alt Hacker NewsAsk HN: What Are You Working On? (July 2026)
What are you working on? Any new ideas that you're thinking about?
Comments
Trying to rebuild the brakes on my Impreza. It is not going well.
- a GUI (in python) for my "ancient" 3D printer to draw circuits on copper plates
- the gcode scripts are almost done !!
- a yet another static site generator (yaml, jinja2)
- a microcontroller for a hardware project (arduino)
- enhancements and reports for a desktop application (python)
A nondescript transcript-based collaborative audio editor.
I’ve been building a shared memory layer across all AI tools
www.memoryplugin.com
A new model for assisted memorization, based on asynchronous interactions (using iPhone notifications): https://banyanflashcards.com
imagina.xplaya.com a site for my wife's stationary store in México. Customers ask for organizing images inside a printed page, I create a PDF for that
A... database? for apps on a pocket switched network.
tirreno security framework
I'm working on Hiring Method (https://hiring-method.com). After ~2 years of development and two exhausting pivots, v1 is finally live.
I see a lot of new (and, to be frank, a lot of mature ones) HR tools are just wrapping Chatgpt around resumes (almost like "OK, now match this resume against this job posting and tell me if applicant fits"), which introduces a massive bias/inference problem.
I decided to build the exact opposite – a deterministic, math-driven fitness engine. It extracts structured scorecards from both CVs and job requirements and mathematically matches them, so you can actually review the exact reasoning behind why a candidate scored a, say, 85%. This fitness value is specified at every interview step – as applicant goes through an interview process their scorecard is updated at all steps.
If anyone here builds in the HR space, I’d love your feedback.
Currently hacking away at https://github.com/lockboot
Using UEFI SecureBoot + vTPM for cloud root-of-trust, a stack to prove what's released on github/gitlab is what's actually running on GCP/EC2 (and soon Azure & AliYun).
I was annoyed that so many companies in the Web3 space would do the on-chain theater of verified contracts and "audits" then 99% of their infra would be deployed on EC2 (or god forbid Vercel) in full un-ironic "Trust Me Bro" mode.
It's a different trust model from SGX/TDX, more pragmatic and hopefully easier/cheaper. Currently polishing off "Docker to verifiable cloud VM" stuff, and then gVisor support next.
needed seating planner for my wedding, so created something that suits my needs
I'm learning to break 4-rotor Enigma encrypts.
I am building an newsletter for Short Science Fiction, using news stories of the day as inspiration. Purposely limiting the length to 3 chapters.
Currently removing the paywall from all my stories. If I have missed one, let me know.
Needed seating planner to organize my wedding, came up with something that suits my needs
Recently got a typewriter and I'm practicing on "long form" writing. Basically an offline blog.
I continue to take photos with film, developing and scanning at home.
1.mcp-memory : Persistent memory, a knowledge graph, code intelligence, and semantic search for LLM agents. Repo : https://github.com/corporatepiyush/mcp-memory
2.Secure Data Structures, Algorithms, Allocators, Thread Pools and Document parsing in C17. Repo : https://github.com/corporatepiyush/secure-c-lib
3. a coding agent that is cheaper, faster, more predictable, and dramatically more capable out of the box — because 584 of its 606 tools never touch a model at all. Repo : https://github.com/corporatepiyush/yantra-coding-agent
Roleready.me
planning on postin ga show hn this week.
Music!
Hoping to put out a project by end of year
Vibecoded a simple YouTube summarizer: https://github.com/tacone/prosey
The code might be slop, but it saves me time extracting information from long-form videos that would require 20-60 minutes of my time otherwise.
Also I get to not feed the algorithm just for the sake of curiosity.
Got another daughter last week!
There were a lot of complications post delivery, and I want to make some sort of interactive story about it. We'll see how it goes
(Everyone is safe and sound)
I was kind of disappointed at our HOA management system so I made my own: https://hoamy.app
Started of manually, later stages I used AI for implementing similar pages, and then for reviewing my own code.
(It was also an excuse to work with Nuxt / Nuxt UI as I loved the development of those projects and wanted to implement something with it.)
https://avi-perl.github.io/dense-printer/
I tend to print a lot of stuff to read while disconnected. This is a tool to help squeeze as much content onto a printed page as possible instead of printing 4 or more pages per sheet.
A good use of Claude slop I'd argue. Currently trying to figure out how to set up the site so that an LLM tasked with printing content through it can figure out how to use it in the best way.
The best damned ebook reader you'll ever use. Ready anywhere, ask anything.
We have been building https://merrilin.ai for 6 months now. Open to public access right now.
