You can. I use it exactly that way with the individual terminal sessions accessible.
I'm mostly using it now because it integrates with ssh while still supporting image paste. I also use it via it's json API for a harness I'm working on which is agent agnostic.
I do expect I'll move off it if it becomes hostile and another tool takes it's place.
I'm doing something similar. Building a text/tactical RPG with typed/structured markdown as the authoring language. So far I've built libraries for character and item rendering, as well as scene graph parsing with procedural generation (also in markdown). Now I'm actually introducing Bevy to enable animation and interactivity. First time using Bevy, and I'm also using teams of agents to do the development, driven by a custom system of plans and review/feedback.
All my graphics are procedural, with no assets apart from open fonts.
The first game is meant to be a sort of Isekei parody, so the animation and character design is anime inspired, with tactical RPG gameplay, and some time-travel/reset mechanics. The story gets into the irony of being a game so magic not being real on Earth, and some historical Earth scientists play a part in the deeper lore modules. The magic construction is an actual MLP puzzle with polar coordinates.
I've been experimenting with using J-Space (and final hidden layers) to extract the semantic meaning of words to improve TTS output accuracy using Qwen and Gemma models. My goal is to either map to an alternative token set where heteronyms are preserved or to output parenthesized IPA annotations for ambiguous words (with standard tokens). It's interesting to me that LLMs preserve this data throughout their processing but discard it in the final output.
I've also looked into extracting actions from J-Space to short-circuit a local assistant on low-end hardware. Are there any resources on how to do this training with inexpensive H100 instances (~$8/hr)? I would be opening up the final weights for Qwen/Gemma layers.
Payments should be the obvious feature. The commercials for various smart watches show the same thing: somebody buying a coffee with just their watch.
But the reality is different. On my smartwatch (an older Samsung, but same Google OS merged with Tizen) there's a PIN required if you enable payments on the watch. I understand why, the secure element requires it. But it makes every other feature of the watch useless to me. I don't have any secrets I want a watch to protect. I want to be able to time workouts while standing on a treadmill.
They could solve this, only have large amounts require the code while letting me buy a coffee without it, but I'm sure there's some line in an agreement between Google and the banks prohibiting this. The risk has to be transferred to the customer, even if the likelyhood of somebody buying a coffee with my watch is low.
Product design should consider all of these things, but getting out the next smartwatch without thinking it through is more inline with quarterly objectives. There isn't even a Steve around to piss off enough to do something about it.
>But it makes every other feature of the watch useless to me
How exactly? Samsung watches only require the pin to be enabled if you want payments enabled. You only have to enter the pin if you have taken the watch off. As long as it can detect that it remains on your wrist then payments continue to be enabled no pin required...
Using it now. It seems like I finally found something that works. Having the same agents accessible on the laptop in a large TUI and quickly viewable from my phone has been useful.
Tailscale integration works well too. The mobile notification setup was a little clunky and the instructions were confusing, until I found the directory with the shell scripts. It should probably expose a herdr action to generate the keys and include that in the documentation.
One thing though: the subagent lines should be clickable like they are in Termux but your actions box absorbs the click and focuses the GUI input line.
If you're looking for way to get userdebug functionality without building a huge source tree, I created regraph[0]. It's similar to other solutions but does not inject sudo or root, other than the supported adb root path.
It starts with an upstream GrapheneOS build and modify the system image (super) in place, signed with the published userdebug keys.
A nice little asciinema demo would be helpful on the TUI page. I should be able to see what it is, how it presents the contained agents, etc.
I've been evaluating a few of these (and built one into another project I was working on, almost by accident), and am mostly looking for a frontend agnostic, terminal only (not harness) which can submit instructions to agents one line at at time with rate-limiting.
I was also surprised by tmux being built on shared memory when I tried to route it over a vsock to a VM. One of the annoyances with tmux is it's failure to forward environment changes to the individual tabs (such as an option when attaching), or allow for something like a ssh-agent forwarder (shouldn't be built in though).
I'm mostly using it now because it integrates with ssh while still supporting image paste. I also use it via it's json API for a harness I'm working on which is agent agnostic.
I do expect I'll move off it if it becomes hostile and another tool takes it's place.
reply