Structured daily and weekly learning memory with dual graph snapshots.
memory/daily_memory/YYYY.M.D/YYYY_M_D.md - Human-readable daily summary for one day.memory/daily_memory/YYYY.M.D/YYYY_M_D.json - Structured daily payload for code and downstream features.memory/weekly_memory/YYYY_M_D_to_YYYY_M_D/YYYY_M_D_to_YYYY_M_D.md - Weekly study plan generated from the last 7 daily summaries.memory/graphs/knowledge_graph.json - Knowledge-point graph.memory/graphs/error_graph.json - Error-pattern graph.memory/MEMORY.md - Auto-generated compatibility snapshot loaded into prompt context.memory/HISTORY.md - Append-only audit log of consolidation events.Prefer these sources in order:
.json when you need structured fields such as date, high_risk_knowledge_points, high_frequency_error_types, learning_status_summary, and tomorrow_study_suggestions..md when you need a human-facing summary..md when you need the next-week learning plan.HISTORY.md only when you need an audit trail of what was archived.Knowledge graph:
time_points, risk, mastery, importance, last_seen, and display_size.Error graph:
error_count, severity, repeated, last_seen, and display_size.MEMORY.md unless you are intentionally adjusting the compatibility snapshot.Archived conversations are automatically summarized into daily memory, graph snapshots, and weekly plans when enough recent data exists. You usually do not need to manage this manually.