alt Hacker NewsAsk HN: What are you working on? (August 2026)
What are you working on? What have you been curious about lately?
Comments
One of the projects I’d like to highlight is Cheaspoly.
It’s an attempt to make chess a bit more, you know real:) Like countries buy armies, chess kings can buy figures. Also it’s easy to bring these new rules into offline games.
It’s quite early stage yet, but you can give it whirl at https://chesspoly.com/
I'm working on an improved Markdown that offers a simplified language, clear hooks for extensibility, and a governance model to let it grow over time.
An opensource derivatives pricing engine, distributed and built on QuantLib and gRPC + FlatBuffers.
I have been working on my master's thesis. I am not really young anymore, so finding the time was tricky.. until I started working with AI agents. Then I started using frontier models and I couldn't sleep anymore, trying to maximize my usage limits. The project is called Agent Sandboxing Framework. If you are interested in AI agents and security, I’d love to hear what you think.
I’m building a registry for packages that add WebMCP tools to sites that have not adopted WebMCP yet. Each package describes tools for a specific site as json and those tools are injected and executed using a browser extension.
I've built Ziggity an ultra fast, keyboard driven terminal UI for Git, written in Zig https://github.com/simoarpe/ziggity
Benchmarking public agent skills: Oh My ClaudeCode, Superpowers, Git Ship Done, (previously Get Shit Done), and the Karpathy ones against Swebench-Pro and SlopCodeBench. I have a July vs June breakdown. It's been an interesting learning exercise and reveals the cost/performance impact of using these.
I've been building a site to help me keep track of the stocks I follow.
* Automatically sets alerts when I favorite a stock
* Discuss and analyze stocks with AI
* Generate AI research reports
Would love feedback from other investors/builders:
I've been trying to get better at chess recently. But also wanted to explore some AI agent development hands on on the side. So, I built an AI chess coach to analyze my games, learning openings, and drill different endgames and such.
Bio tools: CLI app, Python or rust lib for installing and running structural bio/drug-design software without the user messing with python envs, conda, system deps etc: https://github.com/David-OConnor/bio_tools
Working on the ability to create mixnets with sanctum [0] and its cathedrals.
Sanctum already has very capable traffic analysis protections in place in the form of shroud, but being able to build mixnets will make it even more valuable.
But it’s been vacation time so it’s been slow progress as time away from the internet is equally valuable.
A daily puzzle game called Dozenal where you solve each puzzle board by creating chains totalling the number 12. My friend and I came up with the idea over a decade a go, and have finally started bringing it to life in the past couple of months.
Working on https://www.woltspace.com/ over the last few months. It’s my take at an agent orchestration framework
It builds around the concept of “wolts” running a lodge. A wolt takes the identity of a rodent (racoon, beaver or otter) and can inherit any supported coding harness: claude code, codex, opencode, etc. Each wolt carries a persistent identity and memory, so they always know where you left off.
woltspace is designed to help you host your apps directly from woltspace on your machine. If it works on your machine, it works anywhere. This is done through Cloudflare tunnels that you can setup with your own domains (or using ephemeral domains).
Under the hood, woltspace is powered by tmux, which means that sessions persist and can easily be resumed and accessed from anywhere. I personally drive woltspace mainly from the telegram integration, which gives me access to my wolts and CLI literally from anywhere. This means I can chat with Claude code CLI from anywhere, spawn new sessions, all running on my own infra. It’s also all in a docker container so you don’t have to worry about approving every single command.
95% of woltspace was built from within woltspace, and it’s becoming my prefered way of building.
Another feature I really like: the “inter wolt communication layer”, IWCL, allows wolts to chat with each other, making things like having fable orchestrate a gpt 5.6 something that works out the gate.
Woltspace is meant to be used by power users (you can bring your own tmux config and use the TUI CLI) or by beginners. The default split pane makes SEEING what you’re working on really intuitive. Each wolt can host its own website where they can render arbitrary html making planning new features much more intuitive.
It’s all open source, and I’m constantly adding features to it. Woltspace is mostly self documenting, all of the features are also skills the wolts have access to. I'm also improving the documentation surrounding the project as we speak.
