Live data from Hacker News

Ask HN: What are you working on? (September 2025)

news.ycombinator.com

691–700 of 1001 posts

Re: Ask HN: What are you working on? (September 2025)

#691
I'm on the cusp of launching an interior design software I have built with my partner (she's the interior designer, I'm the coder).

https://inspec.design

My read of the industry in terms of software is that it's split into 3 groups:

1. Interior visualisation (basically 3D renders) which largely target the what-if amateur market

2. Big, clunky and old software tools for professional interior designers working on huge projects, which works well but has that universal sort of mild dislike to strong disdain depending on the person

3. New players who want to replace the old clunky software

Seeing this, we decided not to try to overthrow the old all-powerful project management solution, but rather to replace a single process in the interior design workflow. And of course to do it very well.

Re: Ask HN: What are you working on? (September 2025)

#692

Building https://multi.dev , an AI coding agent with bunch of FOSS contributors We took a great amount of learning from tools like Cline, Roo.. After spending some time on their tech as active users/devs, we decided to build multi from scratch with drastically different take on core features, tech stack, ux/devex.. If you are an active user of similar tools, and/or want to try multi.. We want to hear from you. -- edi…

I’ve been using tools like Cline and Roo-Code quite a bit, and the idea of rethinking the core stack/UX from scratch resonates a lot. The agent workflow and devex feel like the hardest problems to get right, so I’m curious how Multi approaches context management and long-running tasks compared to the others. Excited to see it open-sourced and will definitely give it a spin.

Re: Ask HN: What are you working on? (September 2025)

#693
post #10

Currently a one-man side project: https://laboratory.love Last year PlasticList discovered that 86% of food products they tested contain plastic chemicals—including 100% of baby food tested. The EU just lowered their "safe" BPA limit by 20,000x. Meanwhile, the FDA allows levels 100x higher than what Europe considers safe. This seemed like a solvable problem. Laboratory.love lets you crowdfund independent testing of s…

I love this!

I keep telling my euro-friends that food and health regulation could potentially be enforced by the free market more effectively than by corruptible government, and this is a perfect example of this.

I'd want to see all products I can buy in there, with all possible chemical, ingredients and nutrients, and clear indications of good/bad, a little bit like in Yuka. You should partner with them maybe even!

Re: Ask HN: What are you working on? (September 2025)

#695

Building an app where 1 pushup = 1 minute of scrolling allowed [1]. We've fiiinally started to grow and reached a whooping $30k in the last month!! I was literally thinking about quitting in August. My motivation is now at an all-time high - some users have done >8k pushups :) As always, the key has been the marketing (10M views on Instagram). But we have to improve the product to make people love it even more. So th…

Neat idea, but how does that work? Can an app limit other apps ? I didn't know it was possible.

On iOS you can do that using DeviceActivity framework, iirc.

Re: Ask HN: What are you working on? (September 2025)

#696

I’m building a text editor inspired by ed, but instead of editing files on disk, it edits live network flows. In this model, files don’t exist as static objects—they exist in motion. Creating a file generates a self-sustaining pattern of packets circulating through the network, and editing it changes the flow itself. Multiple users can edit the same file simultaneously, because the file isn’t tied to any machine—it’s…

This is insane and I love it!

Re: Ask HN: What are you working on? (September 2025)

#697
I am working on https://productpageshots.com

You copy/paste your product page URL into it.

It scrapes your existing product images + additional context (using Firecrawl's API).

Then it uses Google Gemini vision model to generate recommended missing shots.

It suggests those with a confidence score from 0 - 100%.

Then it uses Google Gemini Flash 2.5 to generate the actual recommended shots.

You can download them and insert them in your product listing.

Re: Ask HN: What are you working on? (September 2025)

#698
Trying to reboot an early-middle-aged brain that has succumbed to a terrifying, long-term brain fog that has almost crippled me by ruining my concentration span.

Personal projects, developing a habit of contributing my time to a large open source project (having only ever run my own very small ones), teaching newer users how to use that open source package by answering questions and making little example videos, beginning to repackage my notes on things into blog-publishable writing.

Really anything that will help me use brief moments of concentration span to rebuild my confidence in my own ability. It is like a snail ride through treacle but this is the first month-long span in nearly two years where I don't feel like I am falling apart.

Re: Ask HN: What are you working on? (September 2025)

#700

I'm trying to incentivize people to build IRL communities instead of AI-related apps because the demand for human interaction FAR outweighs the supply. My platform ( https://onthe.town ), is basically Shopify for social experience clubs. Anyone can start a club and create events based around bringing random people together IRL based on shared interests. You get your own website and infra that handles signups, payment…

Love the idea. From the FAQ section on the website: > Organizers can keep a portion of sign-up or event fees Isn't this a given? Don't event organisers expect to keep the entire sign-up fee for themselves when they host an event? The website banner reads: > Build an IRL community. Get paid for it. I was under the impression that onthe.town will pay the organisers from their own pocket for organising the event, but th…

Really appreciate the feedback. The idea right now is that you set up a club and attendees pay a small amount for each event, and then we take a small (~10%) fee for selecting the venues, doing the matching, and handling payments for you.

But I do love your idea and it's something I'm pursuing. We are matching people to meet at venues (restaurants, golf courses, etc) and it makes sense for venues to pay to be selected. That money would go to organizers and the events could be free. It's just a harder B2B problem to convince companies to sponsor communities.

Ultimately, clubs will have the flexibility to be run in multiple ways - from free, to business-sponsored or attendee-funded, to even onthetown-sponsored as you suggest.

Post reply on HN