2025년 10월 15일의 Show HN

I started working on Halloy back in 2022, with the goal of giving something back to the community I’ve been a part of for the past two decades. I wanted to create a modern, multi-platform IRC client written in Rust.

Three years later, I’ve made new friends who have become core contributors, and there are now over 200 people idling in our #halloy channel on Libera.

My hope is that this client will outlive me and that IRC will live on.

I built Trott out of frustration with my own “Saved” folders on Instagram and YouTube. I’d save reels and shorts—workout tips, recipes, travel spots—thinking I’d find them again later. But, like most people, I ended up with a black hole of unsorted videos: no search, no filters, and if I ever did find the right video again, I’d have to dig through the whole thing just to get that one detail I needed.

When I tried looking for solutions, I found only genre-specific apps or tools that demanded manual uploads or new workflows. None felt like they understood how real users behave or save content. So I decided to build Trott.

What makes Trott different?

You can share any Instagram Reel or YouTube Short (TikTok support launches next week) to Trott, straight from your phone’s native share menu—no manual uploads.

Trott uses AI to extract relevant info automatically (ingredients, places, products, etc.) and sorts everything for you.

It’s fully searchable with natural language. Just type something like “that Kyoto café from Instagram” and Trott finds it.

For travel videos, it can even produce Google Maps routes from extracted locations.

App Store: https://apps.apple.com/in/app/trott/id6751728352 Play Store: https://play.google.com/store/apps/details?id=in.hattimatiml...

I’d love to hear how you organize your own saved content—or if you’ve just given up and let it pile up like I used to. Open to all questions, feedback, and bug reports. Happy to discuss the tech details behind Trott if you’re interested!

Hi folks! Iman and I (Fabian) have been building Specific for a while now and are finally opening up our public beta.

Specific is a platform for building backend APIs and services entirely through natural-language specifications and tests, without writing code. We then automatically turn your specs into a working system and deploy it for you, along with any infrastructure needed.

We know a lot of developers who have already adopted spec-driven development to focus on high-level design and let coding agents take care of implementation. We are attempting to take this even further by making the specs themselves the source of truth. Of course, we can’t blindly trust coding agents to follow the spec, so we also support adding tests that will run to ensure the system behaves as expected and to avoid regressions.

There is so much ground to cover, so we are focusing on a smaller set of initial features that in our experience should cover a large portion of backends:

- An HTTP server for each project. Authentication can be added by simply stating in the spec how you want to protect your endpoint.

- A database automatically spun up and schema configured if the spec indicates persistence is needed.

- External APIs can be called. You can even link out to API docs in your specs.

You currently can’t see the generated code, but we are working on enabling it. Of course, we don’t claim any ownership of the generated code and will gladly let you export it and continue building elsewhere.

Specific is free to try and we are really eager to hear your feedback on it!

Try it here: https://app.specific.dev

HN,

I'm stoked to share this product I've been working on non-stop for the past few weeks. It's an immersive GUI experience for working with many coding agents in parallel. The UX should be familiar to Claude Code users, but we took advantage of the GUI nature to add in a bunch more.

cmux is early but certainly usable—almost all of our internal cmux development rolls through cmux itself. Please let me know your thoughts and feedback!

Hi HN,

We're building Kexa.io (https://github.com/kexa-io/Kexa), an open-source tool developed in France (incubated at Euratech Cyber Campus) to help teams automate the often tedious process of verifying IT security and compliance. Keeping track of configurations across diverse assets (servers, K8s, cloud resources) and ensuring they meet security baselines (like CIS benchmarks, etc.) manually is challenging and error-prone.

Our goal with the open-source core is to provide a straightforward way to define checks, scan your assets, and get clear reports on your security posture. You can define your own rules or use common standards.

We'd love for the HN community to check out the open-source project on GitHub. Feedback on the concept or the current tool is highly welcome, and a star if you find it interesting helps others discover the project!

If you're interested check out website we also have an offer with dashboard, no-code rule builder,..

Hi HN,

I built Pxxl App — a free web hosting and deployment platform for developers in Nigeria and beyond. It’s a Nigerian alternative to Vercel, Render, and Netlify, designed for those who want a simple, fast, and barrier-free way to host both frontend and backend apps.

With Pxxl App, you can connect your Git repo and deploy in seconds — no credit card, no limits. You’ll get a live subdomain like yourapp.pxxl.pro, automatic builds, and continuous deployment.

It supports: • Frontend frameworks: React, Next.js, Vue, Svelte, and more • Backend projects: Node.js, PHP, and Python • Features like environment variables, CI/CD, and instant rollback

The goal is to make cloud deployment accessible to African and global developers without the typical payment or region restrictions.

