Show HN for July 9, 2025

I was looking around for an MCP server that could connect Anna's Archive to Claude Desktop, as I wanted to be able to search and download books directly through the interface.

I couldn't find any public implementations, so ended up building one myself.

What it does?

- It searches Anna's Archive by keywords. - It downloads books from search results. - It works directly in Claude Desktop through MCP.

Check out the repository's README for detailed installation and configuration instructions.

The code is fully open source and builds run on GitHub Actions for transparency.

I figured I'd share, since I couldn't be the only one wanting this functionality!

I have a large collection of music files gathered over the years, so I was sorely missing a decent offline music player that can serve as a frontend for the collection. I tried several Mac apps over the years, but since streaming music is mainstream now, there aren't good offline music players that meet my needs. So I spent the last 3 months building Petrichor! The idea is to solve my problem and learn Swift UI development along the way, while giving back to the community with this open-source project! Here's a list of features it has, with more getting added in future;

- Everything you'd expect from an offline music player!

- Map your music folders and browse your library in an organised view.

- Create playlists and manage the play queue interactively.

- Browse music using folder view when needed.

- Pin anything (almost!) to the sidebar for quick access to your favourite music.

- Navigate easily: right-click a track to go to its album, artist, year, etc.

- Native macOS integration with menubar and dock playback controls, plus dark mode support.

- Search quickly through large libraries containing thousands of songs.

The app is still in alpha, so things may look unpolished, but I've been testing the alpha builds for the past few weeks and fixing issues as I find them for v1 release. I welcome any feedback (and contributions!) on GitHub repo. Please give it a try and let me know what you think!

Hey Hacker News,

I'm a long-time lurker and wanted to share a project I just finished building.

Like many React Native developers, I needed to add marker clustering to a map in my app. The most popular library for this, react-native-maps-clustering, was fantastic in its day but has become outdated and no longer works with modern versions of Expo, React Native, and their dependencies.

After hitting a wall of compatibility issues, I decided to take on the challenge of rewriting it from the ground up, focusing on a modern toolchain and a better developer experience.

The journey was a lot more challenging than I anticipated. It turned into a deep dive into solving dependency hell with different versions of @types/react, wrestling with build tool configurations for pnpm, bob, and ESLint, and ensuring everything was strictly typed with TypeScript. It felt like a classic case of yak shaving, but I was determined to create a solution that "just works" for developers today.

The result is RN Super Cluster, a performant, fully-typed, and easy-to-use clustering library for react-native-maps.

What it does: It provides a <ClusteredMapView /> component that you can use as a drop-in replacement for the standard <MapView />. Any <Marker /> components you place inside will be automatically clustered.

Key Features:

    Modern & Maintained: Built with a modern toolchain and designed to be actively maintained.

    Fully-Typed: Written entirely in TypeScript to prevent common errors and improve autocompletion.

    High-Performance: Uses supercluster under the hood for extremely fast geospatial clustering.

    Spiderfier: At the maximum zoom level, overlapping markers automatically "spiderfy" (spread out on a spiral) so they can be individually tapped.

    Customizable: You can provide your own custom components for rendering clusters, and callbacks for handling press events.

This was a passion project born out of necessity, and I hope it can save other React Native developers the headaches I went through.

I would love to get your feedback, and contributions are more than welcome!

GitHub: https://github.com/suwi-lanji/rn-maps-clustering NPM: https://www.npmjs.com/package/rn-maps-clustering

Thanks for checking it out!

Hi HN! I'm Karl one of the co-founders of Stravu. (https://stravu.com) Using AI for work 24x7, we realized that four things would make AI more useful for us and a lot of other power users and teams:

Editable output: AI gives output that is half right and our only option was to either keep chatting laboriously or copy it to a Google Doc. We made Stravu so you can edit what the AI says in chat or in an attached notebook. Everything editable.

Approve AI changes: When AI makes a change to some text, you can't tell what changes. We put Red/Green diffs that you can approve into Stravu.

Unify text, tables, diagrams: We were jumping between tools to work with AI on text, tables, diagrams, etc.. Just because Microsoft did that 30 years ago, doesn't mean it makes sense now. We made Stravu so you can work with AI across text, tables, diagrams, (and 2x2s, formulas, more soon) and have them inform each other.

Actual multi-player team collab with AI: We couldn't collaborate as a team in AI (even with the ChatGPT Teams plan). We wanted to be able to chat with AI together as a team or see the changes AI was making in the canvas/notebook together and edit together. So we made Stravu support multi-player collaboration in every aspect... chats, notebooks, text, tables, diagrams..etc.

Some of the use cases of our current Beta customers include: scrum teams doing feature/customer/competitive research and feature definition, account teams building vertical/geo/account plans, consultants and investment teams working on market/company analysis.

We are currently in beta and actively iterating based on user feedback. Please try it out at: https://stravu.com We highly value your feedback!

Built this Python package because I wanted to run hardware controlling ML stuff and other control algorithms directly connected to industrial I/O hardware without jumping into annoying PLC toolchains (Windows only, licensing hassle, no editor choice, proprietary version control - you name it). For sure its not for ms‑cycle loops, or uptime critical production stuff, but in applications with relaxed timing it allows for fast iteration on the setup - making prototyping a pleasure. Its easy to use, has no dependencies beside Python, its fully type annotated and MIT licensed. Internal it uses ModBus/TCP for hardware communication, the implementation is exposed, so it co-serves as ModBus/TCP client library.

