personal_memory_systemlisted

# Personal Memory System ## Purpose Give an AI assistant a long-term memory that stays organized, searchable, and current. The skill covers the full lifecycle: **scanning** (collecting from the user's surfaces), **retrieval** (searching before answering), **management** (routing each fact to its home), **indexing** (entity profiles: people, groups, topics, meetings, activities, interests, locations), **organization** (curated files plus an append-only temporal trace), **evolution** (scheduled collect/update/refine and evaluation), and **protection** (a data-protection layer — egress gates, send shims, briefing policy — validated by the muse-leakage-guard add-on). ## Workflow ### 1. Set up 1. Run `bin/init-memory` — creates the directory skeleton and starter files under the memory root (`$PERSONAL_MEMORY_ROOT`, default `~`). Never overwrites existing files. Every tool honors the root, including `bin/memory-log-append` (daily logs land under `${PERSONAL_MEMORY_ROOT:-$HOME}/memory`; `MEMORY_LOG_ROOT` overrides). 2. Fill in the central profile and personalization notes from what you know about the user. Nothing goes into memory without the user's approval (see `references/privacy-and-validation.md`). 3. Schedule the refresh (see `references/cron-templates.md`): one daily collect/update/refine job, an optional lightweight watcher that surfaces urgent items between runs, and an optional nightly evaluation that audits the system's disciplines. ### 2. R