What are you working on? Any new ideas that you're thinking about?
An audit of the active web, what CMS, hosting and technologies are used.
Custom python crawler getting 240 sites a second crawled and classified. ( homepages and minimal probes, no headless browsers )
Be interested to test some false positives, if you have a URL I'll tell you what I see :)
Im still working on station display: https://stationdisplay.com/
I also just posted a new blog post on trash valorisation: https://stefan.schueller.net/posts/kva-winterthur/
The other day I hacked on a little local-first web app to help keep track of a baby's movements in the womb and visualise the pattern over a time period: https://bktrack.ingim.io
I’m iterating on my own coding agent, called `rho`. https://github.com/crustyrustacean/rho-coding-agent.git.
It’s founded in Rust and incorporates a Deno runtime for extensions.
It’s headless now, via JSON-RPC. I’ve got the basics of a trait based system which will enable different frontends. At the moment, I’ve created an extension for `pi` which allows me to use that as the frontend.
I’m working on a coding agent that doesn’t have access to the shell. Essentially all it could do is edit and read code, verify and run tests. But due to that limitation I’ve made it target only rust projects for the time being.
Been writing a bit on my blog: https://devz.cl
And been working on a Mario-with-guns game concept: http://devz.cl/posts/what-if-mario-had-a-gun/
Thought it’d be a short concept to get from start to finish but the things you need to implement and plan for in a video game can be near infinite and decision paralysis is a real problem for me.
integrated agent review surfaces with https://github.com/backnotprop/plannotator
HTML/artifact canvases have a lot of potential
https://x.com/backnotprop/status/2064951065439834378?s=20
https://x.com/backnotprop/status/2065436433985474726?s=20
https://github.com/plannotator/effective-html
Shared context workspaces are important
• A social ebook reading app where you can create reading groups and have realtime discussions.
• A visual moodboard and notes app that uses local models to link and surface content, a bit like an AI powered Memex.
• A new UI design tool for Mac/iOS with deep support for design systems and AI agents.
• A CMS and static site generator that runs entirely in the browser. Download the site as a zip or publish directly to GitHub/Netlify.
I'm working on my self-host TTS cli application for turning articles into spoken audio which I can stream from my PC to mobile device when I'm out and about.
It's called Vocast: https://github.com/cnrmurphy/vocast
Thinking about adding some things like queuing RSS feed items to be converted to audio and a feature for being able to do the conversion from my phone.
I've been working on my vision for a better web app development ecosystem. https://wildloop.dev/
It currently exists of 12 libraries/tool, most of which are pretty stable by now, though some are still very much in flux.
This is one of those things that turns out to be kind of a lot of work. :-)
I am working on a linter for EPUBs for issues not covered by EPUBCheck/Ace by DAISY.
The goals: speed, accuracy of diagnostics (e.g. exact problem start/end position in the XHTML), clear issue descriptions including references, utilizing SARIF.
Implementing a solver/optimizer for the Minizinc challenge in Rust! It's very fun, and maybe next year I will even try and put it into the competition properly. As well, I am working on tracking down the history of Sudoku prior to Wayne Gould's popularization of it in the 2000's, and I have found some really interesting postings on Japanese forums from the 90's about the game.
I'm building a plugin for Ghidra called Specter that aims to bring semi-deterministic agent workflows to Ghidra. It adds a terminal like interface to Ghidra's code browser where you can chat or run DSL queries.
The project is currently 100% vibe coded with codex\gpt-5.5, but after running some experiments, I'm working on replacing some of the vibe coded SQL engine with Apache Calcite.
Working on native mac apps that should be features. Built my first one: https://relaylabs.cc/switchboard Another 2-3 in the pipeline
I've been thinking about and working on a solution to automatically resume a Claude code session in the same terminal when my quota resumes. I hate waking up and typing "please continue"
Working on AI security and governance (MCP + LLM gateways, fine-grained access control, DLP, monitoring, etc.) It's a lot more fun than it sounds. :)
Messing around with my Lambda Calculus tutorial repo. I just did a total rewrite of Nominal Inductive Types.
Im working on a web-based general purpose tree editor with some unique features. https://github.com/justindmassey/tree-editor
I’m working on a website where you can paste your NuGet package references and get notified by email if/when a package you’re using is found in a vulnerability database.
I’m working on improving the global agents.md experience.
I’m doing composable and dynamic global profiles which are selected based on what you’re doing.
A way to access social media content read only without an account, with HTML, RSS/Atom and at some point ActivityPub probably. I will probably post here in a few weeks when PoC will up.
Nothing besides normal work. Sometimes is good to do a break on personal projects after 3 years nonstop
My first video game! It's a 3D First Person Puzzle game where Medusa turns you to stone, but your statue remains when you respawn - and you use this to solve the puzzles in the game
https://store.steampowered.com/app/4810350/Medusas_Gaze/?bet...
