It’s funny what “tiny” means for different people depending on their background. I expected it to be under an MB as well and was surprised by 6MB.

Basically, for me tiny means it fits on a floppy 1.44 HD.

Naturally meaningless when people carry around USB sticks that might even hold a 1 TB, but alas.

> Naturally meaningless when people carry around USB sticks

Do people do that? I think it was a decade ago, I thought people download from web nowadays.

Not everyone lives in areas where that is a convenient option.

Pretty much my baseline as well. Good example how experiences shape our thinking.

[cries in TRS-80 Model III]

Ok, lets make it 178 KB then. :)

For comparison, I publish a CLI tool written in Dart, can compile to native anything including Wasm , the Linux binary is around 5MB and it does quite a lot.

A typical Go binary would be 2-3 times larger. A typical Node project would easily pull more than 6 MiB of just code, not counting the runtime.

Recently featured on HN: https://news.ycombinator.com/item?id=49273175

this looks great! what are you using it for? i like the idea of being able to use one of these (sandboxed) within a larger program kind of like how I use LLM's to do small tasks within my apps now but with a few tools (web search). my current way of doing that is like building a mini-harness with a couple tools within the app, but something more drop-in would be better obviously.

I was going to ask if there's any plans to integrate something like the fx's ACP server[1] or pi's RPC mode [2].

I'm making something like Paseo and hax is very interesting as a Pi replacement.

[1] https://fx.sh/docs/using-fx/acp

[2] https://pi.dev/docs/latest/rpc

I really like the philosophy document! https://github.com/OleksandrChekhovskyi/hax/blob/master/docs...

I don’t know if I am ready to use a new tool written in C and using libcurl but I will give it a shot.

that's an amazing project! people always say why 6mb vs CC's 250mb even matter when you are calling out to LLMs hosted in the cloud. But... I regularly run hierarchies of agents with say 50-100 on a regular basis. So 650 vs 25050 ... is "can do" vs "cannot"

Is that real memory taken? If it's shared code from the same executable surely the multiples are not very relevant?

50-100? How do you do this and for what purpose?

For eg. on a large codebase I do hierarchical review where higher level agents focus on modules and leafs on files. Each reports upwards a summary of its findings incl children summaries.

It looks really nice. Do you have any plan to support Claude subscriptions (pro/max)?

Technically, this would be straightforward. The problem is that Anthropic seems to be really against using Claude subscriptions with anything other than Claude Code - you might even risk your account getting banned for doing so. You could search online for the "openclaw claude banned" for more details on that story.

Didn't Anthropic stop allowing it, can only use the subscriptions with first-party tools?

anthropic hate freedom. what makes you think they want you thinking?