Skip to main content

Architecture

UnifiedMemory is an agent-native memory fabric, not a raw vector database. The hot path runs at the edge; heavier cognition and Courtroom work stay in the origin backend.

Runtime responsibilities

LayerResponsibility
Cloudflare WorkerFast auth, scoped hot reads, MCP/edge API routing, D1/Vectorize access, lightweight runtime status.
D1Canonical production metadata: keys, sessions, memory catalog, review/quarantine state, trust and lifecycle fields.
VectorizeSemantic candidate retrieval using coarse metadata filters. D1 hydration remains the final authority.
R2 and QueuesEvidence snapshots, proof artifacts, async fanout, delayed lifecycle work, and retry/dead-letter surfaces.
FastAPI originHeavy cognition, compatibility APIs, Courtroom reports, Google Memory Bank bridge, migrations, proof tools.
MiniMaxDefault UnifiedMemory-owned cognition and AI judge lane. It can recommend, downgrade, and explain, but not bypass guardrails.
Google Memory BankManaged memory co-processor for session ingestion, generated memories, profiles, and revisions. It is evidence, not automatic truth.

Safety boundaries

  • Effective identity comes from authenticated key/session metadata.
  • Agent-private working memory is not shared by default.
  • Test, smoke, benchmark, diag, eval, forensic, and system-generated rows are excluded from assistant-facing recall.
  • Courtroom deterministic guardrails run before AI judgment.
  • Google and MiniMax disagreement creates review/conflict evidence rather than automatic promotion.

Next steps