2025年7月10日 的 Show HN

Hey HN,

I'm a solopreneur and run a web design agency.

I create open-source apps, but I also work as a freelancer and designer. I was accepting any new freelance project via forms on my agency website.

I was using Typeform, but as time went by and more people submitted forms, it got more and more expensive. That time, I thought to use Google Form, but it was way too blocky and looked very unprofessional on my agency website.

So I thought to build my own forms for my own usage, and it turns out it almost doubled form submissions and inquiry calls.

I was happy, so I thought to build it for everyone and make it open-source.

I added AI functionalities using Vercel AISDK. I can generate forms almost instantly using AI and also added analytics AI so that users can talk with their forms—more like talk with their analytics data.

I hope this product will be as helpful to you as it was for me. Would love your feedback pls

Preet

Hey HN, we're a YC startup building an open-source, privacy-first alternative to Perplexity Comet.

No invite system unlike bunch of others – you can download it today from our website or GitHub: https://github.com/browseros-ai/BrowserOS

--- Why bother building an alternative? We believe browsers will become the new operating systems, where we offload much bunch of our work to AI agents. But these agents will have access to all your sensitive data – emails, docs, on top of your browser history. Open-source, privacy-first alternatives need to exist.

We're not a search or ad company, so no weird incentives. Your data stays on your machine. You can use local LLMs with Ollama. We also support BYOK (bring your own keys), so no $200/month plans.

Another big difference vs Perplexity Comet: our agent runs locally in your browser (not on their server). You can actually watch it click around and do stuff, which is pretty cool! Short demo here: https://bit.ly/browserOS-demo

--- How we built? We patch Chromium's C++ source code with our changes, so we have the same security as Google Chrome. We also have an auto-updater for security patches and regular updates.

Working with Chromium's 15M lines of C++ has been another fun adventure that I'm writing a blog post on. Cursor/VSCode breaks at this scale, so we're back to using grep to find stuff and make changes. Claude code works surprisingly well too.

Building the binary takes ~3 hours on our M4 Max MacBook.

--- Next? We're just 2 people with a lot of work ahead (Firefox started with 3 hackers, history rhymes!). But we strongly believe that a privacy-first browser with local LLM support is more important than ever – since agents will have access to so much sensitive data.

Looking forward to any and all comments!

Hey HN, Henry and Roman here - we've been building a cross-platform framework for deploying LLMs, VLMs, Embedding Models and TTS models locally on smartphones.

Ollama enables deploying LLMs models locally on laptops and edge severs, Cactus enables deploying on phones. Deploying directly on phones facilitates building AI apps and agents capable of phone use without breaking privacy, supports real-time inference with no latency, we have seen personalised RAG pipelines for users and more.

Apple and Google actively went into local AI models recently with the launch of Apple Foundation Frameworks and Google AI Edge respectively. However, both are platform-specific and only support specific models from the company. To this end, Cactus:

- Is available in Flutter, React-Native & Kotlin Multi-platform for cross-platform developers, since most apps are built with these today.

- Supports any GGUF model you can find on Huggingface; Qwen, Gemma, Llama, DeepSeek, Phi, Mistral, SmolLM, SmolVLM, InternVLM, Jan Nano etc.

- Accommodates from FP32 to as low as 2-bit quantized models, for better efficiency and less device strain.

- Have MCP tool-calls to make them performant, truly helpful (set reminder, gallery search, reply messages) and more.

- Fallback to big cloud models for complex, constrained or large-context tasks, ensuring robustness and high availability.

It's completely open source. Would love to have more people try it out and tell us how to make it great!

Repo: https://github.com/cactus-compute/cactus

Hi HN,

After spending some time with the new `flux kontext dev` model, I realized its most powerful capabilities aren't immediately obvious. Many people might miss its true potential by just scratching the surface.

I went deep and curated a collection of what I think are its most interesting use cases – things like targeted text removal, subtle photo restoration, and creative style transfers.

I felt that simply writing about them wasn't enough. The best way to understand the value is to see it and try it for yourself.

That's why I built FluxKontextLab (https://fluxkontextlab.com).

