It's amazing how the beta release of Rex is already so polished and useful. I'm absolutely convinced that when it releases outside the mailing list, it will not only receive a huge hype but will replace Ghostty or iTerm for a huge amount of people. And I was wondering all the time why Ghostty's tab handling was so primitive when every thing else is so optimized, but it now makes sense where all that effort on tab handling went.
For me it has already replaced tmux, herdr, mosh, claude mobile app, hermex, iTerm2 and even ssh in many cases. And in combination with the IOS app for the first time I really feel like I can work from everywhere without any limitations, its incredible. It's really optimized for using claude code with the touchscreen and touch keyboard as well.
Just crazy to think it replaced the whole procedure of running an agent within tmux on a server, then ssh'ing into the server on some random terminal emulator ios app with barely usable controls.
I think herdr has no future in competing against mitchelh and you can see it when you compare the native apps and features at this stage.
I wonder how much they move towards becoming the systemd of agents (IN A GOOD WAY THOUGH)
I use the supermatt skills a lot in a issue-based workflow. It's /orchestrate skill is quite good and you can just tell it to use Rex instead of Herdr.
Also with Rex I just always have one session open with an agent that i tell to "look how far the other sessions are progressing, or to look if anything needs any input from me and if so present me all the decision and things that need me in a site you create for that purpose. explain it intuitively without assuming prior knowledge. a site where i can export my choices and commentary to json so i can send it back to you" or something like this
That's funny, I got tired of tmux the other day (it got into 100% spin loop from an unsigned int underflow used as a loop condition variable. and I debugged it all by myself like a big boy, without LLMs!) and built something that seems to be identical in architecture in terms of the "supervisor which allocates pty, just stream bytes, client decodes" part. I even use libghostty for the HW accelerated GUI I built. It's the right way to go imo and it's not too difficult to build... hence...
I don't really understand why they would turn this into a company. I become suspicious of products that raise a lot of VC money, implying that they expect a unicorn-ish valuation, where I don't see them being able to justify their valuation via obvious monetization techniques (e.g. selling a classic license for a GUI app where you get updates for some period of time, usually a year, and then you get to keep the software, but no longer get updates, just in case people forgot how things worked before subscriptions).
That usually implies something like selling cloud subscriptions, vendor lock-in, or selling data. I'm happy to be wrong, but it's just an extremely common pattern. And as an aside, I know there's an impulse to monetize everything, but I think we should probably fight that impulse.
I think that the tells, if they are in fact legitimate, are negligible at best or subtle at worst. It looks like the site uses Tailwind, so if AI was involved it wasn't generating the design from scratch. If it did then I'm impressed because usually it sucks. This is alright.
Really? The website, you mean? :( I thought to myself, "what a cute, well designed webpage!" when I saw it. Maybe with time this site will stand out like those Claudeslop ones.