brainer if you're applying to multiple jobs.

Congratulations

Congratulations on the launch 🎉 🎉

looks great, congrats! Will definitely be checking this out.

Loved the concept and came across while exploring ai india sumit. I would love to try it oas individual influencer.

What sort of listening does it do?

Great product! Does it do missed information detection as well?

Pretty excited on the applications around this

Nice :) Best of luck

Security tools have gotten good at spotting patterns. But attackers don’t think in patterns, they think in systems.

Claude Code Security reasons through your entire codebase like a human security researcher. It traces data flows, understands business logic, challenges its own findings, and then proposes targeted patches for human approval.

Not just “here’s a vulnerability.” But “here’s why it matters and here’s a fix.”

The adversarial self-verification step is especially interesting. Fewer false positives. More signal. Less wasted analyst time. Released in limited research preview, this feels like a shift from static scanning → contextual reasoning.

Hot question: does this make AI code review tools obsolete?

Short answer: not immediately.

Long answer: tools focused on PR reviews and developer productivity operate earlier in the lifecycle. Claude Code Security feels deeper, more like an AI security researcher auditing entire systems.

If it continues improving at finding novel, logic-level flaws (not just surface bugs), it could compress a huge amount of specialized security review work.

Obsolete? Probably not overnight.

Pressure on them to evolve? Absolutely.

What do you think... augmentation layer or category killer?

I lova Claude Code, but it's not so easy to optimize it for a beginner, so it seams I have to spend a high amount of hours to really understand, what is possible with this tool. But its great in total.

Pika AI Selves lets you create a living, persistent AI version of yourself... one that talks like you, posts like you, remembers like you and evolves over time. This isn’t just “AI that writes.” It’s AI with personality, continuity, and agency.

How to get started?

Upload your selfie. Clone your voice. Map your personality.

Then let your AI Self roam from Slack to social, staying aligned with who you are (or who you want to be).

It’s playful. It’s practical. It’s slightly unhinged in the best way.

We’ve seen AI copilots. This is something closer to a co-existence.

Over to you!

Okay but serious question… Is this the ultimate productivity unlock or the beginning of something mildly dystopian?

Would you create an AI version of yourself? Why or why not?

Hey Product Hunters 👋

Damn excited to finally share Scribble Pad, a complete and unique browser extension, with you all.

Have you ever wished you could just draw directly on a website while explaining something?
It started from a simple frustration, why is it so hard to quickly explain something on a website?

Every time I wanted to share feedback, report a bug, or explain an idea, I had to jump between tools. Screenshot. Editor. Annotate. Send. Repeat.

It felt slow.
It felt unnecessary.

So I built Scribble Pad, a tool that turns any website into your personal canvas.

✏️ Draw instantly.
📝 Write notes directly on the website that saves across browsing session.
📸 Capture and annotate screenshots.
⚡ All in real time.

No switching tabs. No friction. Just open a page and start thinking visually.

This is just the beginning, and I’d LOVE your honest feedback.
A complete life changing extension 😘

Oh, this is nice! This is way cleaner than screenshot > edit > send.

Do the notes/annotations stay private to you, or can you share a link with someone else so they see exactly what you marked up? That collaborative angle could be huge for async feedback.

It was fun, like a game to reduce my screen time

Thanks for Posting

There is a small suggestion whether the design or switch light color interface have not found a place, thank you

Hi all, I'm a hobbyist photographer and take photos and videos on my phone daily. I wanted to create a simple and delightful photos app to revisit my memories and shared albums with my family. I hope you enjoy it.