Google PM open-sources Always On Memory Agent, ditching vector databases
venturebeat.comI just built something similar, specific to Claude Code. It runs as a transparent HTTP proxy that reads & rewrites the entire messages array that CC sends to its API. Same “dreaming” consolidation approach (using Haiku and another instance of CC itself, so it uses your subscription). Check it out!
Been saying this for a while. Vector similarity is the wrong primitive for agent memory. It finds things that sound related, not things that are actually relevant given current context and what the agent already knows.
The "ditching vector databases" framing is a bit dramatic since you still need embeddings somewhere, but the point stands that a raw vector store with no resolution layer is basically a pile of notes your agent can't reason about. You need conflict detection, certainty weighting, temporal scoping. Otherwise you're just building a fancier version of the same problem
I wonder if this is Google's answer to Beads?
Google's own ADK framework already has memory. Whatever VB is posting is far less interesting. But they need to sell that attention too I guess
Your vector database should be in memory