alt Hacker NewsIf you like this list of "why?", you might also like this: https://usehax.dev/ (I am the author). Most of the list applies, similar minimalist Unix tool approach, with some differences. Hax is written in C, the dynamically linked binary is even smaller (0.6 MB), MIT-licensed. No wasm though.
Important difference - fx is currently Vercel AI Gateway only - while hax does support multiple providers already (OpenAI API, ChatGPT/Codex subscription, Anthropic API, OpenRouter, OpenCode Zen/Go), and integrates well out of the box with local llama-server.
Replies
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.
Recently featured on HN: https://news.ycombinator.com/item?id=49273175
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"
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.
It looks really nice. Do you have any plan to support Claude subscriptions (pro/max)?
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.