4nm1tsu

I noticed the self-hosted deployment currently targets Cloud Run. Any plans to support plain Docker or Kubernetes as well?

I'd probably want to run this on my existing k8s cluster rather than spin up a separate GCP project for it.

Have you thought about adding an observability layer on top of the shared memory?

If multiple agents are reading and writing to the same memory, I'd love to be able to see which agent created a memory, which agents later retrieved it, and how it propagated across sessions. A timeline or knowledge graph of that could be really useful, especially for tracking down stale or conflicting memories.