Wow this looks very promising. Clean and simple enough to try today instead of saving it for later in a bookmark.

Honestly, I came across some tmux based tools earlier like agent-deck, their text-clutter and workflow learning curve repelled me because of the very small context window of my brain.

Thanks for sharing!

Thanks for giving it a try!

If you have any questions or problems just open a issue on github!

Thanks for sharing a realistic workflow in detail, I think that would be very useful, specially thinking in terms of "same good software engineering practices" and maybe even going a step further to decouple things when designing future projects.

Thinking about it again, when i tried to use parallel agents last time, I ended up having a lot of overhead in merging and testing the features. Maybe part of it is to either allocate small tasks to each agent, when complete isolation of codebase is not expected, to make the changes easy to test.

I definitely feel a bit more encouraged to try out a bit more parallalization in my work by being more mindful of the surface area of the feature.

They are almost claiming FHE, isn't it just a matter of creating the right tool to get the generated tokens from RAM before it gets encrypted for transfer. How is it fundamentally different than chutes?

But I will loose it all, that's why you should bookmark everything, have terminal bookmarks of paths, use git worktrees to allow leaving workspace messy. Use a lot of notion docs, .md docs, notebooks. Places where you organize stuff, so that you can come back easily when you need it again.

A running txt file for each project/work capsule has been wonders. Then common txt files for anything you learned or, things you need to learn, notes/todos, etc.

I think I would be half as productive as I'd like without this.

Yes. I have started doing this with an Obsidian note for each project. Any ongoing lists go there, and each day has a heading with todos and thought process while solving the todos. Then in my main todo list or kanban I just link to the project with one sentence on where to resume the next day.

I've setup my ~/Stuff, ~/CurrentStuff and mkstuff some time ago and it's extremely useful to keep clutter under control for me. I use this as temporary working directories for small stuff that's not a real project yet. `mkstuff ticket-123-team-db-troubleshooting` creates me a directory `~/Stuff/2026-02/12-ticket-123-team-db-troubleshooting` and drops the shell into that. ~/CurrentStuff is just a link to current months stuff.

This way I have everything about a ticket in a place and if someone is like "uhh, you did something to something some 3 months ago or so?" - ~/Stuff/2025-1{0,1,2} probably knows, I certainly don't. I can find things again like this :)

I'll eventually have to setup some automated archiving for it, but so far it's not using too much space.

Yes, I do believe you own the correct answers - however, can you make a long form blog post about this and share it on Hacker News? We need the rest of the information.

My room should be messy when I come back to it - how else would I find anything if it wasn’t where I left it?

I started working on a task management app that could handle the massive amounts of context switching I do on a daily basis - aggregated over slack, iOS reminders, Jira, linear, and obsidian... I'm glad I'm not alone in having such crazy environment.

I saved thousands of bookmarks and realized that I hadn't opened a single one in ten years. It would be better to have open windows.

I tried this. Never managed to bother going back to those "organized" notes though; ended up being a waste of time.

Lol love the extent of clarity of the experiment, findings and interface. I think that for practical purposes, it would be better if the std-dev of pieces with size above a certain threshold is observed. From my experience, pieces above a certain size cause inconsistency in cooked onions. But maybe it depends on the recipe.