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

Zerostack – A Unix-inspired coding agent written in pure Rust

crates.io

Post reply on HN
Print view View original

201–210 of 334 posts

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#201

Post by GodelNumbering »

tornikeo wrote: post #181
rullopat wrote: post #173

I understand the need for memory footprint in some situations, but what's the point of seeking performance for a software that mostly calls LLMs and waits?

Simplest explanation I could come up with: Just for hype and fun. Rewriting things in rust is "cool". Bun did it, other projects did it. Therefore, writing a coding agent in one should be cool too. And apparently enough HN crowd agrees with it to take the #1 spot on the board.

For the most part, doing things right in the given language matters more than change of language. A lot of refactors in Rust (in the coding agent space) I see jump straight to Rust without considering what inefficiencies can be addressed before changing the language.

Having said that, I considered a Go/Rust rewrite of Dirac (https://github.com/dirac-run/dirac) for some modules to support cases when someone wants to run like 30 agents, but it quickly became obvious that, a) while the node event loop is a bottleneck, it is not the sole bottleneck and b) if you have a VSCode extension, you can't totally get rid of TypeScript, so it just becomes the case of bi-lingual project and the maintenance burden that comes with it

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#202

Post by brabel »

BillStrong wrote: post #61
frio wrote: post #30

Earlier quoted context omitted.

I've been trying to use `Deno` underneath `Rust` so that the tools can still be written in Typescript and thus self-mutated without the compilation step (but I can still try to do clever things with V8 Isolates or similar). It's been an ugly experiment so far; I'm vaguely thinking a simpler model would be to just define a binary "API" and run tools by exec-ing binaries.

Have you thought about Zig? If you limit it to CompTime, isn't that just a scripting language that happens to be compiled to binary?

That’s not how it works. Comptime Zig is Zig, not an embedded scripting language. You can’t run comptime code separately, it only runs as part of compiling a Zig program. Think of it like Rust macros.

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#204

Post by amelius »

mapcars wrote: post #185
rullopat wrote: post #173

I understand the need for memory footprint in some situations, but what's the point of seeking performance for a software that mostly calls LLMs and waits?

I see spreading Rust as an overall good thing, because it changes benchmark on how software should feel in terms of performance, stability, memory footprint. So even if it doesn't create tangible advantage in a particular use case - its still good for the whole industry.

No because it means people will use Rust for the wrong reasons.

Systems programming is only a tiny fraction of code out there.

Approaching every problem as a systems programming problem is a massive waste of resources and intellect.

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#205

Post by GodelNumbering »

mapcars wrote: post #185
rullopat wrote: post #173

I understand the need for memory footprint in some situations, but what's the point of seeking performance for a software that mostly calls LLMs and waits?

I see spreading Rust as an overall good thing, because it changes benchmark on how software should feel in terms of performance, stability, memory footprint. So even if it doesn't create tangible advantage in a particular use case - its still good for the whole industry.

I haven't used Rust extensively but my feeling is, if you change the design (which inevitably happens in many early stage projects), the refactoring takes more time due to borrow-checker semantics. Although I am far from a representative sample and could well have been using it wrong

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#206

Post by eldenring »

GodelNumbering wrote: post #205
mapcars wrote: post #185

Earlier quoted context omitted.

I see spreading Rust as an overall good thing, because it changes benchmark on how software should feel in terms of performance, stability, memory footprint. So even if it doesn't create tangible advantage in a particular use case - its still good for the whole industry.

I haven't used Rust extensively but my feeling is, if you change the design (which inevitably happens in many early stage projects), the refactoring takes more time due to borrow-checker semantics. Although I am far from a representative sample and could well have been using it wrong

Its just not a thing to consider and doesn't happen often.

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#207

Post by gf000 »

mapcars wrote: post #185
rullopat wrote: post #173

I understand the need for memory footprint in some situations, but what's the point of seeking performance for a software that mostly calls LLMs and waits?

I see spreading Rust as an overall good thing, because it changes benchmark on how software should feel in terms of performance, stability, memory footprint. So even if it doesn't create tangible advantage in a particular use case - its still good for the whole industry.

How is it any faster than something written in say, Java?

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#208

Post by usernametaken29 »

Mashimo wrote: post #144
usernametaken29 wrote: post #101

Earlier quoted context omitted.

Junie does not support BYOK inside the IDE

What does the k stand for? Key? You can add any open Ai api endpoint you want, no?

No, you have to buy their subscription within the IDE

Re: Zerostack – A Unix-inspired coding agent written in pure Rust

#210

Post by itsdavesanders »

wint3rmute wrote: post #184
rullopat wrote: post #173

I understand the need for memory footprint in some situations, but what's the point of seeking performance for a software that mostly calls LLMs and waits?

Even a simple coding agent TUI should work instantenously, which I sadly cannot say is true about typescript-based applications like Claude Code or Gemini. After switching away from GNOME Terminal + Zsh to Ghostty + Nushell, I started to appreciate how instant everything feels. Why not make everything just as fast?

I have to say this is one of my favorite things about local Qwen and Qwen code, it seems a heck of a lot faster that Claude and feels better to work with.

Problem is it is nowhere near as smart, so what speed I get in conversation gets killed by iteration.

Post reply on HN