This is much needed! Compared to Codex CLI, Claude Code is insanely slow. $ time claude --version 2.1.143 (Claude Code) ________________________________________________________ Executed in 4.39 secs fish external usr time 29.68 millis 0.26 millis 29.41 millis sys time 71.30 millis 1.30 millis 70.00 millis 5 seconds to show me the version number! I'm guessing Claude Code also needs a rewrite in Rust. But from what I s…
What version of time is giving you that kind of output?
Zerostack – A Unix-inspired coding agent written in pure Rust
191–200 of 334 posts
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#192I 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?
- prolonged life of hardware
- less electricity
- less expensive hardware
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#193New to this. but whats the benefit over models like Claude code ?
Make harness independent of model, so when pricing or quality changes you can switch. Avoid lock in to stack from one provider (things like a harness that only works with models from one provider and so on). Use local models (a couple of them do work a bit now, if you have 20Gb video RAM), which saves money and is more private, and works offline. Can improve the harness, fix bugs in it, make it compatible with differ…
You can use Claude Code with almost any model.
>Use local models (a couple of them do work a bit now, if you have 20Gb video RAM), which saves money and is more private, and works offline.
You can do that with Claude Code.
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#194IMO, the problem with Claude Code, OpenCode, Pi is the harness quality and convincing the agents to do the exact things you need, to define workflows and make the agents stick to it. I didn't experience performance issues. For example I have an agent in Claude Code that has strict rules to do something before implementing every phase in the plan. Sometimes it decides not to do it. "But, wait the feature is simple eno…
But that‘s not an issue with the coding agent. It’s the model that doesn’t follow the instructions. Given how an LLM works, you can never be sure it will always work. LLMs are not deterministic.
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#195I’m also playing around with Rust for building agents—my setup ends up looking a lot like ZeroStack’s approach. If anyone’s curious, my project is here: https://github.com/7df-lab/devo
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#196Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#197I 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?
- Reduce the footprint on the planet - prolonged life of hardware - less electricity - less expensive hardware
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#198I had Claude Code build me one of these as well, though I added Dirac's line hashing for edits etc. Also used Rust, and I had this idea that I should use plugins so it can self-edit by implementing in hooks but in the end, I just have it create exhaust information about improvements into a separate file and just update the source code and recompile. The source code is in a fixed place so it can just rewrite and build…
I am currently in deep refactor mode to introduce modular tooling to Dirac since the concept of 'fixed' set of tools is starting to feel antiquated, adding tools on demand would be super convenient and a likely replacement for MCP (I understand not all use-cases of it)
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#199I 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?
Re: Zerostack – A Unix-inspired coding agent written in pure Rust
#200I 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?
Before I tried coding agents my guess would have been: none. But seeing how slow claude code and copilot cli are and how much ram they use I'm flabbergasted. If you have long running sessions they can both take tens pf gigabytes of ram and feel quite sluggish.