Thanks for the write-up! Comprehension debt definitely feels like one of the biggest issues when I'm leaning heavily on coding agents.

It might fall into the too-heavy prior art category you mention at the end, but I quite like Superpowers (https://claude.com/plugins/superpowers and wrote a short review of why I like it: https://emschwartz.me/a-rave-review-of-superpowers-for-claud...).

Yeah I agree with the implementation plan not being that useful for me to read. I often just tell it to go after reading the design doc.

Seems kind of crazy, but I like it

This is great. It would be nice to be able to add a custom dictionary for words that are often misunderstood.

Pick an embedding model that supports binary quantization and then use a SIMD-optimized Hamming Distance function. I'm doing this for Scour and doing about 1.6 billion comparisons per second.

https://scour.ing

https://emschwartz.me/binary-vector-embeddings-are-so-cool/

Seems neat. Could you plug it in to DataFusion to use their SQL layer?

Yes! This is a great idea. Thanks for mentioning it! GlueSQL could be another cool target too (https://github.com/gluesql/gluesql). I think there's a fun exploration in taking a storage engine and seeing if it's compatible with different SQL layers — GlueSQL as a simpler starting point, DataFusion as the more complete option (https://github.com/apache/datafusion). Plugging into a real SQL engine seems like a great strategy for uncovering bugs, fixing correctness issues, and discovering what use cases the storage layer actually needs to support. It's also interesting how certain SQL engines and storage engines tend to align well with each other — the right pairing can unlock a lot. Definitely a direction I want to explore.

This is exciting work. I especially appreciate that it was trained to support binary quantization (I wrote about how cool binary quantized vector embeddings are in https://emschwartz.me/binary-vector-embeddings-are-so-cool/)

This sounds interesting.

Reading your website and the investor deck, one of my main questions was "who is behind this (and is this just AI-generated)?" It would be useful to put more of a bio on there.

Not having macOS/Windows support is going to make it hard to develop with. Would it be possible to build some kind of shim on top of other libraries that mirrors the API, even if it doesn't match the performance?

Also, one of the advantages of using a popular HTTP server stack is getting lots of battle-tested middleware that other people have developed and tested. Is there any way to leverage any of that or do you need to build everything from scratch? Granted, that is certainly somewhat easier in the AI era, but still.

Hey! I'm Evgeniy, a solo tech founder based in Europe with ~20 years of experience in the industry. It all started as a simple idea: build a web server and infrastructure purpose-built for AI services and agents -something with lower latency that could handle thousands of concurrent connections. That's why I chose Linux as the main platform and io_uring as the foundation (I'd worked with it before and knew how fast it could be). From what I could see, existing infrastructure just wasn't ready for AI workloads.So I built a completely new web server from scratch, designed as a foundation for AI agents. Under the hood: Linux + io_uring, Rust, and kTLS. The result is faster than nginx (one of the best out there) with lower latency (1.3-1.8x). About the website: I'll be honest some of the content was AI-generated, and some was AI-polished. Marketing isn't exactly my strong suit (solo tech founder, remember?). As for Windows/macOS support - it's important, but not the priority right now. The current focus is on polishing the web server, finishing server-sent events (almost there).

I believe so. When you call `raw_sql`, the API doesn't provide a way for you to specify which parts of the query are parameters, so it just passes that exact string in to exec.

You should try Scour (https://scour.ing)!

You specify your interests as free form text, it ranks articles by how closely they match, and you can consume your Scour feed as an RSS feed to read it in NNW.

Disclaimer: I’m the developer

HSTS issue, can't access.