JunNanLYS/dsh-layered-memory

★ 9 · Memory & Knowledge

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

View on GitHubBrowse similar plugins

About this plugin

Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.

How to install

See the GitHub repository for installation instructions — this plugin does not publish a standard install command.

中文说明:Layered memory pipeline for DSH: auto-distills conversations into atomic facts, scene summaries and a persona profile (L0–L3), with hybrid BM25 + vector retrieval, chat/work family separation, and context injection before each model step.(安装方式请参考 GitHub 仓库说明。)

More plugins like this