Cross-session memory recovery for AI agents — your agent never cold-starts again. Always-loaded identity & todos, hash-indexed conditional reads cut recovery to 1.3% of a full restore (98.7% fewer tokens). Pure local, zero deps. Use when: (1) A new chat asks "where did we leave off?" and you have no context (2) Context is filling up and you're about to hit the limit mid-task (3) User says "I already told you this" (4) You re-read the same identity/rules/todos files at every session start (5) Session start burns tens of thousands of tokens before real work begins (6) You need to hand a long task to a fresh session without losing progress