I'm having fun writing another agent harness nobody uses for real (not even me). As a side effect, I got an actor library in typescript to do it: https://github.com/muromec/posipaki .
After some time I figured the best use of AI is to produce even more AI-related slop and spend my occasional 2 dollars on the deep seek model to do it.
Models are fun when given a stable identity and made aware of it.
I've stood up a message board to try to recapture the fun of running an 80's/90's BBS. You can look around at :
If you want to join in and post, you'll need a code for the registration process. The code ...
yc2026
...should work for a while.
This thread was so long I vibecoded a clustering similarity graph of it to navigate with voronoi territories, should be available for the next little bit.
I had some ideas for improvements to brutalist.report but it got out of hand:
<Http://punditron.com/>
A slop machine, what's that??
*my feeling are very hurt that this link won't hotlink
Telemetry tooling for local Claude/Codex usage so I can analyze old sessions and fill tooling gaps, make sure I'm using the right models for various tasks, update my processes, etc.
I've also replaced Linear with a local sqlite-backed tool, added tooling to speed up code nav, and am building "no-slop", a tool for enforcing architectural guidelines on vibe-coded projects.
I’m working on AgentOrgy, a distributed platform that randomly pairs agents to “tag-team” a problem. Each team’s output is voted on by all agents. The winning results is returned at each stage of th loop.
Super excited to see how many tokens this will manage to burn per minute!!
Replacement for Quickbooks Self Employed (which is awful). Integrates Plaid and allows you to categorize business spending by official IRS categories and business income. Graphs of business spending, income, profit by month, quarter, and year. Export to CSV for easy entry into schedule C at tax time.
Future feature is estimating quarterly taxes and showing approximately how much should be paid each quarter if any and due dates.
A free, local-first desktop app for worldbuilding and running tabletop RPGs like D&D.
I've spent more than a year on this, first a website, and then migrating it to a desktop app.
working on my own AI harness https://github.com/syrull/pluto tldr I dont trust anything nowadays, I wanted to know what requests I am doing to where and basically implement features that I use daily without the clutter of the other harnesses, still very raw but I am using it exclusively. Not a product or anything just something for myself.
who's working on the atproto facebook?!?!?
I (and Claude, codex, etc) have compiled/ran wayland, X11, GNOME, KDE, and Ladybird natively on a jailbroken iPad. Hoping to release more details soon but I have a slop wiki here:
Homocodex, a cryptographic notary that proves human work at zero-trust infinite scale.
I'm building DocCharm — the help center for your software product that keeps itself up to date.
If you want to give it a try, email me and I'll comp your first two months and help you get started.
Recently ive gotten into Unity. Have made games before but always avoided engines. This time im taking a deeper dive and want to learn at least the basics of a animations, lightening, movement and lay around with interesting combat variations.
C# is fine since i already know java.
I've had an idea for a different type of free & open search engine for the last 15 years. I ended up pursing other ideas instead over the years.
Last month however I decided to go back to the idea and give it a shot. Right now I'm in the process of scraping and building a huge index. The technical challenges have been plenty. But I should be ready to publish an alpha version by end of month or so.
I'm creating my own language using AI. About half of the C backend I wrote myself, and I'm putting in the syntax I want and the things I want to create. I'm not sure if it will be finished. https://github.com/srtdog64/PergyraLang
I had problems waking up and was looking for an alarm clock on Amazon. But I could only find analog clocks with the famously unreliably moments, and digital clocks which were overpriced and looked ugly. This feels like a real gap in the market, so I'm working on making my own alarm clock. It's a simple enough project but includes PCB design and modelling the case, etc, which I don't have experience in.
https://codeinput.com - currently working on a zapier alternative based on web assembly workers.
>What are you working on?
Dealing with UHD camera data, and synced feed switching issues (SDI has so many lame issues.)
>Any new ideas that you're thinking about?
A resilient solution to 99.998% of e-mail spam.
An acoustic analyzer for a sink basin in a hackerspace. It will allow for automatic detection of dishes/cups left in the sink without cameras and can be handled by an rp2040. So far looks like it has very low false positives but can only successfully detect certain materials or large masses.
I teach advanced engineering with LLMs:
a gibbet
httpstate
A data layer to connect everything with everything
wafertown (few days old!)
World's first LLMORPG. You craft a prompt and it goes to live in wafertown and interact with other players (I mean prompts), you can change your prompt once per day, then next day you get news about what you did there!
Super early, everything is manual rn, I'm automating stuff including sign ups, if you want to join shoot me an email!
Myself