MemorySync
Getting Started

Architecture at a Glance

MemorySync sits between your application and model as a scoped context service. Your server writes useful facts, retrieves relevant memory, and decides how to use the results.

The application flow

  1. 1Your server authenticates with an API key and identifies the project and end user.
  2. 2The server writes a durable fact or event through the memory API.
  3. 3Before a later model request, the server queries with the user’s current intent.
  4. 4MemorySync returns relevant records from the same request scope.
  5. 5Your application selects the useful results and adds them to the model prompt.

Responsibilities by system

SystemResponsibility
Your applicationAuthorization, stable external identifiers, write policy, prompt construction, and final user experience.
MemorySyncScoped memory operations, relevance-based retrieval, metadata filters, and lifecycle APIs.
Your model providerGenerate or classify using the context your application sends.
Source systemsRemain authoritative for documents, permissions, and transactional records.

Scope every request

  • X-API-Key authenticates the server-side caller.
  • X-Project-ID identifies the application or workload.
  • X-End-User-ID identifies the person represented by a service request.
  • Use stable opaque identifiers; do not place email addresses or secrets in scope headers.

What crosses the boundary

Send the minimum context needed for the memory use case. A memory can include text, a source label, and application metadata. Query responses return candidate records for your application to inspect and use.

Go deeper

Was this page helpful?