It’s completely free to start, and I’d love to hear feedback from the HN community on how to improve it or what features you’d want next.

Check it out: https://pxxl.app

Hi there, Enes here, first-time founder, and I am excited to share Xona.ai with you!

We've been working on this project for the past several months and launched our beta in April. Since then, we have attracted over 10,000 users, and I couldn't be happier with the results.

Xona.ai makes it incredibly easy to generate beautiful redesigns of your home within seconds. Our focus is on usability and design. We collaborate with experienced interior designers, and our customers love the handcrafted design styles we offer. We've invested countless hours in prompt engineering to get the most out of our models. Of course, you can also create your own prompts.

At Xona, we are aware that AI-generated images are not always perfect. To address this, we've developed a set of tools to improve the results. Our features include:

Magic Eraser: Erase small mistakes (similar to cleanup.pictures). Creative Upscaling: Enhance generated images by upscaling them (thanks to clirityai.co). Find and Replace: Easily change materials or colors of items, like flooring or couches. Google Lens Integration: Love the generated sofa? Find similar furniture with Google Lens. Feeling overwhelmed by the options? Don't worry, we provide short tutorials to help you get the most out of Xona.

And we're not stopping here. We are currently experimenting with Virtual Staging. After evaluating competitors' offerings, we believe we have a solution that will surpass everything currently available on the market.

One last note: we dislike subscriptions as much as you do. You can get 4 credits for free, and a single purchase unlocks all the extra features (Magic Eraser, Find and Replace, Upscaling) for a lifetime.

Thank you for your attention, and we hope to see you at https://xona.ai!

I modeled it after last year's Project Skydrop (http://projectskydrop.com)

* 24/7 web cam trained on the treasure of $26k in gold coins * shrinking circle (100 miles today) showing its location and updating every morning * premium option for aerial photos that go higher and higher every morning. $10 from every premium upgrade goes towards the pot

Over 5k people have joined so far. Good local media attention but nothing national yet. There's a private community for premium users and it's actually been pretty fun with people posting photos of their hikes and sharing their updates.

If you've ever thought about doing something crazy like this feel free to AM(almost)A about the hunt

Osaurus is an open-source local inference runtime for macOS, written in Swift and optimized for Apple Silicon.

It lets you run Apple Foundation Models locally — fully accelerated by the Neural Engine — while also exposing OpenAI- and Ollama-compatible endpoints, so you can connect your favorite apps, tools, or clients without any code changes.

Key points:

* Supports Apple Foundation Models natively

* Compatible with OpenAI & Ollama APIs

* ~7 MB binary, runs locally (no cloud, no telemetry)

* MIT Licensed, open source

Project: https://osaurus.ai

Source: https://github.com/dinoki-ai/osaurus

We’re exploring what a local-first AI ecosystem could look like — where inference, privacy, and creativity all happen on your own hardware. Feedback and testing welcome!

Discover professional nano banana prompts and banana image prompts created by our AI prompt generator. From nano banana model prompts to gemini banana prompts, explore the best banana AI prompt examples for stunning image generation with nano banana image prompts.

Features: - uses your Claude subscription (no extra LLM API cost) - actually looks at the code (not only docs like .md) - supports private repos with Github PAT - semantic search using qdrant(oss) - mcp integration - data stays in your machine - use gemini embedding (local model WIP)

Quickstart: git clone https://github.com/cheolwanpark/snippets && cd snippets cp docker/.env.example docker/.env # Add CLAUDE_CODE_OAUTH_TOKEN & EMBEDDING_API_KEY docker-compose -f docker/docker-compose.yml up -d claude mcp add --transport http snippets http://localhost:8080/mcp

When Claude Code makes changes, giving targeted feedback is annoying. You have to switch back to chat and explain "actually, change line 47-65...."

I built a VS Code extension that adds inline comment boxes directly on git diffs. Click a line or select multiple, type what you want changed, hit send -> goes straight to Claude Code's terminal with the exact diff context.

Makes the feedback loop way faster when you need surgical edits instead of re-explaining the whole file.

Its free and open source.

I’ve been exploring how we might treat knowledge as a geometric structure instead of a collection of embeddings. KAG (Knowledge as Geometry) positions facts, classes, and instances in a shared coordinate space — making retrieval spatial, about distance, density, and context rather than simple vector similarity. It’s an early-stage research prototype — not production-ready, but meant to spark discussion. I’d love feedback from people working on retrieval, embeddings, or conceptual modeling.

I've been coding with coding agents for a while now and ran into the same issue of ending up with 400+ markdown files. so i built a tool that lets coding agents track issues.I found it to be more useful that tracking markdown files. Hope it will be useful for you guys as well.