On the site, I've presented these curated examples with before-and-after comparisons. More importantly, there's an interactive playground right there, so you can immediately test these ideas or your own prompts on your own images.

My goal is to share what this model is capable of beyond the basics.

It's still an early project. I'd love for you to take a look and share your thoughts or any cool results you generate.

Hey HN,

I spent 30 years writing CAD plugins in C++, mostly in Visual C++ 6.0. Then the industry collapsed. And I lost an intellectual lawsuit, my income dried up, and my marriage ended.

Now I live alone in a trailer in rural Canada — still writing code, still surviving, trying to crawl back.

This is a short video I made (50 seconds), documenting a quiet moment from this strange life. If you’ve ever hit rock bottom and kept going, you might relate.

https://youtube.com/shorts/dDLSd3pfIYI?feature=share

Thanks for watching. Just sharing — not selling anything.

Today marks ten years, 3652 consecutive days, of running at least one mile every day under the USRSA rules [1]. To celebrate, I built an interactive dashboard that turns a decade of GPX files into charts you can explore.

Running has truly changed my life: I've made lifelong friends, explored beautiful places, and more importantly invested into my own health and fitness, which I'm starting to see the positive benefits as I get older.

The stack is pretty simple: a NextJS app, with a Postgres database to keep all my running data, and all the stats are pre-computed and cached in Redis, so I effectively only hit the database once a day when a new run is ingested. On the fronted, I toyed with the idea of using D3 or pre-existing data viz libraries, but ended up rolling my own using SVGs directly, it gave me more control on the visualizations.

I used the Strava bulk export to pre-populate the database, and I'm using their webhook API to do incremental updates. I have to tap into OpenWeatherMap and OpenCageDate to enrich the running data a little bit.

Happy to answer anything about the stack, data pipeline, or how I stayed motivated for 10 years!

[1] https://www.runeveryday.com Run Streak Association rules: ≥ 1 mile per day

My kids are endlessly curious, always asking questions like “Why do stars twinkle?” or “How do volcanoes erupt?” I love their curiosity, but I found myself constantly searching for good ways to answer them, and without adding more screen time to their day.

Podcasts are great, but kids’ podcasts are often generic and don’t cover their specific questions. I wanted something more personal and engaging.

So I built WonderPods - an app that creates personalized podcast episodes to answer whatever they’re curious about, even saying their name in the story. It turns their curiosity into fun, screen-free learning moments, whether at bedtime or in the car.

We just launched, and there’s a free trial. I’d love your feedback on the idea, the experience, and any thoughts you have on making it better.

Hey HN,

A few years ago, when I was working as a freelance web developer, there were many projects that used repetitive layouts and designs

That's when I built my own collection of basic UI components like buttons and all. At that time, I was using CSS, so I styled my components using CSS. Later, I decided to open-source these components, and that’s when I created HextaUI

After a few months, I found out about Tailwind CSS, so I decided to recreate all components with better design, modularity, and accessibility. This time, I also added animated components, not just base components. After building and launching, I left it and went on a break. (It didn’t get any response because I didn’t know marketing.)

Two months ago, I decided to rebuild the entire project—but this time, I wanted to scale it and make it stand out, because there’s a lot of competition. So I rebuilt all base components, made them last versions, and gave it my all

This time, it got a great response in fact, it crossed 50k visitors in just 72 hours

Looking at the response and demand, I created pre-built blocks using the base components and launched them at a minimal price. That also blew up and crossed more than 10 sales and crossed $500 revenue in just 24 hours. I was selling pre-built website blocks and UI components.

What I learned: product matters the most. No matter how many competitors are out there, people still buy good products. If you think, “People are already building what I’m building,” or “There are better options” then build something better. Make something specific. Niche down under that same niche

Just build it.

Preet

I made a tool to make LinkedIn posting feel less like a chore.

it’s called Linkgenie, and I just opened it up for early users.

Using Claude for generating post and get for hooks its saves you time.

I’d love if you gave it a try + told me what’s missing, what slaps, and what needs a glow-up.

Howdy All

We've finally made our product public and available for self-serve. groas is an AI agent ecosystem for optimising every single part of your google search campaigns, from building custom dynamic landing pages to 24/7 keyword research.

