Replies: 1 comment 2 replies
-
Auto-detection is a bit tricky and not sure if it's worth to start fixing those challenges. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I know that if I ssh to a server, we don't know what kind of shell is running there. But maybe I can configure an assumption (I use bash everywhere) or we could autodetect - OS, shell, everything.
But it would be pretty cool if I could ssh to a machine, run /prepare to configure the prompt and work as if I am in prepared session.
Yes, I can ssh to the target machine, install tmuxai there and work that way. The problem is that if I run local model on my laptop, I don't have that accessible on the remote machine and it might not be capable of running the model. And I might not want to give my commands to a cloud machine via API.
Beta Was this translation helpful? Give feedback.
All reactions