Live data from Hacker News

TmuxAI: AI-Powered, Non-Intrusive Terminal Assistant

tmuxai.dev

61–67 of 67 posts

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

#62

I do love this, but haven't managed to actually try it out. ( I stopped trying and moved on) But well done for launching (the following is not hate, but onboarding feedback) Who else had issues about API key ? 1. What is a TMUXAI_OPENROUTER_API_KEY ?? (is like an OPENAI key) ? 2. If its an API key for TMUXAI ? Where do I find this ? Can't see on the website ? (probably haven't searched properly, but why make me searc…

Thanks for feedback, agree those stuff could be clearer. Will handle. Just to answer your questions, it's an OpenAI API compatible service, which you can generate here: https://openrouter.ai/settings/keys Also added recently in readme how you can use OpenAI, Claude or others.

Why does running 'help' require tokens?

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

#63
post #49

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?

Gemini has a very generous Free Tier for their API (including 2.5 Flash and 2.5 Pro): https://aistudio.google.com/app/apikey

Keep in mind that using the free tier models means Google will keep what you send and use it for training.

In bold in their terms is: "Do not submit sensitive, confidential, or personal information to the Unpaid Services."

https://ai.google.dev/gemini-api/terms#unpaid-services

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

#65
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…

and this is why you want mfa and gitops with multiple users signing off on a change

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

#66
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…

Yes there is, Velero.

Yeah it might be problematic, but people make mistakes like this all the time, which is why rm -Rf /home /user/.file is a well known rite of passage.

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

#67
post #44

Earlier quoted context omitted.

There's this new thing I'm currently working on. I have a tool that does a clean execvp of what you pass it through, as a total wrapper. You can do ./tool "bash" and then open up nvim, emacs, do whatever, while the tool sits there passing things back and forth cleanly. Full modern terminal support. Now here's the thing. You get context. Lots of it. Here's what it can do: psql# I need to join the users and accounts ta…

Mind blown. This is so simple. It’s like rlwrap, but generic. So you could reimplement rlwrap with this. I’ve been experimenting with schemesh recently. It’s a shell with ask control structures in scheme. Amazing, but a little immature still. Having a scheme middleware would be stronger: I can have a full zsh where a control key drops me onto a Scheme interpreter. Now, how far up your process tree do you want to host…

https://9ol.es/tmp/fizzbuzz.webm

Finally kind of working. There's the first demo video

I escape out three times: once for basic shell help, the next while I'm inside of vim and finally at the python interpreter. The recent input and output are the context clues to solve the query, which is the part in reverse video.

Then the code is injected into the proxy wrapper

https://github.com/kristopolous/llmehelp/tree/main/shellwrap is the code.

Post reply on HN