Any marketing gurus would be great to get you on it!

Peace

DP

Hey HN,

Prasad here, I've been using cursor from very early days.

Adding rules to my project really improved the quality and the Autonomity of cursor agent, but it took a good bit of time for me to do that manually.

So I built a tool to generate rules based on the technology and various preferences.

Please check it out.

https://cursor-rules-generator.xyz/

Hi HN,

I built Activiews as a fitness alternative for Apple users who want a simpler, more private, and more visual way to view their workouts, with a heavy focus on maps.

The app reads from Apple Health and Watch data without requiring an account or sending anything to the cloud.

I built it because I wanted a fitness app that:

   - Has no social network features

   - Does not store my data on their servers

   - Doesn't require an account or login

   - Stays lightweight and free of bloat

   - Is simple to use, with a focus on customizable workout visuals

Core features:

   - Customizable workout maps and shareable cards

   - Flyover route animations

   - Calendar heatmap showing activity over time

   - Offline-first, data stays on device, no login/account needed

   - Dark/light themes, map styles, unit system, and accent color customizations

   - Reads data directly from Apple Watch

   - Localized in 13 languages

   - €0.99/month or €24.99 lifetime

It’s built in Swift & SwiftUI using native APIs and focused on performance and privacy. I’d love your feedback, ideas, and comments.

App Store:https://apps.apple.com/de/app/activiews/id6747010245

Website: https://activiews.xyz

Thanks!

I built Hapstack - an ultra fast, lightweight browser extension for Google Workspace that gives you instant visibility into your SaaS stack—what tools are being used, by whom, and how often.

* Deploys in 60 seconds * See 6 months of historical app usage * Uncover underused tools, shadow IT, and category overlap * Reduce wasted spend and simplify offboarding

No surveys, no setup. All your tools are tracked automatically.

I’d love your feedback and are offering early users free access.

Try it out: https://www.hapstack.com

I built a free tool to generate realistic-looking credit card details for testing payment forms, checkout flows, and frontend validation.

Key features: Supports 15+ networks: Visa, Mastercard, Amex, Discover, RuPay, UnionPay, JCB, Maestro, and more

Region-specific formats with a valid Luhn check

Interactive UI with card flip animation

Copy to clipboard or generate a QR code of the card details

No signup, no backend — works offline as a PWA

No tracking or data is stored anywhere

Use case: Testing UIs, building demos, or teaching how payment flows work, without using real card data.

Would appreciate feedback or suggestions from the community!

https://goonlinetools.com/credit-card-generator/

I built SimRepo, a browser extension that adds a “Similar Repositories” panel directly into GitHub repo pages (for repos with 150+ stars). It's useful for discovering related projects while browsing. It's based on a vectorized model trained on GitHub star data.

Repo: https://github.com/Mubelotix/SimRepo Chrome/Firefox support, no tracking, fully open source.

Would love feedback on the recommendation quality or UX!

This afternoon, I used Claude Code to quickly build a tool for browsing Hacker News Show HN projects. The UI and database came together in one go, with some final tweaks and mobile optimization. From start to deployment, it took about 30 minutes.

Planning to add product analytics features soon.

Hope you find it useful!

https://buzz0.com

Hi HN! I built arxiv explained (https://arxivexplained.com) to make AI research accessible to everyone.

What it does: It's a free app with audio explanations of the latest AI research papers. Each paper gets a ~5 minute breakdown in simple language - no jargon, just clear explanations of what the researchers did and why it matters. Key feature: The app already comes loaded with all the popular and recent AI papers, so you can browse and discover the latest research right away. You don't need to bring your own papers - just open the app and start exploring what's new in AI.

How I use it: I pop in my earbuds during my commute or while doing chores and listen to explanations of cutting-edge research. It's like having someone explain the latest breakthroughs to you in plain English.

You can also paste any arXiv link to get a custom explanation, but most people just browse the curated collection of recent papers that's already there. Technical note: It uses AI to analyze papers and generate natural-sounding audio explanations focused on clarity over complexity.

Would love to hear your feedback, especially if you try it with papers from your field!