AI memory architectures: a Claude conversation

Captured from a working session with Claude Opus, 2026-03-12. Cleaned, structured, and saved as a permanent URL so the next AI session can pick up where we left off.

The question

What architecture should a personal memory layer use? Three patterns are in production today:

  1. Vector recall — every message goes through an embedding model, gets stored, retrieved by cosine similarity on demand. ChatGPT memory beta works this way.
  2. Episodic snapshots — full conversation transcripts are stored verbatim, indexed by date and topic. Claude Projects does this.
  3. Hub-shaped memory — the user authors structured notes; the AI reads them as URL-addressable resources.

What Claude argued

Vector recall trades precision for breadth. Episodic snapshots trade verbosity for fidelity. Hub-shaped memory trades automation for author-control.

The third pattern wins for one reason: the human stays the author. Vector + episodic both let memory drift — once stored, the user can't easily edit or curate without leaving the AI's UI. Hub-shaped puts the artifact in a place the user already lives (a document) and the AI reads from there.

Takeaway for mdfy

This is the existing direction. Worth checking against the spec page — /spec already documents the URL contract. No code change needed; this conversation just validates the choice.

Related concepts

  • Vector recall, episodic snapshot, hub-shaped memory
  • Forgetting as a feature
  • URL-addressable knowledge