Organize memory

Benchmark first

Corpora: LongMemEval · QASPER · LongBench

Protocol: Replay sessions in timestamp order without gold-answer fields. Report information extraction, multi-session reasoning, temporal reasoning, knowledge updates, and abstention separately; add evidence Recall@k, write amplification, stored bytes, reader tokens, and latency. Compare raw-history, retrieval-only, extracted-memory, and consolidated-memory baselines under identical context budgets.

• Memory segmentation and mutation plans
• Memory organization and evidence notes
• Knowledge admission and mutation planning
• Tiered memory consolidation