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

It maintains a vector store and a SQL database. While vector store supports usual RAG operations, the ones that require counting, summation, selection are routed to the SQL database.

There is an option to start with an initial schema, or let it discover the schema itself. Then on the day to day use, if a user query cannot be responded, a candidate schema entry is created to be populated on the next backfill run.

So in actual use, user asks the question such as "Give me the list of people who are scientists". If it is not in the schema, LLM suggest checking it later. Backfill runs at night. Next day it can answer the same question without issues.

Or at least, I'm trying very hard. When I was younger, I was super happy about all the gifts that I received from anonymous strangers through the Debian package repository.

Then I had a phase where I tried to contribute to and publish my own open source software. I got horribly ripped of by companies, multiple times, in some instances they even sent their paying customers to my private email for support inquiries, so I got unpleasant insults and thinly veiled threats by random strangers who thought they were paying for my open source software and I was the asshole.

Then I stopped doing any Open Source for a while.

And now I feel like we urgently need a new way of financing software for the common good, like Thunderbird, Wine, and maybe one day a Linux file manager that feels as intuitive to use as the Mac Finder. The world could also really use a desktop GUI framework to replace those pesky Electron apps. 128 MB of RAM used to be enough for a snappy coding IDE. But it looks like recently every infrastructure-level Open Source project is effectively fighting for survival because it gets turned into a hyperscaler cloud service and then nobody donates to its development, despite astronomical user counts. The last defense that still worked was AGPL, but with AI "re-implementation", that won't help anymore.

And that's why I strongly feel like we need to find a way to build trustworthy closed-source apps for the common good. Like where regular everyday non-technical people spend a few dollars a month to help support software that makes their everyday life better. (As opposed to being digital hostages in services that sell them as the product to be advertised into buying useless junk.)

The key insight I found was that the best real-world knowledge base for this already exists — Twitch streamers. Many show their settings on stream, and they're running known hardware. By extracting settings from clips and pairing them with each streamer's setup I've built a database of 200+ curated configs that go way beyond "just set everything to low" and looking to add more.

If you've ever burned 30 minutes tweaking shadow quality and anti-aliasing before actually playing a game, this is for you. Would love any feedback.

Most of the people in this space are tech illiterate, but I think that's going to change when they start to age out.

The next generation of antique dealers and collectibles market curators are going to need tools built for them.

I only entered the space 6 months ago after inheriting some old vintage travel and tourism material. I was lured in! I've spent the last 15 years of my tech career working on custom built systems that are perfectly suited and tailored to my needs and the needs of my team.

As soon as I started shopping on ebay, checking comps on worthpoint, browsing for auctions on liveauctioneers, manually searching hathitrust and other institutions for research... I started to want to build my own tools immediately.

I don't want 15 different dashboards. I want one. So, I plan to leverage my technical background and expertise in building systems to hopefully enable me outmaneuver other dealers and curators.

I hope to build custom intake pipelines. There's a keyword crisis in the collectibles market. If the seller doesn't put the right keyword in their listing, or the buyer doesn't put the right keyword in their search query, the two never meet. I look for very specific types of old vintage travel and tourism material, and I have to manage a list of hundreds of search terms in order just to find one specific type of item. They are out there, they're just hidden and unaccessible.

https://raygum.com