Live data from Hacker News

TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

tmuxai.dev

31–40 of 67 posts

Re: TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

#32
Had a terrible experience with warp. I personally don't use warp, but I know one colleague who uses it. One day, he ran `kubectl describe ` and warp suggested `kubectl delete ` and he pressed enter. He was lucky the resource was not critical and could be recreated without any damage. Think about what would have happened if the same thing had happened for the namespace resource. People go into automatic accept mode after some time, and this is very dangerous when you do anything at the terminal, because there is no UNDO button.

Re: TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

#33
post #28

I've got a similar approach from a Unix philosophy. Look at the savebrace screenshot here https://github.com/kristopolous/Streamdown?tab=readme-ov-fil... There's a markdown renderer which can extract code samples, a code sample viewer, and a tool to do the tmux handling and this all uses things like fzf and simple tools like simonw's llm. It's all I/O so it's all swappable. It sits adjacent and you can go back and fo…

Maybe if you could explain what exactly is happening in the savebrace example because it's not clear how it relates to this.

thanks. that's exactly the feedback I need! Appreciated. I put more screenshots here: https://github.com/kristopolous/llmehelp ... maybe that's clearer?

Re: TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

#34
post #32

Had a terrible experience with warp. I personally don't use warp, but I know one colleague who uses it. One day, he ran `kubectl describe ` and warp suggested `kubectl delete ` and he pressed enter. He was lucky the resource was not critical and could be recreated without any damage. Think about what would have happened if the same thing had happened for the namespace resource. People go into automatic accept mode af…

I love warp but I always turned the AI off- the GUI improvements were enough for me. I have maintained a general rule for a long time now that when manual commands are run on production, someone else must be watching what’s going on and approving commands or approve them ahead of time.

Re: TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

#35
post #31

Can this be aimed at ollama or some other locally hosted model? It wasn’t clear from the docs since their config examples seem to presume you want to use a third party hosted API.

Given ollama has a openai compatible API[0], quick searching in repo returns this

https://github.com/alvinunreal/tmuxai/issues/6#issuecomment-...

1: https://ollama.com/blog/openai-compatibility

Re: TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

#37
post #28

I've got a similar approach from a Unix philosophy. Look at the savebrace screenshot here https://github.com/kristopolous/Streamdown?tab=readme-ov-fil... There's a markdown renderer which can extract code samples, a code sample viewer, and a tool to do the tmux handling and this all uses things like fzf and simple tools like simonw's llm. It's all I/O so it's all swappable. It sits adjacent and you can go back and fo…

Maybe if you could explain what exactly is happening in the savebrace example because it's not clear how it relates to this.

If I've understood this interesting workflow correctly, there's two major components.

streamdown: a markdown renderer for the terminal, intended for consuming LLM output. It has affordances to make it easier to run the code snippets: no indentation, easy insertion in the clipboard, fzf access to previous items.

llmehelp: tools to slurp the current tmux text content (i.e. recent command output) as well as slurp the current zsh prompt (i.e. the command you're currently writing).

I think the idea is then you bounce between the LLM helping you and just having a normal shell/editor tmux session. The LLM has relevant context to your work without having to explicitly give it anything.

Re: TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

#40

So I have yet to use any tool that needs an API key because I am concerned about costs. Does anyone have any idea what the daily usage of something like this would cost?

it's not that big with gemini flash model, no need for full model for this
Post reply on HN