Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Just-bash: Bash for Agents

github.com

Post reply on HN
Print view View original

11–20 of 78 posts

Re: Just-bash: Bash for Agents

#11

Post by gaigalas »

esafak wrote: post #10
athorax wrote: post #5

Earlier quoted context omitted.

Why do you think there is a lot of training data? Could it be because it's stable and virtually unchanged for decades? Hmmm.

Because bash is everywhere. Stability is a separate concern. And we know this because LLMs routinely generate deprecated code for libraries that change a lot.

This project runs on all shells, totally portable:

https://github.com/alganet/coral

busybox, bash, zsh, dash, you name it. If smells bourne, it runs. Here's the list: https://github.com/alganet/coral/blob/main/test/matrix#L50 (more than 20 years of compatibility, runs even on bash 3)

It's a great litmus test, that many have passed. Let me know when just-bash is able to run it.

Re: Just-bash: Bash for Agents

#12

Post by RobertLong »

This ends up reading files into node.js and then running a command like grep but implemented in JS. I love the concept but isn’t this incredibly slow compared to native cli tools? Building everything in JS on top of just readFile and writeFile interfaces seems pretty limited in what you can do for performance.

Re: Just-bash: Bash for Agents

#13

Post by _pdp_ »

Interesting concept but I think the issue is to make the tools compatible with the official tools otherwise you will get odd behaviour. I think it is useful for very specific scenarios where you want to control the environment with a subset of tools only while benefiting from some form of scripts.

Re: Just-bash: Bash for Agents

#14

Post by wild_egg »

IceWreck wrote: post #7

At this point why not make the agents use a restricted subset of python, typescript or lua or something. Bash has been unchanged for decades but its not a very nice language. I know pydantic has been experimenting with https://github.com/pydantic/monty (restricted python) and I think Cloudflare and co were experimenting with giving typescript to agents.

Agents really do not care at all how "nice" a language is. You only need to be picky with language if a human is going to be working with the code. I get the impression that is not the use case here though

Re: Just-bash: Bash for Agents

#16

Post by esafak »

gaigalas wrote: post #11
esafak wrote: post #10

Earlier quoted context omitted.

Because bash is everywhere. Stability is a separate concern. And we know this because LLMs routinely generate deprecated code for libraries that change a lot.

This project runs on all shells, totally portable: https://github.com/alganet/coral busybox, bash, zsh, dash, you name it. If smells bourne, it runs. Here's the list: https://github.com/alganet/coral/blob/main/test/matrix#L50 (more than 20 years of compatibility, runs even on bash 3) It's a great litmus test, that many have passed. Let me know when just-bash is able to run it.

I have no connection to coral or just-bash. Why don't you do it yourself and let us know, since you are familiar with it?

Re: Just-bash: Bash for Agents

#17

Post by simonw »

IceWreck wrote: post #7

At this point why not make the agents use a restricted subset of python, typescript or lua or something. Bash has been unchanged for decades but its not a very nice language. I know pydantic has been experimenting with https://github.com/pydantic/monty (restricted python) and I think Cloudflare and co were experimenting with giving typescript to agents.

Being unchanged for decades means that the training data should provide great results even for the smaller models.

Re: Just-bash: Bash for Agents

#18

Post by simonw »

RobertLong wrote: post #12

This ends up reading files into node.js and then running a command like grep but implemented in JS. I love the concept but isn’t this incredibly slow compared to native cli tools? Building everything in JS on top of just readFile and writeFile interfaces seems pretty limited in what you can do for performance.

Performance of the tools doesn't really matter when you have a full LLM inference loop in between each tool call.

Re: Just-bash: Bash for Agents

#19

Post by simonw »

gaigalas wrote: post #2

https://github.com/vercel-labs/just-bash/blob/main/src/spec-... That's a lot of incompatibilities. LLMs like to use the shell because it's stable and virtually unchanged for decades. It doesn't need to worry much about versions or whether something is supported or not, it can just assume it is. Re-implementing bash is a herculean effort. I wish good luck.

Incompatibilities don't matter much provided your error messages are actionable - an LLM can hit a problem, read the error message and try again. They'll also remember that solution for the rest of that session.

Re: Just-bash: Bash for Agents

#20

Post by sheept »

IceWreck wrote: post #7

At this point why not make the agents use a restricted subset of python, typescript or lua or something. Bash has been unchanged for decades but its not a very nice language. I know pydantic has been experimenting with https://github.com/pydantic/monty (restricted python) and I think Cloudflare and co were experimenting with giving typescript to agents.

I feel like Deno would be perfect for this because it already has a permissions model enforced by the runtime
Post reply on HN