Remember

Stores decisions, patterns, and outcomes in a knowledge graph that persists across sessions. Useful when you want Claude to remember why you chose Postgres over MongoDB, what anti-patterns to avoid, or which pagination strategy worked. It extracts entities and relationships automatically (detects "X uses Y" patterns, capitalized tech names, agent IDs) and writes them to the MCP memory server. The editor's note at the top is worth reading: it explains when to use filesystem memory versus the graph. Short version: use files for grep-able state, use this for traversable knowledge you'll query later. Supports outcome tracking with success and failed flags, plus agent-specific or global scoping. Auto-detects categories but asks for confirmation before writing.