Created with 0 AI assets
I think that the IoT open source software landscape is missing a simple middleware to abstract the various network providers. I'm trying to fill that gap and hope to author a "show HN" soon about that :-)
Audion - a scripting language that is very fun to write and lets you make interactive music, installations, generative compositions etc https://github.com/audion-lang/audion using supercollider or any daw and hardware. AI picks it up easy so Agentic coding in Audion works very well too.
hack music
I'm working on https://docx-editor.dev/, open-source, .docx editor library for building document apps.
Making it possible to share a deck in my flashcard app https://texeditor.com
Trying to upgrade my data viz project [0] from Svelte 5.35.7 (pre async) to the latest version and making sure that the performance is not negatively affected (e.g. [1]).
A kubernetes desktop client that can connect to multiple cluster simultaneously
Been working on making it much easier for application deployments to get access to a isolated database/schema. The usual pattern currently is to assume that each app creates a new database, which ignores the backups, monitoring etc required for each database. Implemented support for Postgres and MySQL.
Wrote up more details at https://openrun.dev/blog/service-binding/
Trying to write a formally verified simplified (1D) implementation of Ruckig, more to learn the tools than for the result, although I want that too. Some fun challenges with numeric stability (using the big hammer of arbitrary precision to address that for now), etc. Still don’t have a real path to bridge correctness arguments through a formalization of Sturm’s theorem or similar, accepting it as an axiom for now.
Compiled agents: http://squig.com/
It takes your instructions, write a versioned spec, then generates a hybrid workflow of code+LLM calls and protects it with tests/evals
The result is that the agents run much faster (90% of it is code), cheaper (LLM steps are scoped tightly and uses smaller models) and reliably (specs get turned into coded state-machine)
Attemping to write my own CDCL SAT solver right now. I've experimented in the past with a DP & DPLL SAT solver. I'm currently somewhat mentally stuck on how to create the derived clause after a conflict, but I'll get there :)
I have been building https://longhorizon.dev
It let's developer do test planning and testing automation using their coding agents. The records of the testing sessions are then shareable and can be added to PRs, giving the reviewers visibility into how the feature works, what scenarios are handled and tested and what might have been missed.
Working on Margin Points (https://www.marginpoints.com/): a daily essay series on business and tech. Already over 80 essays in. I'm playing around with a daily live call-in show for readers who want to discuss ideas while the essays are rough drafts and help shape the thinking.
Currently working on HN Alerts — a simple free site I made to alert me (via email) to trending stories on Hacker News.
It sends me an email once a story hits a certain number of upvotes per minute, so it's useful for keeping track of breaking news.
It'll also soon allow you to get alerted to specific words or phrases in titles. (I have one set up so the monthly hiring threads notify me as soon as they appear.)
I enjoy creating new benchmarks for LLMs. Lately, combining scientific computing tasks (n-body sim, Monte Carlo, etc) with Apple Metal GPU kernels (evolved through LLMs) led to a curious benchmark I believe: https://github.com/vicgalle/metal-sci-kernels
Working on caddy-snake, a python plugin for Caddy: https://github.com/mliezun/caddy-snake
And on a new post about how to design web apps for the AI-era for my blog: https://mliezun.com
Been deep diving into visual model architectures. Currently running some small evaluations on an idea around unlabeled mask segmentation that will run efficiently on mobile phone hardware. Looking promising so far!
For fun: https://squishy.franzai.com/
For curiosity: https://airplane-ai.franzai.com/ based on Gemma
For profit: optimizing my virtual desktop in the cloud setup for AI First workshops
A DSL for machine learning programs: https://pypie.dev/ Embedded in Python, written like Python, but with static type safety (e.g. it catches tensor shape mismatches at compile time)
I am working on https://coderscreen.com/
an open source technical interview platform built for modern interview workflows like takehomes, agent coding sessions, as well as the standard leetcode-style questions.
A very simple idea: when you eat more than your maintenance calories, you gain weight; when you eat less than your maintenance calories, you lose weight.
By using an algorithm, we can accurately figure out your maintenance calories more accurately than traditional regression based formulas like katch mc ardle.
It's way more accurate than calorie burn tracking devices like fitness bands and watches. (garmin/apple watch etc...)
MacroCodex helps you spot dips in maintenance calories from metabolic adaptation, then auto adjusts your calorie target and macros so your plan stays aligned with your real maintenance calories (TDEE).
It's very useful to those who find it hard to gain or lose weight.
it's a completely free app, no paywall, no unnecessary data collection.
Already reached 13,000+ users
I'm working on Kronotop, an open-source, distributed, transactional document database built on FoundationDB, featuring Redis protocol compatibility and a MongoDB-style query language.
Vinyl-Tags: a set of command line tools to facilitate the process of preparing analog recordings for addition to music libraries. Fetch metadata and cover art from Discogs (or generate your own); co-run with Audacity to locate track boundaries efficiently; add the metadata to the audio tracks.
Been building a file manager for almost four years that combines the best of Notion and Obsidian while remaining a competent file manager in the process. It's called Phials.
Not technically released even though the site is live, but close enough to a beta at this point.
I'm using an old domain to put together a curation of film edits set to music
I am working on a human-only community called Island. You can request an invite now over at https://island0.com.