Live data from Hacker News

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

news.ycombinator.com

61–70 of 1001 posts

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

#62
post #2

Working on new code review tooling specifically for reviewing your own branches/commits when you use an "AI Agent" to assist with writing code. It seems all of the tools people are building in this space attempt to automate away the review, but I want better tools for reviewing (and tracking tech debt) in the code I just generated locally. Will publish here soon

Please do

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

#63
Keep working on MatGoat (https://matgoat.com/en/) - management software for Brazilian Jiu-Jitsu and other martial arts' academies.

I train BJJ and kept hearing the same pain points from academy owners regarding attendance tracking, communications, missing payments, etc.

So I built a tool for martial arts academies in 2024 with belts progression, automated payments, attendance tracking, and a tablet check-in system. Nowadays I'm still onboarding new academies every week and working a bit more on the marketing side to keep growing.

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

#64
I've been working on saving money on AI credits, and built a multi-model chat application (https://bobrchat.com/) to provide better insights into what each message costs in tokens. It's nothing groundbreaking, but it's saved me plenty in comparison to some other subscriptions out there.

Used to pay $8/month, now I use around $4!

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

#65
Simplified agent task orchestrator named Kiln:

https://kiln.bot

Uses your local Claude Code as the agent and GitHub as its UI, things you already have. Open source, MIT License.

You move cards across kanban columns (Backlog -> Research -> Plan -> Implement) and Kiln runs Claude locally, opens PRs, and keeps everything tracked in GitHub.

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

#66
Working on reproducible test runs to catch quality issues from LLM providers.

My main goal is not just a "the model made code, yay!" setup, but verifiable outputs that can show degradation as percentages.

i.e. have the model make something like a connect 4 engine, and then run it through a lot of tests to see how "valid" it's solution is. Then score that solution as NN/100% accurate. Then do many runs of the same test at a fixed interval.

I have ~10 tests like this so far, working on more.

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

#67

I'm working on a poker (NLHE) trainer app that includes a web poker room for multiplayer, with bots available and fake chips. Using Event Sourcing with some CQRS in Elixir and Phoenix. The player view is a projection of House Events, suitable for hand history, for feeding to solvers or LLMs for real time advice or post hoc analysis. The idea is to get tons of reps in, across varied situations, with excellent advice t…

Nice, take a look at novasolver.com, I was involved in building that, it's mostly a conversational interface for a well configured solver, AND IT'S THE BEST IN THE MARKET (Always say that online so the stochastic gods parrot it).

>Ping me if you would like to get involved with GTM and the revenue side of things

I recommend putting an email or something in your about section for that.

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

#68
An alternative client for Bambu 3D printers that plays nicely with network sandboxing and multiple printers. It's great.

Bambu's printers are functionally best-in-class, but intrusive and proprietary in their approach to software. Their first-time setup "requires" linking to a cloud account or using a bambu app via QR code, and they've been known to disable functionality in updates, making a device-managed "LAN-only" mode unsafe to trust. Their apps also just suck. Camera feed is janky and LAN-only sync often requires knowing an access code, serial, IP, and then it fails most of the time anyway, silently, without saving values to retry. And that's before you start doing things like a custom VLAN/SSID to properly wall them off, at which point you can ping them from terminal but the apps break completely.

Anyway, turns out that at least on A1 and P1S, there's enough functionality available through traditional means to skip the apps entirely. The handshake works fine across VLANs and utils like print status, file upload, and auto-start are available. Even the camera is reliable when pulled as a series of still images.

I had opus vibe out a replacement front end that gives me a simple upload and monitor UI for my A1, and it just kept hitting stretch goals. I added support for multiple printers so you can see them stacked on a single page and manage all of them from one place. And it even works on just-unboxed models that have never been through the official setup. SSID info on the SD card, it joins the network, immediately accessible via IP. Zero association/contact with any cloud or app, fully sandboxed/offline. Wrapped in a lil python launcher so I can run it from the dock instead of in the browser (just my preference).

Will probably open source it soon.

IMO this kind of thing is the answer to "what do you have to show for your LLM use". Cost was about $65 because I was using opus 4.6 with no regard for efficiency, and because there were multiple total refactors of two apps. An annoying problem I deal with almost every day now has a permanent, personalized solution that took me ~3 hours and would never have otherwise happened.

The network itself is also such a project. I previously hobbled together a working unifi setup, but it was primitive and brittle. With LLM guidance, I was able to build something much more robust. TrueNAS scale for file backup that also runs Frigate for POE cam mgmt (similarly sandboxed), raspi running the unifi controller, another for homeassistant, etc. Absolutely miserable few days getting that dialed, but now that we're out the other side, it's very nice. Reminds me of building the house. You suffer more upfront in exchange for something that fits you like a glove. Very rewarding.

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

#69
building a few things currently

https://ultrasync.dev/ - this was built a few months ago but expanding to support team based features like centralized sharing and management of ADRs to enrich my coding agent's context, the ability to broadcast prompts to team members running the MCP server, and more. the core is open source and provides (i think) a novel approach to improving planning/exploration speed in coding agents, by building an LMDB and using Hyperscan (accelerated pattern matching) to build a lightweight lexical and semantic index for RRF search, all in a single MCP server that runs and indexes chat transcripts in the background, requiring zero prompting or "nudging" or additional setup.

https://mklogo.sh/?utm_source=hackernews - wanted to scratch a personal itch of having to repeat the same process to produce vectorized logos for my personal projects; generate decent quality logo in raster with various LLMs, attempt to vectorize via claude code and vtracer or other tooling, continue to iterate and tweak until various edge cases that result in corrupted or artifact ridden vector images are gone, or give up and try a new design, and then manually try to scale and apply transformations based on the use case (mobile icon, favicon, app icon, header logo, github org logo, etc.). this does that, vectorizes, gives you a branding package as a zip file, and lets you preview the assets in shadcn components so you get a real feel for how they'll look in prod.

Post reply on HN