I'd love to hear your use cases, feature ideas and PLC toolchain stories ;)

Docs: https://nonannet.github.io/pyhoff

Hi HN, I'm 11 years old and I'm learning to code with the help of AI. I recently created my own social media app inspired by TikTok and short videos. I built it from scratch using my Android phone and some programming apps like Replit and Base44. The idea is to allow users to post and watch short videos, follow others, and use a like-based system. I created the interface and logic myself, and AI helped me when I got stuck on bugs or needed help understanding something. This is my first serious project, and I'd love to get feedback from real developers and creators. Here's the link: *[https://app--woo-short-78d020b9.base44.app]* What do you think? What should I improve next? Thanks for reading

built snub, a fast and lightweight recursive file search tool for Windows, written in modern C (C17). File Explorer and PowerShell often crawl on large codebases — so I wrote something that doesn’t.

snub is: - Fully multithreaded - Avoids indexing entirely - Supports globbing, size/date filters, result limiting, and JSON output - Packaged as a single small executable

No dependencies. Just raw C and the WinAPI.

GitHub: https://github.com/seeyebe/snub

Would love feedback on C idioms, WinAPI practices, or ideas for portability and better build flow.

I just launched Piplo on the iOS App Store tonight. Piplo helps you stay in touch with the people who matter to you. It provides smart reminders, flexible scheduling, and a simple design to make relationships feel natural again.

I hope that Piplo will serve you well. Please download and don't hesitate to use the feedback link in the app! Piplo will remain 100% free (i.e. no ads, in-app purchases) and, if you really insist on showing your appreciation, I added a link in the app settings to a Doctors Without Borders fundraiser.

Hi HN,

I've built my dream Chrome screenshot extension, "Schnippi," a combination of features I couldn't find in any other extension.

Features include:

- Optimized for Speed: Reduce the number of key presses or clicks to capture and export (download/copy) a screenshot. With one key press and one click, you'll have a screenshot in your clipboard or download folder.

- Flexible Capture and Selection: Capture any visible HTML element and cycle through the element hierarchy to refine your selection. You can also capture a free-form rectangle or the full viewport.

- Source URL Inclusion: Export your screenshot with the source URL of the captured page.

- Multiple Export Options: Copy to clipboard or download in various formats.

- Zoom-Friendly: Works well with "zoomed-in" pages.

- Privacy-Focused: No server uploads of your screenshots or any data collection.

- Clean UI: Neutral and minimal graphical user interface.

It's completely free! You can try it out here: https://chromewebstore.google.com/detail/schnippi-screenshot...

Why Screenshots Are Great:

- Speed: Unless it's raw text, taking a screenshot is often the fastest way to capture information or data from a website.

- Context: Screenshots can provide essential context around the captured data.

- Universal Format: Most word processors, note-taking apps, email clients, LLM chats, and search engines support image input.

A Problem Schnippi Solves:

An issue with just a PNG file of a screenshot is that an important piece of information is lost: the URL of the captured page. It's like a citation without a source. A screenshot without the page URL is often not very valuable, as you can't easily get back to the page to verify information or learn more about the context.

To fix this, Schnippi allows you to "Copy as HTML," which includes both the URL of the captured page and the image PNG. Many apps support this format, including Google Docs, Gmail, Apple Notes, Pages, Microsoft OneNote, and Word, among others.

How I Use Schnippi:

- For any kind of research or collecting visual inspiration for a project.

- Taking a screenshot of a data graph to share with a colleague. With "Copy as HTML" I don't need to copy the link to the page separately.

- Capture and copy a screenshot from the clipboard to a search engine / llm chat.

- Note down a piece of information including the source URL.

What's next:

I am planning to add the option to annotate the screenshot with text and shapes like arrows, rectangle or circles.

I'd be happy to hear your feedback! Thanks!

Hi HN, I just launched Todo2 – an AI-powered project management extension for the Cursor AI editor. I built Todo2 after getting frustrated with leaving my IDE to plan tasks in ChatGPT/Perplexity. It lets you create todos by simply prompting, auto-researches latest best practices, and keeps everything inside Cursor. It’s free with 14-days trial on the Cursor Marketplace. Would love your feedback or questions! Thank you - https://todo2.pro

KCast is a KDE Plasma 6 widget that lets you cast video files or youtube URLs to a Chromecast devices in your local network.

me and my friend built leaves, an obsidian plugin that automatically archives notes unless you actively tend to them (by editing or linking).

we thought of it after reading this article https://medium.com/westenberg/i-deleted-my-second-brain-b7a6.... most of our "second brain" content is just digital hoarding. notes without context or connections die after a set time, making space for what actually matters.

do you think artificial scarcity/decay could improve pkm systems? have you tried similar approaches to combat information overload in your own workflows?

We created a tool that helps discover “stars” within a team: match a business task to the team skills, spot those who can handle it better, and create a training program for the missing knowledge.

How it works — https://nordstars.ai/

You can also play around with it and test it with your team (no login required):

Add team members and their skills. Enter the business goal. Generate a program for the skills your team is missing or needs to improve to handle the task.

Hi HN!

We’ve built RecomPal, a no-code AI chatbot designed specifically for Shopify stores. It helps merchants increase conversion rates and average order value by assisting shoppers in real-time—just like a human sales rep.

Key features: Plug & play installation (2 minutes)

Understands customer intent and recommends products

No scripting or flow-building required

Privacy-first: no data sharing with third parties

We’ve seen up to 30% sales increase in early tests with small-to-medium stores.

We’d love your feedback, feature suggestions, or ideas on how we can improve. Try it out: https://recompal.com

Thanks! – Team RecomPal