Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

cortexdb.ai

Post reply on HN
Print view View original

1–10 of 13 posts

Re: The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

#4

Post by shreymaheshwary »

This problem hits home for me. I’ve been trying to use various AI therapist apps issue is all of them forget about patterns we identified, Many of the personal details I shared about me and any big breakthroughs from earlier sessions and issue has always been AI summary just doesn’t work the nuance that matters get lost. Cortex storing all the raw data is the correct approach. My Threapy app providers bring this on Asap.

Re: The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

#5

Post by psyduck123 »

I work with small clinics in India — their entire patient "CRM" is WhatsApp scroll-back. Doctor replies "ok do MRI" with no context, patient's son follows up two days later from a different number asking about cost, receptionist forwards a screenshot of the fee chart from another group. That's what one patient thread looks like, and there are hundreds. Going to try piping a WhatsApp chat export from one of these clinics into CortexDB this weekend. The stuff I want to query is mundane — what was this patient's last X-ray finding, did we already discuss surgery with the family, how many ACL cases did we see this quarter. Stuff the receptionist currently answers from memory or by scrolling for 10 minutes. The event-sourced approach is what makes this interesting to me over something like Mem0. This data is messy enough that I don't trust any model to extract the right structure at write time. Store the mess, derive views later, re-derive when the model gets better — that feels right for this kind of input. Will report back.

Re: The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

#6

Post by prmalik »

sanchitsensei wrote: post #3

Feels like “memory as infrastructure” is the missing piece in a lot of AI apps right now. If this works as advertised, it could simplify a lot of messy stacks.

It does work , infact it does very well on a number benchmarks. Please let me know if i can help with any integrations.

Re: The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

#7

Post by prmalik »

shreymaheshwary wrote: post #4

This problem hits home for me. I’ve been trying to use various AI therapist apps issue is all of them forget about patterns we identified, Many of the personal details I shared about me and any big breakthroughs from earlier sessions and issue has always been AI summary just doesn’t work the nuance that matters get lost. Cortex storing all the raw data is the correct approach. My Threapy app providers bring this on A…

That is a great use case , and its very easy to integrate just 3 lines of code . Please let me know if you need any help help@cortexdb.ai

Re: The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

#8

Post by prmalik »

psyduck123 wrote: post #5

I work with small clinics in India — their entire patient "CRM" is WhatsApp scroll-back. Doctor replies "ok do MRI" with no context, patient's son follows up two days later from a different number asking about cost, receptionist forwards a screenshot of the fee chart from another group. That's what one patient thread looks like, and there are hundreds. Going to try piping a WhatsApp chat export from one of these clin…

Awesome , looking forward to how your integration goes.

Re: The Long-Term Memory Layer for AI Systems by the Creator of Apache Cassandra

#10

Post by prmalik »

alameenpd wrote: post #9

i wonder how this defers from retaindb.com . also humm the website could be very very improved and can help you cause it looks kind of vibe coded

i dont think we want to take any db written in a scripting language seriously.
Post reply on HN