What Are You Working On? (April 2026)

VERDURE is still a creative plant-generation sandbox where you grow and sculpt stylized trees.

https://store.steampowered.com/app/4069810/VERDURE/

I'm building a robust sandboxing environment for AI agents.

It supports multiple sandboxing backends such as docker, podman, kata, firecracker, and for Mac seatbelt and tart.

Any agent is in theory supported, but it has specific support for Claude, Gemini, codex, aider, and opencode.

Your workdir is never touched by the AI, nor is your system. It doesn't have access to your secrets (beyond what you've explicitly given), and you can restrict network access.

You move changes back to your workdir using diff and apply, so you choose which changes to keep.

I use it for all my agentic work, and couldn't go back to using Claude without it.

https://github.com/kstenerud/yoloai

I am working on a P2P VPN app that lets you route your traffic through a friend's Internet connection easily. It has a few distinct uses, but right now I am testing whether emigrants from authoritarian countries will be interested in providing censorship-free connectivity to their family/friends at home.

It's called Spora: https://spora.to/

The current MVP is about 90% vibe-coded while being a fairly sophisticated piece of software.

Building Sensonym (https://sensonym.com), a vocabulary learning app that uses phone sensors (gyroscope, camera, mic, accelerometer) to create physical interactions tied to word meanings. Based on embodied cognition research. I've just launched it on iOS and Android in Germany with support for 10 languages.

The garden.

Ha! All jokes aside testing some different local dev workflows, so much cool AI tooling about.

Currently working on community engagement for AI education infrastructure — specifically focused on the gap between technical AI literacy (well-served by HN, fast.ai, etc.) and non-technical AI literacy for people who use and govern AI without coding.

Building out content and community presence for IAIDL (https://iaidl.org), a vendor-neutral AI certification for non-technical roles. The angle: AI deployment decisions increasingly involve non-engineers — managers, HR, compliance — and the training infrastructure for them lags far behind the technical side.

Interested if anyone else is working in the "AI for non-developers" education space.

https://crit.md - a CLI tool for reviewing AI coding agent output like a GitHub PR.

I got frustrated with Claude Code and Cursor producing plausible-but-wrong changes with no easy way to annotate and push back, without making a full PR. crit makes the review stage fun again!

Works on both plans as well as code itself. It’s been very rewarding hearing from folks who use it, everyone has been very kind! My most successful side project already :)

GitHub: https://github.com/tomasz-tomczyk/crit