We built a persistent agent memory layer on Elasticsearch with 0.89 recall

itissid

I have a request: can this text be even more AI generated?

stingraycharles

This is such a basic thing nowadays, and ElasticSearch is massive overkill for it. Something like SQLite or LanceDB or basically any vector database is much more appropriate. This seems to be coming from the “we must make ElasticSearch AI-compatible” department more than anything.

reactordev

I built one into my agent using sqlite…

voidUpdate

For someone who isn't super familiar, what is "R@10", and is 0.89 good? It's impossible to google for

0xbadcafebee

Summary of the article ( https://pastebin.com/aawJfrF6 ) since the original one is like reading an academic paper filtered through an LLM that hates human readers. It seems like a cool approach. Don't know if it's novel but it's much smarter than "shove markdown files into directories".

tuo-lei

so the 11% miss rate - do users actually notice when the agent drops a memory? like if someone already said they tried X and the agent suggests it again.

koinedad

I think this is cool and helpful but my biggest complaint is the writing style and word choice just scream LLM

dominotw

is there any proof that all these shenanigans impove agent performance

BiraIgnacio

TIL - Hybrid recall + reranker: Two searches merged, then re-scored for best matches - Supersession: Old facts get hidden, new ones take their place - Decay: Recent or often‑used memories get a score boost - DLS: Each user only sees their own documents

verdverm

I'm using Typesense to power my take on a md kb, highly recommend this option which positions itself against Elasticsearch and Algolia. Combines vector with bm25 and all the extras you get from a trad search tool like Algolia.

leoprctmp

try Manticore Search, it's much more lightweight