hello fellow yukoner, that is insane
HN user
monadoid
full-stack dev from northern Canada, passionate about building cool stuff quickly.
Cool idea! You should make it so that I can only play one audio message at once (currently if I click to start two, they both play simultaneously)
Not the creator, just wanted to put this out as a PSA: the rust docs MCP tool is actually great, thanks to docs.rs having rustdoc JSON output I believe. Since the source docs are fully structured JSON, my LLM can cache docs locally and then fly through them. I hope more MCP tools can become like this!
`Simple, Boring Tech Stack: shell scripts over k8s, keep code modular`. wut
Yeah fair enough, I guess the core of it might just be the similar names!
Despite everyone hating on the AI slop (I myself hate AI slop), I am excited about cap'n web and am jonesing to try it out in rust so I will take a look!
I'd love to see (might try to add on) an optional type layer: define contracts as json schema or JTD or something? Does something like this already exist - maybe you could use protobufs ontop of this? Would be nice to make it so that you didn't need to share types between client / server out of band, something like an openapi spec allows all clients (not just those you are in control of) to have types!
This is someone's rust port of the new "cap'n web" protocol Kenton just released, which he's calling a spiritual sibling to cap'n proto (which he also built). This might be AI slop but this info is all in the OP, come on man!
Yeah my thoughts went to DAOs! I'm so excited for a future where we can use DAOs to harness the power of the people :)
I think HN is getting old - nobody has mentioned second screen viewing! imo, youtube videos are getting longer because everyone is just turning stuff on in the background while they're on their phones.
Love you supabase
This is well written, thanks!
Agreed I love this pattern! I'm a big fan of using nuqs for this in nextjs, but really stoked to try out rust / loco / htmx for my next project.
Yeah I hope they open up support to all MCP tools - this is lame as-is.
Why would I use this vs @openai/openai-agents-python (or openai-agents-ts) - the new realtime agents SDKs?
There are so many AI frameworks out there that live & die so quickly that I am generally hard pressed to use any of these unless there is some killer feature I absolutely need.
that's definitely a big question but I don't think it's the big question. this is 100% progress and it's standalone cool
Yes I agree strongly, if I could just make a small percentage for my mildly interesting LLM wrapper it would be perfect! @anthropic please implement this
hey thank you for posting this. I'm sorry to hear about your condition but happy LSD was able to help a bit.
One unsolicited idea from a stranger: consider trying it again! I was in a similar situation for a long time (found it helpful but no strong desire to try it again), but multiple trips over time ended up being very helpful - for me at least.
Cool! I'm curious if any rust wizards would have recommendations for best practice in rust, and if they would differ to design 2 or design 3 from this article?
Loco is awesome! Hoping that the openAPI generation comes soon - then I can generate zod schemas from the openAPI doc! It would be really cool to use something like hygen/plop or maybe tera (idk) to automatically generate svelte or react CRUD pages, similar to what loco is already doing for htmx.