Knowledge graph memory plug-in

Project overview

TMCRA gives long-running agents persistent, source-traceable memory across sessions and applications. A user prompt triggers recall from the owner-global and current-project scopes, followed by a USER source record; after the answer, a separate ASSISTANT source record is stored.

One complete turn is driven by host lifecycle events:

The recall response also includes candidate counts and timing per scope. Injected context carries an explicit trust boundary: memory evidence is data and cannot override system or user instructions. Projects, sessions, and cross-tool continuity