On the "why bash not python/lua" question -- the answer isn't that bash is a better language. It's that bash is the only language you can assume is there.
When we run autonomous agents across different environments (Vercel functions, local dev, CI containers, remote VMs), Python availability is a negotiation. Bash is given. The agent doesn't need to worry about whether venv is activated, which Python version is installed, or whether a package needs to be pip-installed first.
There's also a subtler benefit: bash commands have predictable, well-documented side effects. When an agent runs `git commit -m "..."` it knows exactly what happened. When it runs a Python script that does the same thing via subprocess, there's now an abstraction layer to reason about.
The performance concern is real for I/O-heavy tasks. But for orchestration -- "list files, check git status, curl an API, write a line to a log" -- bash overhead is negligible and the interoperability wins dominate.
The place where this breaks down is anything requiring complex data transformation or error handling with multiple failure modes. That's where we drop into Python. The architecture that works for us: bash for the orchestration layer (run this, check that, pipe here), Python for anything with real logic.
IceWreck 5 hours ago [-]
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.
kkukshtel 4 hours ago [-]
This is a really interesting idea. I wonder if something like Luau would be a good solution here - it's a typed version of Lua meant for sandboxing (built for Roblox scripting) that has a lot of guardrails on it.
They use bash in ways a human never would, and it seems very intuitive for them.
Spivak 50 minutes ago [-]
If you present most LLM's with a run_python tool it won't realize that it can access a standard Linux userspace with it even if it's explicitly detailed. But spiritually the same tool called run_shell it will use correctly.
Gotta work with what's in the training data I suppose.
0x457 10 minutes ago [-]
There are a lot of shellscripts holding this world together out there.
simonw 4 hours ago [-]
Being unchanged for decades means that the training data should provide great results even for the smaller models.
wild_egg 4 hours ago [-]
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
Bolwin 3 hours ago [-]
I've had LLMs write some pretty complex powershell on the fly. Still a shell language but a lot nicer.
Ideally something like nushell but they don't know that well
andrewingram 3 hours ago [-]
just-bash comes with Python installed, so in a way that's what this has done. I've used this for some prototypes with AI tools (via bash-tool), can't really productionise it in our current setup, but it worked very well and was undeniably pretty cool.
inetknght 4 hours ago [-]
Bash is ubiquitous and is not going away any time soon. Nothing is stopping you from doing the same thing with your favorite language.
sheept 4 hours ago [-]
I feel like Deno would be perfect for this because it already has a permissions model enforced by the runtime
tosh 3 hours ago [-]
At least for me codex seems to write way more python than bash for general purpose stuff
snowhale 2 minutes ago [-]
[dead]
huntaub 5 hours ago [-]
We just released a driver that allows users of just-bash to attach a full Archil file system, synced to S3. This would let you run just-bash in an enrivonment where you don't have a full VM and get high-performance access to data that's in your S3 bucket already to do like greps or edits.
The unix commandline tools being the most efficient way to use an LLM has been a surprise.
I wonder the reason.
Maybe 'do one thing well'? The piping? The fact that the tools have been around so long so there are so many examples in the training data? Simplicity? All of it?
The success of this project depends on the answer.
Even so, I suspect that something like this will be a far too leaky abstraction.
But Vercel must try because they see the writing on the wall.
No one needs expensive cloud platforms anymore.
CuriouslyC 2 hours ago [-]
Trying to secure the sandbox the harness is running in seems like the hard way to do things. It's not a bad idea, but I think it'd be easier to focus on isolating the sandbox and securing resources the harness sandbox accesses, since true security requires that anyhow.
Just curious: why wouldn't you attack this with a jail?
wild_egg 4 hours ago [-]
Jails are alien magic and typescript is safe and familiar
otterley 4 hours ago [-]
What, exactly, is "safe" about TypeScript other than type safety?
TypeScript is just a language anyway. It's the runtime that needs to be contained. In that sense it's no different from any other interpreter or runtime, whether it be Go, Python, Java, or any shell.
In my view this really is best managed by the OS kernel, as the ultimate responsibility for process isolation belongs to it. Relying on userspace solutions to enforce restrictions only gets you so far.
wild_egg 3 hours ago [-]
Ah I forgot to add an /s
I agree on all counts and that this project is silly on the face of it.
My comment was more that there is a massive cohort of devs who have never done sysadmin and know nothing of prior art in the space. Typescript "feels" safe and familiar and the right way to accomplish their goals, regardless of if it actually is.
jeffchuber 4 hours ago [-]
last weekend I vibe-coded a project called `openfs` that plugs into just-bash
What problem were you trying to solve ? ( not that you need to solve one. I’m just curious )
andrewingram 3 hours ago [-]
I did a slightly less ambitious prototype a few weeks ago where I created added lazy loading of GCS files into the just-bash file-systems, as well as lots of other on-demand files. Was a lot of fun.
jeffchuber 2 hours ago [-]
yeah (optional) caching is interesting to think about - incl write_through and write_back
_pdp_ 4 hours ago [-]
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.
RobertLong 5 hours ago [-]
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.
cramforce 58 minutes ago [-]
In practice it is actually extremely fast because there is no process fork. You're talking nanoseconds for common commands
[Disclaimer: I made the thing]
simonw 4 hours ago [-]
Performance of the tools doesn't really matter when you have a full LLM inference loop in between each tool call.
tcdent 4 hours ago [-]
I still find it revolting they're writing this stuff in typescript.
Lerc 5 hours ago [-]
I have been playing around with something like this.
I'm not going for compatibility, but something that is a bit hackable. Deliberately not having /lib /share and /etc to avoid confusion that it might be posix
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.
cramforce 52 minutes ago [-]
I would not over-read into that doc. In practice, the only missing stuff are extreme edge cases of the type that is actually not consistent between other implementations of bash.
