← Back to list

dsh-plugin-memory

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill.

带 LLM Wiki 结构与 SOUL 人格文件的长期 markdown 记忆库：会话启动注入 boot 块（默认提问后才注入、且只注入当前激活会话），含 remember/recall/consolidate/forget 工作流、内嵌 memory 技能、pack/unpack 迁移工具，以及空闲时以第一人称主动追忆（recall nudge）的拟人化能力。同时补上记忆库原先缺的“可观测 + 可维护”：按文件分配 boot 预算（索引路由表不再被截断）、自动戳记 last_access（salience 衰减真正生效）、只读记忆健康看板（体量/新鲜度/与 lint 同源的体检）、声明式索引编译器（页面声明 summary:，一条命令重写索引行），可拖动、可滚轮缩放的记忆图谱（页间链接 + 共享 tag）、结构化检索（tag/type/salience/hot/stale 过滤）、针对「尚无内容关系」页面的补链建议，以及以「最该做的 N 件事」收尾的 `checkup` 体检报告。同时把操作细节移到按需加载的技能，boot 注入体量减少约 23%。