2026년 3월 20일의 Show HN

Yes, that Fortran.

Email is one of those tools we check daily but its underlying experience didn’t evolve much. I use Gmail, as probably most of you reading this.

The Arc browser brought joy and taste to browsing the web. Cursor created a new UX with agents ready to work for you in a handy right panel.

I use these three tools every day. Since Arc was acquired by Atlassian, I’ve been wondering: what if I built a new interface that applied Arc’s UX to email rather than browser tabs, while making AI agents easily available to help manage emails, events, and files?

I built a frontend PoC to showcase the idea.

Try it: https://demo.define.app

I’m not sure about it though... Is it worth continuing to explore this idea?

I go on a lot of backcountry trips where I barely get cell service. If my group splits, nobody knows knows where anyone is until you regroup at camp or at your destination. You can buy Garmin radios or try to set up an ATAK, but ATAK is Android-only and assumes you have a TAK Server running somewhere to make use of all of the functionality. Cool tools themselves, but expensive to set up correctly. I just wanted two iPhones to share their location directly over Bluetooth when cell coverage was lacking.

Red Grid Link does that. Start a session, and anyone nearby running the app shows up on your offline map. When they walk out of range their marker stays as a "ghost" that slowly fades.

The hard part was making sync reliable over BLE. The connections drop all the time. Someone turns a corner, walks behind a vehicle, whatever. I built a CRDT sync layer (LWW Register + G-Counter) so there's never merge conflicts. Each update is just under 200 bytes (from what I have tested so far). When a user/teammate disappears the app does exponential backoff from 2 to 30 seconds before giving up and marking them as a ghost.

Everything is encrypted (AES-256-GCM, ECDH P-256 key exchange per peer pair). Sessions can require a PIN or QR code to join. It also offers offline topo maps with MGRS grid coordinates, same system as in my other app, Red Grid MGRS.

The app is free, and I'm looking for some honest feedback from other real-world users. Let me know if you have any questions!

Over the last months, more people are shipping small apps, experiments, and side-projects at a much higher pace. I'm one of them and initially created a showcase page for myself to track them but this week decided to create something for others.

Happy to read feedback on how to improve it further!

As I started building AI integrations, I came to realize that for many projects, the the best agentic experience is one that simply enables the user's personal agent to take actions within your app.

The existing options like MCP or A2A are quite involved and for simple apps that are already URL parameter driven, those options seem like overkill.

This led me to prototype the Agent Use Interface (AUI) spec.

The idea is simple: a lightweight, open spec that makes any app "agent-navigable." You drop an XML file at /agents/aui.xml that describes the URL-parameter-driven actions your app supports, like search, create, filter, etc. And that way any AI agent can read aui.xml, understand what's possible, and construct URLs on behalf of the user.

That's it. No SDK. No auth flow. No API keys. Just a catalog of what your app can do, written for LLMs to understand.

Is there something like this that already exists? Is the approach too simple to be useful?

If your app already supports Universal Links or is otherwise URL parameter driven you could probably add support for AUI in an afternoon.

See a working example: https://habittiles.app/agents/aui.xml

Hello! I've been working on this for a couple years and I think it's finally reached a "okay maybe it's complete enough that other people can use it and I can take a break" point. I've been dog fooding it for maybe 6mo now.

I think the readme has a lot of accessible info including an actual description, but to add on: I wanted one piece of software to organize everything. No plex, uhh tachiyomi?, that other thing that's kind of like plex but for audio, obsidian, the other thing, that dropboxy thing, with different UIs, different logins, different databases, backup + restore methods.... I just wanted one thing. So I made this.

Given the breadth of use cases there's still infinite things I'd like to add. Some of the tools are bare bones at the moment. I'm not sure if the web is good enough for consuming video. Gamepad input in case you use it on a TV. It probably needs optimization, maybe at a level that's beyond me (it does work okay with my collection of a few thousand cds/hundred comics/tens of movies+tv FWIW). Better content import tools (browser plugin?). A graph-like graph visualization. Things for uploading directories verbatim, so the data can be tagged/related later. I'm not sure a lifetime would be enough to do everything myself, so I'm trying to keep my own scope limited.

But I think it's pretty cool where it is now!

I'm probably going to take a break for a bit (I will try to respond to bugs) but I'd love to get some feedback for my next pass.

I’ve spent the last year getting back into film and testing a bunch of screenwriting software. After a while I realized I wanted something different, so I started building it myself.

This has been a super fun project - with the core text engine written in Rust.

i built a small site to collect memories of the things we grew up with: floppy drives, Game Boys, cassette tapes, forgotten software, classic games. the tech stack is React, Supabase and Vercel.

fair warning: the items on there right now were seeded by AI to get things started. the goal is for it to grow through community submission. there's a submit form, no account needed.

i'd love to gather some early feedback and get some more ideas. something i was thinking about in the future is having users create accounts to favorite items and comment their own personal experiences with items. right now everything requires manual approval but in the future i'd like to push that towards the community.

thanks for looking!

You meet 20 people at a meetup/hackathon. You remember 3. The rest? Lost in a sea of business cards you never look at and contacts with no context. Build this to solve that particular problem which granola, pocket or plaude is not solving. Feedback is well appreciated.

I was tired of stitching together Langfuse for tracing, promptfoo for red teaming and evals, and custom scripts for CI/CD. It was a mess so I built EvalsHub.

EvalsHub does all of it in one place. Automatic production scoring, red teaming, prompt versioning, and CI/CD integration. Zero to full eval coverage in 30 minutes.

Would love brutal feedback from anyone shipping AI in production.

evalshub.ai

Hi HN,

This is a small python app with optional webUI. It is intended to be run locally. It can be run with Docker (cookie autodetection will not work).

It allows you to download a single substack, either entirely or partially, and saves the output to an epub file, which can be easily transferred to Kindle or other reading devices.

This is admittedly a "vibe coded" app made with Claude Code and a few hours of iterating, but I've already found it very useful for myself.

It supports both free and paywalled posts (if you are a paid subscriber to that creator).

You can order the entries in the epub by popularity, newest first, or oldest first, and also limit to a specific number of entries, if you don't want all of them.

You can either provide your substack.sid cookie manually, or you can have it be autodetected from most browsers/operating systems.

Hi OP here,

This is a chrome extension where you can add a nostalgic CRT Retro Effect on any website. Currently comes with presets from 1920s Mechanical to 1990s Color CRT display. It was fun to develop, hope you enjoy it as well.

I needed to remove sound effects and limit min animation frequencies due to health concerns.

Oscillating sound effects was risky for younger people, and low frequency was risky for photosensitive people.

Planning to add some sort of sounds effects later on by using a different method but I think flicker effect is good enough as is.

Any feedback is welcomed and much appreciated.

Thanks in advance!

mostly vibe-coded in 2 days, only contributed ~5 core insights, the rest is all opencode (trying it for the first time, it was ok)