Governed agentic memory

OME
MemoryGuard

A policy gate between an AI agent and persistent memory. Every proposal is risk-scored, explainable, auditable, and tenant-scoped before it can shape a future action.

CockroachDB × AWSchecking runtime…checking auth…

Fail closedDenied content is fingerprinted, never persisted

Scoped retrievalTenant + namespace + status + expiry + clearance

Atomic evidenceMemory and audit event share one transaction

1. Propose a memory

Run the same API flow an agent would use.

Namespace

Sensitivity

Content Purpose

Source URI

Retrieval clearance

2. Decision

The API returns only policy metadata for a denied proposal.

Choose a scenario and run the policy gate.

01 · ProposePurpose and provenance

02 · EvaluateDeterministic policy

03 · PersistCockroachDB vector row

04 · AuditAtomic decision trail

3. Audit trail

Denied inputs appear only as reason codes and a SHA-256 fingerprint.

No events yet.