jack1689

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 :)

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

I have been hearing a lot about "AI will help us create greener energy" with the promise to sort of close the loop (linking here one from MIT I came across a while ago: https://news.mit.edu/2025/how-ai-can-help-achieve-clean-ener...)

Wondering: 1) How? 2) Is the balance gonna be actually positive or will manufacturers and customers pay the bill for it as you say?

Yeah totally feel you on this one! To avoid it or at least limit that I usually ask it to create external memories, clearing the context window and leaving just a trace to recall the memory created for that run. I hope it might help!

I was reading a bit about their story, it feels like they managed to succeed by turning overly funded (and by then devalued) software products and restructuring them for long term profitability as they are not bounded to the classic 10 year time horizon of private funds. Wondering if we will see more plays like this as alternatives to traditional private equity and as fallback option for VC backed companies that bursted.

How can you effectively defend tho in todays AI era?

100% would echo that - but I'd say it's a wide problem across job markets not just for junior programmers

I feel it has rather created an opportunity for a junior programmer to deliver 5x faster than before and it has lowered the barriers to be a decent junior developer. Perhaps in today's job market for junior devs what changed are the metrics against which they are judged for. It's not just knowing theory of coding, it's about speed at which you ship and most importantly quality. Ultimately, how good is such a developer to push code with agents. What do you think?

Genuinely experiencing it daily and tackling it by having a few audit agents running in parallel to keep the big picture and feed context as needed. However, this is terribly expensive.

My question tho is, how confident are we about an agentic future? I mean coding was the one thing agents "are best at". How would you run a complex system/organization on an agent where they will need to face with a massive (and growing) context through a limited context window?

How is this sustainable in the long run tho? Major enterprises are already making the headlines as they cut licenses and reduce token consumptions. The conversation is moving a lot toward return on token... is automating this activity with an agent giving me a higher return rather than having a human run it? Plus the advent of local AI and open source models are creating new opportunities to reduce token costs

Wondering if it's just the iphone and the fact that we have it always in our pockets or the amount of "radiations" we are exposed it constantly at home at the office tbh