How does cognee handle temporal evolution of memory (e.g. when facts change over time)? Curious what’s still an open problem here because AFAIK this is really hard to solve.
Is cognee meant to power agent memory that builds up evolving contextual data about individual users and agents acting on their behalf? Say you track evolving user preferences in some domain space e.g. travel. If so, how do you handle user-specific memory separation—especially in multi-user or multi-agent setups?
We have temporal resolution mechanisms we are building, and framework is generalizable enough to build any custom logic. We have a few ideas and some things will be posted there soon.
Hey, this looks super interesting - nice work!
Couple questions:
How does cognee handle temporal evolution of memory (e.g. when facts change over time)? Curious what’s still an open problem here because AFAIK this is really hard to solve.
Is cognee meant to power agent memory that builds up evolving contextual data about individual users and agents acting on their behalf? Say you track evolving user preferences in some domain space e.g. travel. If so, how do you handle user-specific memory separation—especially in multi-user or multi-agent setups?
Hi, founder of cognee here
We have temporal resolution mechanisms we are building, and framework is generalizable enough to build any custom logic. We have a few ideas and some things will be posted there soon.
cognee has notion of nodesets which work similar to tags: https://docs.cognee.ai/core-concepts/node-sets
And also we have graphs per user now available. So, user permisions + graph filtering