Live data from Hacker News

Ask HN: What Are You Working On? (December 2025)

news.ycombinator.com

881–890 of 1001 posts

Re: Ask HN: What Are You Working On? (December 2025)

#881
not really projects but productivity tools for codex/claude code etc

https://github.com/agentify-sh/safeexec/ - this will prevent rm -rf or git reset --hard being run by off chance when used with --dangerously-bypass-permissions flag

https://github.com/agentify-sh/10x/ - codex productivity booster which adds skills (most likely need to be phased out now since codex has skills), redundant checkpoint/backups with git and jj, subagents, parallel agents, PLAN/RUN/THINK modes.... im actually not sure about releasing this anymore because of how much better codex has gotten.

Re: Ask HN: What Are You Working On? (December 2025)

#882
I’m building something that keeps finding gaps I didn’t realize were gaps.

It’s called Riftur, a gap analysis tool that compares two documents and highlights gaps, missing requirements, and inconsistencies. The interesting part for us has been getting the system to understand intent instead of just keywords, so it can flag partial matches and subtle gaps rather than just “present / not present.”

Still early, but it’s been useful in ways we didn’t fully expect. If anyone’s curious, you can demo it out here: https://riftur.com I'm happy to hear thoughts or learn how others handle this kind of review work.

Re: Ask HN: What Are You Working On? (December 2025)

#883
Something small that has been on my mind for the past decade or so -- assistant chatbot.

Basically I long wanted to plug a chatbot into my messenger of choice with all sorts of tools for quick use, of course after the emergence of LLMs it was only a matter of time before I find time for it.

As an experiment I have decided to use Claude code + opencode to develop it, and after some trial and error I am very thoroughly impressed with the results, it grew to a nearly 10k LOC in a week and it is still very much manageable, I haven't changed a single line of code manually still.

I have developed it as a "core" that imports modules with a rigid and thoroughly documented in a spec.MD file interface, and every single bit of functionality essentially acts as a different sub-app that can consume events that trigger it and handle all of the internal logic within itself, that way everything is separated nicely and totally manageable within LLM context.

It does everything from setting up and sending reminders and todo lists, helping me track car mileage and fuel consumption, getting an overview of the day ahead(sometimes if task is important even a reminder few days prior to its date), to even opening my front gate. And all of that is exposed to 'core' chat module through tool calls, so I can request anything in plain English or voice.

Also has a web-ui where I can review tasks, reminders, settings or search past conversations.

Been using it a lot, and since I'm using groq for inference, I still haven't even needed to pay a thing, since it fits within the free limits

Re: Ask HN: What Are You Working On? (December 2025)

#885
https://joinpromptify.com/

A prompt engineering tool that takes vague prompts and transforms them into context-rich JSON/XML structured prompts. Fully customizable and tracks prompting history safely in tab session, automatically injecting context and learns style.

Makes outputs of any AI so much better due to restructuring and breaking down requests into instructions AI can easily execute upon and mitigating risk of hallucinations. Perfect for complex tasks like coding and content creation.

Exists as a free chrome extension right now. Would love if you tried it and have any feedback!

Email me at krishnamalhotra150@gmail.com

Re: Ask HN: What Are You Working On? (December 2025)

#886

I shared this last month, but I’m still having a lot of fun working on it. I made a daily word puzzle called Tiled Words. https://tiledwords.com Currently about 2,000 people play every day and I’ve released 59 puzzles! One feature I’m excited about is crowdsourcing puzzles. Today’s puzzle is a “community puzzle” made entirely from clues that players submitted! I plan to do this every week or two. I wrote about launch…

Thanks for this game, I've been playing it since you last posted it and it's become a regular in my morning brain wake-up routine of Minute Cryptic, Shuffalo at The New Yorker and a couple others, so I like the bite-size nature of it a lot.

Re: Ask HN: What Are You Working On? (December 2025)

#887
Working on improving the data pipeline for https://iplocate.io - an IP intelligence service I've worked on since 2017. A couple of recent focuses:

1. VPN and proxy detection. We already track dozens of providers, but we can do better here. There's also a bunch of metadata we collect as part of this process which we don't currently surface, so I'm looking at what else we can bring to our databases and free API.

2. Better detail and evidence on how we build and test our own geolocation database, which we create from scratch. There's been a recent trend of misinformation about geo accuracy, including from some other providers, so I want to better explain the accuracy (and inaccuracy) of various techniques, our policy for when we prefer certain data, and so on.

(Open to partnerships for any folks looking for a new provider!)

Re: Ask HN: What Are You Working On? (December 2025)

#889
Working on migrating Hopp's [1] overlay window, which we use for drawing the remote cursors, from winit + wgpu to gpui. I used claude in the weekend to make a prototype and now I want to make a gpui app, which will replicate all of our requirements, in order to see what is missing and if I need to contribute upstream. I am planning to write a blog post when the migration is over.

[1] https://github.com/gethopp/hopp

Re: Ask HN: What Are You Working On? (December 2025)

#890
A security-focused "check engine light" for your shell prompt: https://github.com/erichs/dashlights

There's a gap in most security tooling: it's not IN the terminal with you. It doesn't have enough context: your environment, your repo state, your current directory, etc. to catch the small hygiene mistakes that accumulate over the many tiny decisions you make every day to ship code and learn new tools. Those "cut corners" add up, and can lead to costly blunders.

Dashlights attempts to bring awareness and visibility to your immediate shell context.

Post reply on HN