This looks great! I would use this if you had a dispatcher for using a custom/local OpenAI-compatible API like eg llama.cpp server. If I can make some time I'll take a stab at writing one and submit a PR :)

Already exists :)

Set the `local_uri` setting in the configuration (`llm2sh --setup`), and either pass `-m local` on the CLI or set `"default_model": "local"` in the config.

PRs are always welcome.

Thanks so much!

Some really nice things:

+ GPLv3

+ Defaults to listing commands and asking for confirmation

+ Install is just "pip install"

+ Good docs with examples

Is there a way to point at an arbitrary API endpoint? IIRC llama.cpp can do an OpenAPI compatible API so it should be drop in?

I'm glad you like it! The whole point is to have a simple no-frills clean CLI experience.

> Is there a way to point at an arbitrary API endpoint?

Yes. Set the `local_uri` setting in the configuration (`llm2sh --setup`), and either pass `-m local` on the CLI or set `"default_model": "local"` in the config.

Oh, nice; thanks:)

Nice tool. I am using ai-shell for that purpose.

https://github.com/BuilderIO/ai-shell

Wonder how this compares to open interpreter.

Would consider rewriting in a language that is more portable? Ideally this would be a single binary, excluding the models!

I've no plans for it myself, but that sounds like an interesting project! It should be fairly easy to hack together. The actual logic itself is just a few dozen lines of glue code around a single HTTP POST request.

There are plenty of variations on this tool around, it would be nice to see a comparison.

I remember at least 5 of them discussed right here on HN

Cool! I’m experimenting with something like this that uses docker containers to ensure it’s sandboxed. And, crucially, rewindable. And then I can just let it do ~whatever it wants without having to verify commands myself. Obviously it’s still risky to let it touch network resources but there’s workarounds for that.

What is the (hoped for) future after your experiments? Are you hoping to gain enough confidence/refinement on it that you can run it on you main system? Or just hoping to serve curisioty? (I could see myself doing either, so just curious)

I wouldn't be happy to run it containerless, per se, but within docker or on a remote spun-up box it's fine. I think it's mostly something to play with for now, but I'll eventually build it into a couple of AI platforms I run, just to help with amorphous tasks and more deterministic outputs with math and data.

Does it understand commands such as "get this Nvidia driver to work"?

Not sure that it actually read any context from your environment. GitHub copilot CLI does not. So if you want it to answer something like that, then you will need to tell it exactly what "this Nvidia driver" is actually is.

I think it's one-round, not interactive. So it can't do complex tasks

This looks good.

I created something similar using blade a while back, but I found that using English to express what I want was actually really inefficient. It turns out that for most commands, the command syntax is already a pretty expressive format.

So nowadays I'm back to using a chat UI (Claude) for the scenarios where I need help figuring out the right command. Being able to iterate is essential in those scenarios.

How much time does this gain you from the perspective of "you have to double check its output and hope it didn't make a mistake"?

Doesn't save time, but it's a nice experience. Sometimes you get exposure to something you didn't know, other times it makes the boring stuff less annoying.

This is a fascinating tool! `llm2sh` looks like it can save a lot of time and hassle for those who often find themselves Googling shell commands. The fact that it supports multiple LLMs and offers a 'YOLO mode' is both exciting and a bit scary . I'm curious, has anyone tried integrating it with more complex workflows? Any stories of it saving the day (or causing chaos)?