Live data from Hacker News

Ask HN: What are you working on? (September 2026)

news.ycombinator.com

461–470 of 827 posts

Re: Ask HN: What are you working on? (September 2026)

#461

It would be great if these posting could have tags like below prefixed at the top by the poster. [HUMAN-CODE] - code written by humans [AGENT-CODE] - code written by Claude/Codex/Other agents out there [HYBRID] - Combination of Humans/Agents I would prefer to go through projects where people are writing code themselves. And this kind of tagging would help me filter through easily.

Indeed as it helps to give more meaningful feedback. Somebody in [HUMAN-CODE] might appreciate suggestions on the code but not care as much about business whereas [AGENT-CODE] probably prefers the other way around.

Re: Ask HN: What are you working on? (September 2026)

#462
I'm building a RSS Discord syndication tool called [FeedSync](https://feedsync.net).

It's pretty simple to set up and is designed to "just work", set and forget.

Recently, I've been experimenting with an Elixir Lua runtime (https://deflua.com/) to build custom feeds by parsing HTML, which has worked exceedingly well, so hoping to release that soon.

It's an extremely niche product, but has been growing well organically, which is nice for a side project!

Re: Ask HN: What are you working on? (September 2026)

#463
I'm vibe coding a toy chatbot with OpenCode and GLM 5.3 - I'll open source it once it's meaningfully done (keeping the repo private for now until I am _so so_ sure there are no secrets in it!). This has been an exercise in learning about lots of new AI SWE concepts including some tech (Mastra, LangSmith, DeepInfra) - as well as a chance to try some open weights models. The actual useful output is an iteration loop orchestrator based on GitHub issues/PRs which I have found a lot of fun to use. That'll also be open-sourced.

Re: Ask HN: What are you working on? (September 2026)

#464
https://github.com/Rinkia/monohunter

Find single long-period mono-transits in public TESS light curves — the single-transit events that periodic pipelines (SPOC/QLP, which fold on a period) structurally under-find. Built so many people can each search under-covered targets and combine machine-readable finds.

I usually search 5k stars each run, you have to be lucky to find something, would you give it a try?

Re: Ask HN: What are you working on? (September 2026)

#465

I'm building an self hosted, privacy friendly attribution and marketing suite targeting mobile apps. The market is owned by a few, branch, appsflyer etc, and its impossible to become a new MMP without spending ridiculous ammounts on money on their platforms, so I'm trying to build something different, and more provacy friendly without reliying on them. https://grovs.io

this still works if user has ad blocking at dns and user device? Plus most ad blockers strip off the common URL parameters for "attribution"

Re: Ask HN: What are you working on? (September 2026)

#466
post #458

Still OnlineOrNot ( https://onlineornot.com/ ), 5.5 years on. Most recently I shipped an MCP server (w/ OAuth sign-in) recently to expose the API a bit better to agents, a TypeScript SDK and rewrote the CLI to use it. Also been reworking the terraform provider to cover the whole OpenAPI spec's surface area. Just before LLMs became a thing I took the time to rewrite from having a private GraphQL server + public REST A…

how is this any different from healthchecks.io or openstatus.dev? Seems I can't even selfhost your product either, which is a huge redflag in my book.

> how is this any different from healthchecks.io or openstatus.dev?

Those are the competition! There's never a good reason to not have alternatives available.

I'm not sure if this is intentional, but your comment comes across as a little disparaging, when individuals are sharing things they've built with passion, often in their spare time.

Re: Ask HN: What are you working on? (September 2026)

#470

I'm vibe coding a toy chatbot with OpenCode and GLM 5.3 - I'll open source it once it's meaningfully done (keeping the repo private for now until I am _so so_ sure there are no secrets in it!). This has been an exercise in learning about lots of new AI SWE concepts including some tech (Mastra, LangSmith, DeepInfra) - as well as a chance to try some open weights models. The actual useful output is an iteration loop or…

[dead]
Post reply on HN