Looking for some feedback and users to try it out. You can one line install it with
curl -fsSL https://woltspace.com/install.sh | bash
Project page: www.woltspace.com GitHub: https://github.com/jerpint/woltspace
I'm working on a bunch of stuff, but most interesting is maybe https://Octoloops.com - it's a sort of marketing harness for indie devs/SMBs. Still early days yet, feedback very welcome!
I am working on AI memory. Have been working on YantrikDB since January this year. Started as a pet project solving my own problem but now its growing. It's fun and satisfying at the same time
I am still working on my IndexedDB manager browser extension, Kahuna. The recent release added direct editing of values from the grid view for all 42 data types that can be stored in IndexedDB.
I am releasing my music player into open beta this week! I’ve been working on it for a year or so, created my own language, engine, and network protocol to make it all sync wirelessly, and with no AI :) https://github.com/mjdave/katipoBrowser
I am working on an update to my mobile client for Learnalist, specifically bringing upgrade path to gate 200 free flashcard entries before payment. This now includes, a new add UX, embracing images on the server, not local anymore.
Aside from this:
- I asked codex to use my mobile app and web page for the flashcard UX, and make me one using qt + qml so I could run it on the remarkable 2, super happy with the initial results. This will be released as a reference for others, as the eco-system is too clunky today to offer it the non-technical users of remarkable devices.
- I learnt about my set-up box, and got assistance in making my first app, so I can post and image from my iphone to it via shortcuts. Currently, it only accepts one photo, but it is cool throwing it up on the tv. This also let me learn a little more about "ios Shortcuts" and cherri, a golang cli, that makes it a little easier to make shortcuts.
- Using nurb, to 3d print things, currently working thru printing a stand, so I can mount an iphone and record doing things on the remarkable. Its been really fun testing with little physical prototypes of small parts to then roll into the stand.
#Reference
Published [0] a few days back - learning IO techniques in Linux. Got as far as epoll and will explore io_uring next!
[0] https://parallelthoughts.xyz/2026/08/learning-linux-io-part-...
a toy thing for the game path of exile 2.
Fed up of wading through a metric oodle of waystones and tablets to figure what best, along with a billion stash tabs full of a zillion items.
I'm making a tool that scans your inventories and lets you rank and analyse things based on their affixes, so the best ones according to criteria you set pop out at you, minus the hours of staring and thinking.
Hobby project, so full on vibe coded zero code review type stuff. If it works, thats good enough. for now, anyway.
KimiK3 is the weapon of choice for this one, and its doing pretty damn good!
iI am working on a synth engine (music synthesizer) in Python and C++ not a developer; music producer, classical pianist, and occasional NI Reaktor programmer.
It creates sound from math expressions which were inspired by the Desmos graphing calculator.
The sounds are mainly of the FM/DX7 taste.
i can't decide whether to show my progress on video by hiding or showing the expressions LLM(s) and myself "discovered".
It sometimes sounds extremely musical and sometimes very dirty and experimental, what's normal for frequency modulation.
Please help me decide: show all and open source or continue working on it and pitch it to some big names. ;-) I have the feeling it has strong potential for prototyping, as well as taking the role of a keyboard engine. It is completely viable to manipulation via AI because of its concept.
It runs nicely on an M4 Mac mini with 256 voices of polyphony and has a very high level of expressivity mainly via half-pedaling (sustain pedal).
Velocity, 8 macro knobs, no filters, no fx, ADSR envelope. A web interface and additionally CLI.
My wife hates clutter and the junk that we've accumulated the past few years because of our two children receiving junk toys.
I built a simple wish list app that anyone can create a wish list and share without the need to create an account. Great for birthdays, evergreen lists, Christmas, etc.
whichwishlist.com/
Automatic local events aggregator https://whatson.town/
I'm bilding Jamful - ios audio looper app. I always loved using guitar looper pedals, so i wanted to have something similar on my phone. Currently it's on TestFlight https://testflight.apple.com/join/W7nD6v5H
I'm still working on CT RailTime. It's an app I made to make traveling on CTrail better. CTDOT's app they've outsourced is really bad and broken most of the time. People who use CTrail deserve something that works.
