Isn't a standalone Bun binary like 50MB because it has to bundle the runtime? How could this get smaller?

Hi, the creator of crust here, the binary size varies between platforms. With the hello world cli, the smallest, on darwin-arm64 it is 58.1M, the largest on windows-x64 is 109M. hope this helps!

good point.

we’re using “framework” intentionally because it goes beyond argument parsing. crust handles parsing, but also:

type inference across args + flags end to end compile-time validation (so mistakes fail before runtime) plugin system with lifecycle hooks (help, version, autocomplete, etc.) composable modules (prompts, styling, validation, build tooling) auto-generates agent skills and modules from the CLI definitions

so it sits a layer above a traditional arg parser like yargs or commander, closer to something like oclif, but much lighter and bun-native.

thanks for flagging! the post itself works, just the link at the bottom

will fix in the next hour!

thanks for the catch, what we meant is that we’re not committing to strict stability guarantees yet, so APIs may still change as we iterate toward 1.0.

I understand, but that's already implied by a 0.y.z version number.

I will say that this doesn't seem to be how semver is used in the wild, which I would argue is more important. I personally didn't know about this rule. Tons of Rust projects follow semver don't follow it either, and just stay on 0.x.y forever.

How is it used in the wild, in your experience? Have you observed projects following some alternate set of rules?

I thought projects that stay on 0.x.y forever mostly do it because it means they're allowed to break things. Also, since 0.x.y means "anything goes", projects can introduce their own conventions within that range without violating the spec.

I know that some package managers (including Cargo and npm) confusingly treat 0.1.0 → 0.1.1 like a "minor" update, despite the spec. Is this what you're referring to?

Yes, that was what I was referring to, although I thought the reason of staying at 0.y.z was more of a cultural one. v0, at least to me, implies that the API may change arbitrarily and quickly, but makes no assertions about the actual versioning scheme itself.

There's a website making fun of it: https://0ver.org/

one of the examples would be trynia.ai (search and index api for ai agents)

here is github: github.com/nozomio-labs/nia-cli

sick

rag is not a core! we use both semantic search but combining with fts, grep, direct read, etc.

Open source models with minimal safety fine tuning or Grok

Grok is arguably not uncensored, it’s re-aligned to a specific narrative lane.

“Uncensored” is simply a branding trick that a lot of seemingly intelligent people seem to fall for.

Wait, is abliteration actually just a branding trick? That doesn't sound correct.

My post was sociological - yours is technical.

Are you on purpose not having the same conversation or are you confused as to whether or not I think abliteration itself is marketing?

Saying grok is uncensored is like saying that deepseek is uncensored. If anything deepseek is probably less censored than grok. The doplin family has given me the best results, though mostly in niche cases.

Thanks for testing this. The Bannon email from June 30, 2019 is in there (HOUSE_OVERSIGHT_029622). Good stress test idea.

Couple things happening:

Semantic search limitation: Less-famous names don't have strong embeddings, so it defaults to general connections rather than specific mentions Keyword search gap: You're right — raw grep can catch exact names I'm missing

I saw a similar problem. Roger Schank had some conversations with Epstein and the emails can be seen in Epsteinvisualizer.com but your site claimed there was no emails or connection. To be fair to Roger, who was an AI legend of his time and someone I knew personally before his untimely death, he really was not a pedo, and most likely never got involved with the girls, I think him and Epstein just talked about AI and education mostly.