Viewing profile — gusye

I’ve seen teams struggle on both sides of this. The vendor route feels great at the beginning with clean UX and fewer moving parts, until costs creep up or you suddenly need an eng…

Hey HN, I'm Gus. I built Memobase, an open-source memory backend that works like ChatGPT Memory. I know everyone is quite tired of the term "Memory System" recently. I was among th…

I did something similar to this: https://github.com/memodb-io/drive-flow . It supports tasks, dynamic routes and parallel execution in pure Python build-ins(zero deps). But just a …

Cool project, looks neat! I'm curious how the adaptive memory decay is implemented and how is it different from mem0?

Hey folks, I know there might have been similar threads on HN before, but I'm still super curious about this topic. I'm looking to build a SaaS service that I think could be really…

I noticed the new feature of llama-index: the event-driven workflow[1], which allows for building agents based on LLMs. I think the concept of an event-driven workflow is cool, but…

Yeah, that's something I definitely love to add in next few days. I plan to use one of the Test Dataset from GraphRAG paper.

I made a simple GraphRAG call nano-graphrag. The reason is I try to hack the official implementation released by Microsoft but that version is very hard to read/hack. This algorith…

Thank you for your reply! Indeed, creating an extension for Alfred or Raycast would be better. However, personally, I feel that it may not be fast enough since it would require som…

I really enjoy using some launch tools, like Spotlight, Alfred, and so on. I love the feeling of being able to switch applications without having to leave the keyboard. Recently, I…