Ask HN: What Are You Working On? (March 2026)
381–390 of 1001 posts
Re: Ask HN: What Are You Working On? (March 2026)
#382- UI for sandbox-exec to protect filesystem - Network sandbox per domain - Secrets filter via gitleaks - Vertical tabs option
It's highly customizable. You generate native macOS app wrappers for each terminal app, each with its own rules and customizations.
Re: Ask HN: What Are You Working On? (March 2026)
#383There is an API, and it’s a straightforward task, but one thing led to another and I’m also improving the app UI. The update will take some time but I hope it will only be better.
[1]: https://lab174.com/nonodle/
[2]: https://apps.apple.com/app/nonoverse-nonogram-puzzles/id6748...
Re: Ask HN: What Are You Working On? (March 2026)
#384This is the kind of project that creates something from as little as possible, where the only things you need to get started are a very basic RISC-V assembler and a computer or emulator to run it on.
I don't have anything interesting to show yet because I just started yesterday, but one day I will show you.
Re: Ask HN: What Are You Working On? (March 2026)
#385I changed gears and moved into the video games industry at the end of 2021. I started developing a city builder called Metropolis 1998 [1], but wanted to take the genre in new directions, building on top of what modern games have to offer: - Watch what's happening inside buildings and design your own (optional) - Change demand to a per-business level - Bring the pixel art 3D render aesthetic back from the dead (e.g R…
Re: Ask HN: What Are You Working On? (March 2026)
#386The problem: every agent (Cline, Aider, Codex, Claude Code) has unrestricted access to your filesystem, shell, and network. When they process untrusted content — a cloned repo, a dependency README — they’re prompt injection vectors with full machine access. No existing tool evaluates what the agent actually does at the syscall level.
grith wraps any CLI agent without modification. OS-level interception captures every file open, network call, and process spawn, then runs it through 17 independent security filters in parallel across three phases (~15ms total). Composite score routes each call: auto-allow, auto-deny, or queue for async review. Most will auto approve - which eliminates approval fatigue.
Also does per-session cost tracking and audit trails as a side effect of intercepting everything.
Re: Ask HN: What Are You Working On? (March 2026)
#387I just started building an operating system that will be written entirely in one text file. This text file includes in order: a readme, a RISC-V assembly boot code, then the rest. You run it by compiling the initial boot code with a RISC-V assembler, then you concatenate the binary with the whole text file itself. Then when you run it, the boot code will compile the rest of the text file (the operating system), inclu…
Re: Ask HN: What Are You Working On? (March 2026)
#388https://finbodhi.com — It's an app for your financial journey. It helps you track, understand, benchmark and plan your finances - with double-entry accounting. You own your financial data. It’s local-first, syncs across devices, and everything’s encrypted in transit (we do have your email for subscription tracking and analytics). Supports multiple-accounts (track as a family or even as an advisor), multi-currency, a…
Re: Ask HN: What Are You Working On? (March 2026)
#389Re: Ask HN: What Are You Working On? (March 2026)
#390I vibe coded a tiny MUD-style world sim where LLMs control each character. It's basically a little toy sandbox where LLMs can play around. There's no real goal to this, I just thought that it would be fun, like a more advanced tamagochi. One of the issues I encountered initially was that the LLMs were repeating a small set of actions and never trying some of the more experimental actions. With a bit of prompt tweakin…