A software SDLC harness that can run complex long horizon coding projects.
https://github.com/conductor-oss/conductor-agents/tree/main/...
Open for collaboration, still in early dev.
I'm working on https://memoryindex.io/ :
A better way to track real-time pricing of DRAM and HBM pricing in the market specific to equipment type, manufacturer, and other metrics. Feedback welcome to improve and see if there is a market for something more in-depth.
A roguelike with card battles: https://uzudil.itch.io/rquest
Very early. Tech: raylib-zig with Lua, loreline convos, shaders. Graphics in aseprite.
I started yesterday working on an airless 3d printed tire/wheel for my electric scooter, and got the first full PLA prototype. Currently waiting for small scale TPU tests to decide which of my designs to go with, and I expect to have a working prototype tomorrow or Tuesday
Larger puzzles in my app[1].
And some yak shaving in the form of selective zoom, where only the board would zoom in but the clues around the board would still remain visible.
for you tennis players out there, I'm working on RallyClip, an app for free tennis match segmentation. It's a free and open source alternative to SwingVision:
github: https://github.com/iroblesrazzaq/RallyClip website: rallyclip.app
I'm working on model performance and an iOS app right now; would love feedback on the macOS desktop app.
Fast native language (java/rust) regular expression matchers:
* Java: https://github.com/la3lma/rmatch
NVIDIA Parakeet running locally in the browser. Implemented in raw WebGPU compute shaders & SIMD WebAssembly audio frontend:
The aim is for it to be a high-performance implementation. Can currently transcribe 1 hour of audio in 20 seconds on an M5 Mac.
Been working on adding support for Gaussian Splats directly in ThreeJS specifically for WebGPU:
https://ben3d.ca/blog/gaussian-splatting-for-threejs
This PR was merged yesterday morning so the August ThreeJS release will have this new feature.
Two things. https://www.draftdownapp.com/ an open source 3d modeler. https://factchronicle.com/ a fact-based news story aggregator.
Sports betting odds over sms (US only). I’ve had to work with carriers to get exemptions as they have rules about providing betting advice or being affiliated with sportsbooks, which has been interesting.
Found existing React web frameworks either bloated, buggy or too complex, so I built: https://www.rshono.com/
Working on an Agentic IDE (free) - multiple AI agents support + classic IDE experience
BETA - means, production ready, but not still extending and experimenting with features - I keep working on it, and collecting feedback.
I rewrote my AI agent written in POSIX sh to be a single file. So now to use it all you have to do is download the file, mark it executable, and set up environment variables.
I've been working on a puzzle game Quilt. Hope to get the demo out this coming week or next week.
I've been building Wellsy (https://wellsy.se/en), a mobile app (iOS + Android) that turns CBT methods into structured programs for diet, lifestyle and emotional wellbeing.
I've slowly been making some tiny apps that just don't collect data in anyway that I want to use myself, pretty basic stuff. I'm sure there are plenty of them but I feel like it says something the world of smartphone apps that they're hard to find.
I've been digging deep into Metal and I recently made this! https://github.com/Exorust/metalworking/
Idk who it helps, but it's been a fun journey!!
Atoll, it's part of my Archipel project.
It's just me, building my own tools and self-hosting them. Atoll is a project management project. Nothing fancy, not over-engineered: - Go - SQLite - HTMX (server side rendered, no SPA)
Archipel will count different other projects (Atoll, Balise, Passe, Sillage)
My comedy newsletter featuring short-ish essays about random nonsense: https://yelluwcomedy.substack.com/
I'm creating an Emacs package out of the custom JJ stuff I had. I'll probably publish it to Melpa in a month or so.
I've been using coding agents to drive data visualization to help me understand complex concepts. Here is the latest on how reasoning models reason:
A probability grid of chain-of-thought, read through Boyd's OODA loop lens [0]
[0] https://adamsohn.com/reasoning-grid/