In practice it works great. I haven't seen a failed command in a while
[Disclaimer: I made the thing]
simonw 4 hours ago [-]
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.
gaigalas 3 hours ago [-]
I don't think the current incompatibilities can be worked around.
Also, huge waste of tokens. And the waste is not even worth it, the sandbox seems insufficient.
Again, good luck to the developers. I just don't think it's ready.
esafak 5 hours ago [-]
No, they use it because there's a lot of training material.
Why do you think there is a lot of training data? Could it be because it's stable and virtually unchanged for decades? Hmmm.
esafak 5 hours ago [-]
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.
gaigalas 5 hours ago [-]
This project runs on all shells, totally portable:
It's a great litmus test, that many have passed. Let me know when just-bash is able to run it.
esafak 4 hours ago [-]
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?
gaigalas 4 hours ago [-]
I've been working with the shell long enough that I know just by looking at it.
Anyway, it was rethorical. I was making a point about portability. Scripts we write today run even on ancient versions, and it has been an effort kept by lots of different interpreters (not only bash).
I'm trying to give sane advice here. Re-implementing bash is a herculean task, and some "small incompatibilities" sometimes reveal themselves as deep architectural dead-ends.
esafak 3 hours ago [-]
The project does not list portability as a concern. It's for agent use; they are not trying to re-use existing bash code.
gaigalas 2 hours ago [-]
Before, you said:
> they use it because there's a lot of training material.
Now, you say:
> they are not trying to re-use existing bash code.
Can't you see how this is a contradiction?
---
I'm sorry, I can't continue like this. I want to have meaningful conversations.
esafak 53 minutes ago [-]
Is English your second language? "They" refers to very different things here.
gaigalas 5 hours ago [-]
[flagged]
SignalStackDev 2 hours ago [-]
[dead]
raphaelmolly8 3 hours ago [-]
[dead]
sentra 4 hours ago [-]
[dead]
dostick 4 hours ago [-]
Why couldn’t they name it `agent-bash` then? What’s with all the “just-this”, “super-that” naming?
Like developer lost the last remaining brain cells developing it, and when it’s came to name it, used the first meaningless word that came up.
After all you’re limiting discovery with name like that.
4 hours ago [-]
Rendered at 20:04:11 GMT+0000 (Coordinated Universal Time) with Vercel.
When we run autonomous agents across different environments (Vercel functions, local dev, CI containers, remote VMs), Python availability is a negotiation. Bash is given. The agent doesn't need to worry about whether venv is activated, which Python version is installed, or whether a package needs to be pip-installed first.
There's also a subtler benefit: bash commands have predictable, well-documented side effects. When an agent runs `git commit -m "..."` it knows exactly what happened. When it runs a Python script that does the same thing via subprocess, there's now an abstraction layer to reason about.
The performance concern is real for I/O-heavy tasks. But for orchestration -- "list files, check git status, curl an API, write a line to a log" -- bash overhead is negligible and the interoperability wins dominate.
The place where this breaks down is anything requiring complex data transformation or error handling with multiple failure modes. That's where we drop into Python. The architecture that works for us: bash for the orchestration layer (run this, check that, pipe here), Python for anything with real logic.
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.
https://luau.org/
Gotta work with what's in the training data I suppose.
Ideally something like nushell but they don't know that well
Check it out here: https://www.npmjs.com/package/@archildata/just-bash
I wonder the reason.
Maybe 'do one thing well'? The piping? The fact that the tools have been around so long so there are so many examples in the training data? Simplicity? All of it?
The success of this project depends on the answer.
Even so, I suspect that something like this will be a far too leaky abstraction.
But Vercel must try because they see the writing on the wall.
No one needs expensive cloud platforms anymore.
TypeScript is just a language anyway. It's the runtime that needs to be contained. In that sense it's no different from any other interpreter or runtime, whether it be Go, Python, Java, or any shell.
In my view this really is best managed by the OS kernel, as the ultimate responsibility for process isolation belongs to it. Relying on userspace solutions to enforce restrictions only gets you so far.
I agree on all counts and that this project is silly on the face of it.
My comment was more that there is a massive cohort of devs who have never done sysadmin and know nothing of prior art in the space. Typescript "feels" safe and familiar and the right way to accomplish their goals, regardless of if it actually is.
https://github.com/jeffchuber/just-bash-openfs
it puts a bash interface in front of s3, filesystem (real and in-memory), postgres, and chroma.
still very much alpha - but curious what people think about it.
see an example app here: https://github.com/jeffchuber/openfs-incident-app
[Disclaimer: I made the thing]
I'm not going for compatibility, but something that is a bit hackable. Deliberately not having /lib /share and /etc to avoid confusion that it might be posix
On neocoties for proof of static hosting
https://lerc.neocities.org
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.
In practice it works great. I haven't seen a failed command in a while
[Disclaimer: I made the thing]
Also, huge waste of tokens. And the waste is not even worth it, the sandbox seems insufficient.
Again, good luck to the developers. I just don't think it's ready.
pro-tip: vercel's https://agent-browser.dev/ is a great CLI for agent-based browser automation.
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.
Anyway, it was rethorical. I was making a point about portability. Scripts we write today run even on ancient versions, and it has been an effort kept by lots of different interpreters (not only bash).
I'm trying to give sane advice here. Re-implementing bash is a herculean task, and some "small incompatibilities" sometimes reveal themselves as deep architectural dead-ends.
> they use it because there's a lot of training material.
Now, you say:
> they are not trying to re-use existing bash code.
Can't you see how this is a contradiction?
---
I'm sorry, I can't continue like this. I want to have meaningful conversations.