Check out Claude Code Team Orchestration [1].

Set an env var and ask to create a team. If you're running in tmux it will take over the session and spawn multiple agents all coordinated through a "manager" agent. Recommend running it sandboxed with skip-dangerous-permissions otherwise it's endless approvals

Churns through tokens extremely quickly, so be mindful of your plan/budget.

1. https://code.claude.com/docs/en/agent-teams

Very cool, we have some Korean Pokemon cards that this would work great on. Are you planning to support other languages?

It's for personal use, and I wouldn't call it great software, but I used Claude Code Teams in parallel to create a Fluxbox-compatible window compositor for Wayland [1].

Overall effort was a few days of agentic vibe-coding over a period of about 3 weeks. Would have been faster, but the parallel agents burn though tokens extremely quickly and hit Max plan limits in under an hour.

1. https://github.com/ecliptik/fluxland

This is really cool. Out of curiosity did you know how to do this sort of programming prior to LLMs?

Not really, most of my programming experience is for devops/sysadmin scripts with shell/perl. I can read python/ruby from supporting application teams, but never programmed a large project or application with it myself. Last I used C was 25 years ago in some college courses and was never very good with it.

Pretty cool!

Lynx supports gopher [0] and check out Bombadillo [1], it's a stripped down "small web" (gopher, gemini, finger) only terminal browser.

Gopher is sort of like Latin, it's a dead protocol, but is still useful.

0. https://lynx.invisible-island.net/lynx_help/lynx_url_support...

1. https://bombadillo.colorfield.space/

This eerily feels like speed running Eternal September.

I've read 51 books this year (just finished Hyperion) which is 50 more than 2024.

I attribute this increase to a few things,

1. Borrowing from Libby puts a 21 day time limit to finish a book, encouraging me to read it before it's due.

2. Not discriminating from reading on my phone. Kindle app syncs between devices, and makes it easier to read a few pages here and there instead of waiting for uninterrupted sessions with my Kindle.

3. Continually updating a To Read list, mostly by going to Barnes and Noble, taking pictures of featured book tables, then adding the interesting ones to my Libby hold list.

4. Borrowing with Libby makes it easier to bail out of a book that doesn't intrigue me. Instead of forcing myself to finish something I spent $ on, I can just return it and move onto something else, feeling 0 guilt.

There are search engines, directories and feed aggregators [1].

Best means of discovery is like the original web, you surf it, bouncing from capsule to capsule finding what you like.

1. https://github.com/kr1sp1n/awesome-gemini?tab=readme-ov-file...

From what I remember about the name, it's derived from NASA space programs. Where Gopher is Mercury, Web is Apollo and Gemini is in between.

Gemini is a new internet protocol which:

- Is heavier than gopher

- Is lighter than the web

- Will not replace either

- Strives for maximum power to weight ratio

- Takes user privacy very seriously

No images is a bit of a deal-breaker for almost everyone I would have thought.

Images aren't prohibited. They are linked but can be shown.

Gemini users kind of have a meltdown if you try to implement any optional features. One browser implemented favicons and users were flaming the github issues demanding it be removed or they would implement IP blocks for any users requesting the favicon url. I tried to find the link but search results are drowned out by Google's Gemini.

By users in plural you mean a professionnal troll called Drew Devault who afaik isn't a gemini protocol user anymore.

That sounds about right. My memory of the thread is a bit fuzzy.

Yes I mean images in the page.

I wonder how discovery and search work if it’s just a bunch of linked documents? Do search engines exist outside of Gemini and link into it?

There are several search engines of Geminispace, running as Gemini servers. There are also a number of feed aggregators that are widely used.

Also, part of the idea is discovery through linked high-quality sites. Like the webrings of the 1990s.

You find a capsule you like and discover others through that person's links.

The protocol supports query strings so the server can generate content based on the string, which can be used for an in-Gemini Gemini search engine. It doesn't have to be all static content. People could also build out a directory (like the now defunct DMOZ and similar directories for the Web).

And a Gunship sticker. After looking at some of these I wish there was an optional field people could add so others with overlapping interests could follow a blog/socialmedia/etc.