saxenauts

I am building a graph memory too, and I agree with you. It is almost useless to generate triplets, and instead generate nodes that are usually statement strings. And can extend up to a short paragraph too.

I have strong opinions that memory should be a graph + vector hybrid. The vector store can store and index information as a cognitive fragment( ex. all things related to my house), and can keep editing it as a set of statements, while that node can be associated with other nodes (ex. my renovation plans, budgeting, etc.), because those are separate fragments. I am also using LLM to consolidate and find new patterns across the connected memories

> But one problem I see with these memory systems is that they can reduce interest on a topic once we put it in the KB.

Can you elaborate please?

I find the associative nature of our memory can only be represented as a graph, but we definitely need a vector store.

I like to pose this as an identity question rather than memory as colloquially memory is only associated with fact extraction and retrieval, while identity extends that to traits, behavior, preferences, memory and narrative causal relations.

essentially a self organization of symbols and memories to produce a coherent singular entity.

I had written about it here.

https://saxenauts.io/blog/persona

working on a cross web, self organizing digital footprint that serves as a human memory and identity for LLMs

https://github.com/saxenauts/persona

90 percent of the AI companion use cases today can work well with just a vector DB to retrieve facts, and chunks of memory, but a connected digital footprint would need a graph+vector hybrid.

memory in the coming future will not just be about fact retrieval but need backlinks of memetics, new streams of data, holistic analysis, infinite schema-less key value store, causal reasoning and other things that define "who and why" of a human and imitate neuroscience's understanding of how our identities work today. this then needs to be translated as language chunks to LLMs

benchmarking this against popular tools, on longmemeval. getting good results so far. i would love to learn from you guys, what's your take on identity and human representation for LLMs in the coming future

why is our perception and the way it works different from the universe?

with enough agency, and ignoring everything else in the world you realize that your perception is all there is, that you can ever be sure of.

There is no universe, there is no quantum physics. Those are just models, your perception models them.

This is beautiful, I can create my own idea pipelines. Apply some rules for system based thinking, and have it generate carefully generated ideas.

Why choose a graph data structure ? Is it better for memory than AI agents as opposed to vector embeddings of statements or having a NoSQL database? I am bullish on graph, but seems like noone else is, so want to understand your perspective on this