thank you for your feedback! I see your point, and we keep asking this thing ourselves.

If this was just some sort of static retrieval, I'd agree with you. But the truth is that we're tackling something more fundamental: improving and evolving it over time, through adaptive scoring and self-improvement.

Also being able of vibe coding it doesn't mean you should: delegating this to a library means delegating the maintenance of this piece of code (which is not trivial, in our opinion).

Anyway, we'll talk about how we tackle self learning loops with it, so stay tuned! :)

What kind of agent are you building btw?

Hey, yes it's on the same family for sure! The difference is that it works with anything, not just MCPs, and it runs in-process without any additional infra (which usually isn't the case for other RAG solutions). Happy to hear your feedback if you try it out :)

Hey guys, fair callout, but no AI involved, promise! You're right that some comments look off and someone's farming karma for sure. We see genuine traffic to the repo anyway, so people is checking it out!

Critical feedback is what we're here for, so fire away if you have anything :)

This comment was detected by our software as AI generated. It could always be a false positive, but if you're using AI at all to write your comments, please stop. It's against the guidelines and only harms your reputation in the eyes of the community.

Thank you! Right now we're adding some frameworks adapters to lower the adoption friction, and pushing deeper on new algorithms on the retrieval side. More languages support is not on the radar yet, but we accept contributions! :)

Thank you! Let us know how it works if you try it out :) of course real world is another story, but we agree benchmarks are amazing indeed!

Yes! I should have mentioned in the original post. It was actually built in Typescript at first, but then the performance were not good enough for production use cases. With Rust the footprint was way lower, and we managed tear the latency down from 200ms to 20ms for a single search

Would love to hear your feedback if you can try it. We initially rolled out BM25 for tool search as it worked best for us internally. Recently rolled out also embeddings and an hybrid option that is being tested in production as we speak

The common fear is that the giant AI labs that sell proprietary models are somehow acting like Trojan horses. I feel the real question is how can we effectively prevent that, yet having best in class inference? Are open source models the endgame then?

Wondering whether they are more worried about security concerns given the latest model releases (see European Central Bank about Mythos) or a potential bubble and how/if they can do something about it

I feel like 12 months ago it was just about "we just need the next great model" and now we are seeing how there is a lot of infra to be built around these models to avoid ROI negative tokenmaxing outcomes