[dead]
Ask HN: What are you working on? (January 2026)
671–680 of 914 posts
Re: Ask HN: What are you working on? (January 2026)
#672I am rebooting a theme inspired by Deus Ex Human Revolution for various apps and tools.
A bit like DraculaTheme.com
https://tomaytotomato.github.io/jensen/
https://github.com/tomaytotomato/jensen
The plan is to get a Chrome and VSCode theme shipped this week.
"I never asked for this...."
Re: Ask HN: What are you working on? (January 2026)
#673I recently switched to native Linux. I have a dotfiles repo that installs and configures a number of CLI tools, complete with theme switching for a bunch of years that works on Arch / Debian / Ubuntu and macOS, with WSL 2 support too.
Now I've been piecing together a complete desktop environment using niri and many other tools. If you're using Arch, you can opt-in to turn this feature on. There's an install script which can be run on a new system or existing system, documentation on each package and more at https://github.com/nickjj/dotfiles. I'm using it on 2 systems at the moment.
Re: Ask HN: What are you working on? (January 2026)
#674I got tired of keep optimizing prompt and rolling out changes in production. So I built a neurosymbolic language to help with that, where prompts as policies instead as hard rules.
Re: Ask HN: What are you working on? (January 2026)
#675I started working on a simple Telegram bot with llm backend and .md knowledgebase that would help me organize, track and research my long-term hobby projects. The problem that I am repeatedly facing is that I am trying to build a home server and I keep asking chatgpt questions, but it is hard to keep all the little details in one place. The way I see it is that I can just text my assistant bot and ask it something li…
I ran into the same problem. Tried using ChatGPT as a scrum manager. It was really good at checking off todos through conversation, but as I fleshed out the details of the project it would forget critical information - not necessarily todos, but critical information constraining the implementation of the project. In the initial stages, it was great, but it lost usefulness over time.
Re: Ask HN: What are you working on? (January 2026)
#676When AWS released the S3 Vectors last year, I wanted to try it since I had no experience with Vector DBs, so I built a simple audioguide app to play around with it.
Basically, just use it to identify artworks from a photo, then return a pre-generated AI-Audio for that artwork based on the data on their site. I put up a basic live version on my site for The National Gallery in London: https://victorsantiago.me/audioguide/national_gallery.html
(If you want to try it, you can open it on your phone and take a picture of some painting on the National Gallery Website, e.g.: https://www.nationalgallery.org.uk/paintings/vincent-van-gog... )
It was pretty fun to try it out and play with different LLMs and TTS models to generate the output. Might make a it a proper web app some time soon!
Re: Ask HN: What are you working on? (January 2026)
#677Super specific use case, only a handful of users(mostly friends with free account). https://apps.apple.com/nl/app/multipark-amsterdam/id67469835...
Use Case: Assumption: You have access to your friends visitor parking login in Amsterdam.
You are going to a restaurant/or visiting a place near their parking zone(geo fenced polygon). You want to pinpoint a point in map and drive to that point. Being 100% sure that you can park at that point. Automatically pick a meter near there spot and park almost instantaneously. Then this app is for you :D
Update: Recently updated for this to work with new APIs and in the process updated the UI as well(slightly modern)
Re: Ask HN: What are you working on? (January 2026)
#678A suite of productivity tools for Claude Code, Codex CLI and similar CLI agents. These solve pain points for me, and I build and share them in the repo[1]. I’ll highlight a couple: - an “aichat” command group that enables continuing work from a session that is at full context usage, by creating a new session and injecting session lineage pointers so the agent/sub-agent can recover arbitrary full details from ancestor…
This is interesting. I wrote a “memory indexer” with the idea to provide a tool (cli) for my agent to “remember” past conversations we had in other session. A little bit in the spirit of your second tool I think I’ll take a look at the others you have.
The thought behind my aichat tool was to directly leverage the session log files and avoid creating any special memory artifacts. I do create a rust/tantivy index for the fast full text search.
The aichat approach does require intentionally asking the agent to find specific earlier work: it doesn’t automatically have “awareness” of prior work. I think of this as the “unknown unknowns” problem. This is where creating explicit memory artifacts can be useful since we can pre-inject recent work-summaries into context. So I’m thinking about a lightweight hook based system to automatically create memory artifacts or work-logs of some sort.
Re: Ask HN: What are you working on? (January 2026)
#679I was working on building a chatbot on WhatsApp - to help people build better habits. The bot would suggest a program consisting of daily/ weekly micro-goals for the habit the user wants to build. The bot also messages you with reminders ( set by user) and check-ins to see if users have completed their micro-goals. Ran a beta test with 20 odd users , didn't see much uptake. So back to drawing board. Not sure if I got my set of beta users wrong ( most of them are busy couples with kids) or if it was just the product.
Re: Ask HN: What are you working on? (January 2026)
#680On a recent flight home for Christmas, I tried to get some side-project work done on my MacBook… and immediately lost the battle with Seat 28C. I could barely open the laptop, let alone type comfortably.
The real constraint on planes these days is elbow room. That got me wondering: could a small, handheld keyboard and trackpad setup make in-flight work tolerable?
After failing to find anything compelling on Amazon, I realized something obvious: my iPhone already has a great keyboard and touch experience. So why not use it directly?
I looked for existing apps, but the top options felt dated and required both devices to be on the same Wi-Fi network—which isn’t always possible (or desirable when paying ridiculous prices for airplane Wi-Fi).
So over the last few days I’ve been tinkering with a project I call Magic Input. It turns your iPhone into a wireless keyboard and trackpad for your Mac.
How it works (high level):
• The iOS app discovers nearby Macs using MultipeerConnectivity
• Keyboard input and touch gestures are streamed directly to macOS
• The macOS app injects events at the system level (requires Accessibility permissions)
• No shared Wi-Fi network required; devices connect peer-to-peer
It’s very early, but already supports basic typing and cursor control—especially useful in cramped spaces like planes.
Here’s the TestFlight link for the brave. You’ll need to install the same app on both macOS and your iPhone:
https://testflight.apple.com/join/T1PgucDs
Happy to answer questions or dig into implementation details if anyone’s curious.