Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: What Are You Working On? (March 2026)

news.ycombinator.com

Post reply on HN
Print view View original

741–750 of 1001 posts

Re: Ask HN: What Are You Working On? (March 2026)

#741

Post by eugf_ »

Ordr — AI task manager for people with too much to do and too much in their head: https://useordr.app

Most productivity apps make you do the organizing — projects, tags, priorities, fields. That's fine when you're calm. It's impossible when you're overwhelmed.

I'm building for the moment when your brain is full and you just need to dump everything out. You throw in voice, text, images, links — Ordr calls an LLM to parse intent, extract tasks vs. events, assign order, and surface one clear next action. No tagging, no sorting, no deciding. Just: here's what to do next.

Built with Flutter + Supabase + Groq/Cerebras. Still early.

Curious if anyone here has hit this wall — tried every app, built their own system, still feels broken. What did you actually need that nothing gave you?

Re: Ask HN: What Are You Working On? (March 2026)

#742

Post by consumer451 »

consumer451 wrote: post #666

I just launched a free wysiwyg markdown editor. It currently uses only IndexedDB for storage making it as private as possible. The only network calls are polling for the "click to update" toast, and the feedback form. I was sick of getting cross-eyed when looking at tables in raw markdown and was just running it locally. This weekend I realized it might be useful for others. The goal was simple as possible UX. Open u…

Free multi-device sync is now enabled with email, github, and google OAuth. Of course, privacy is not guaranteed in that case. However, people wanted it for convenience.

I was really trying my best for friction-less UX on this project. I would appreciate any feedback on how I did, either by comment or the feedback button.

Re: Ask HN: What Are You Working On? (March 2026)

#744

Post by veverkap »

Recently two selfhosted open source file sharing platforms archived their repos indicating no further updates (most recently https://github.com/kyantech/Palmr).

I wanted an opportunity to learn more Svelte so I created Enlace which has a Go backend and Svelte frontend.

It's nearly complete but I would love any assistance with testing.

Re: Ask HN: What Are You Working On? (March 2026)

#746

Post by bilsbie »

swsieber wrote: post #737

I'm writing a print farm manager for my wife, who has 8 bambu printers. I've put one of them in lan mode for testing, but I'm pretty close to replicating the important handy (Bambu's cloud app) features, at which point I'll be able to start adding the really nice. She sells a product with 16 different printed parts, and she prints the parts in bulk batches across 7 different pause points, some of which have pause poi…

This is so cool. Why does 3d printing make sense vs injection molding? Low volume? To many customizations?

Re: Ask HN: What Are You Working On? (March 2026)

#747

Post by bilsbie »

I use iPhone notes to write down all my thoughts and things I want to track. I want to make an app that turns each one into a heading text, and AI generated image or short video. And then I can scroll through them like tik tok and interact with them by adding more notes, etc.

Re: Ask HN: What Are You Working On? (March 2026)

#748

Post by LavaDMan »

Building a self-hosted agentic OS I call AEGIS — Adaptive Execution & Generative Intelligence System. Running on a single workstation with a consumer GPU. The core idea is a three-tier model cascade: a cloud model handles architecture and review, a local 32B model handles execution and code generation, smaller local models handle evaluation. The cloud model never executes directly — it reviews diffs and approves before anything gets committed. The interesting problems so far: GPU arbitration across competing inference services using a distributed lock, giving local models read-only access to institutional memory before task execution so they're not flying blind, and autonomous fleet provisioning — I spun up a new server node last night without touching it after the USB went in. Next phase is adding department queues so the system understands context — infrastructure work vs. client consulting work vs. internal tooling — and idle-time priority advisory so it starts anticipating what I need rather than waiting to be asked. Goal is something closer to Jarvis than a chatbot. Early days but the bones are solid.
Post reply on HN