For AI systems that need to remember and reuse knowledge over time, maintaining a canonical registry with persistent aliases and source tracking prevents fragmented relationship histories and lets evidence accumulate reliably.
FIRME is a memory system for financial AI that tracks investor knowledge across time and sources by maintaining a canonical registry of relationships. It reconciles different ways of describing the same observation (e.g., "Apple stock" vs "AAPL") and links investor discussions to cash-flow data, while preserving where each piece of information came from and when.