DeepSeek Harness plugins — Page 795

本地 Markdown 记忆：通过 memory_md_* 工具把值得长期保留的内容写进 ~/.dsh/memory-md/，让助手跨会话记住你。

极简 Markdown 长期记忆 for DeepSeek Harness(dsh)：中文可搜、人类可直接编辑、不依赖 web。Minimal Markdown memory for dsh — CJK-friendly substring search, hand-editable file, no web surface required.

DSH 一体化记忆与上下文管控增强插件 — 四层记忆 + 上下文压缩 + 提示词编排

把「这个对话要不要进全局记忆」变成一个会话内的开关：输入框工具行里的记忆按钮 + 跨会话的全局记忆注入（非官方插件）

Persistent memory plugin for DeepSeek Harness: memory_* model tools, automatic memory:recall prompt injection, /memory/api JSON routes, and a 设置→记忆 (Settings → Memory) management panel.

Long-term memory for DeepSeek Harness: memory_save/recall/list tools plus a sidebar panel visualizing what the agent remembers about you

DSH 记忆/规则插件：每轮注入记忆与规则，提供 memory_* / rule_* 工具，标题栏图标浮层 + 设置页「记忆与规则」

Persistent memory for dsh in the style of Hermes Agent: a memory tool that keeps a user profile and the model's own notes, delivered to every chat as a logged context message — at the start, after a change and after compaction — and a session_search tool that reads earlier chats only after the user approves, with a Memory panel to see and edit what is kept.

记忆提炼：把长对话整理成你点头之后才写入的长期记忆条目。自动读会话事件流取料，剥掉注入提示词、运行时快照与推理正文；提炼出候选后必须逐条确认才落盘；写入走版本预检、整份备份、读回核验三道闸。侧边栏面板可查看、编辑、导入、删除记忆文件。

Cloud-backed cross-session memory for DeepSeek Harness: structured entries + vector retrieval persisted to S3-compatible object storage (AWS S3 / MinIO / R2 / OSS), with local cache projection, approval-gated writes and auditable trails

Markdown 笔记 → Agent 的长期记忆：本地 embedding + SQLite FTS5 混合召回（中文 bigram），可选密级过滤。

Zero-dependency DeepSeek Harness plugin: inject local markdown/text files into every session's system prompt as lightweight memory.

Explicitly governed shared memory spaces for DeepSeek Harness sessions

记忆管家：为 dsh-memory-evolve 补上记忆入库之后的生命周期闭环——预算看门狗、整理到期提醒、待审批队列与审批 Tab、带备份执行。只读观测记忆文件，写入一律回调 memory-evolve 官方 HTTP API。

全局记忆：AI 主动写入与读取的记忆文件，每轮对话前自动注入索引，不占上下文，仅按需展开；支持本对话禁用。

Cross-session memory vault for DeepSeek Harness: remember / recall / forget tools, per-turn prompt injection, and a browser management page.

外置记忆库插件：为 dsh 提供长期记忆的增删改查、搜索、分类、归档工具，记忆数据保存在 ~/.dsh/memory/memory.db，与当前工作区无关。

Knowledge and memory vault for DSH: memory groups with automatic summarization, free assignment between conversation memory and the knowledge base, priorities, a base-prompt layer, and AI curation.

dsh.bundle bridge that exposes the memory-vault Python CLI as DeepSeek Harness tools

外置记忆库插件（hjj588 原版的修复分支）：为 dsh 提供长期记忆的增删改查、搜索、分类、归档工具，记忆数据保存在 ~/.dsh/memory/memory.db。修复了对话记录重复堆积、标题被宿主注入消息污染、中期到长期压缩不可达、预设注入不幂等四个缺陷，并新增项目维度（条目按会话工作区归属，检索默认收窄到「当前项目 + 全局」）。

Per-project long-term memory for DeepSeek Harness, backed by SQLite.

DeepSeek Harness 记忆查看插件（Web 端 + Node 半身）：把 DSH 真实运行状态投影为短期记忆 / 工作记忆 / 长期记忆 / 过程与语义记忆四层视图，并支持 AGENTS.md / CLAUDE.md 指令文件的查看与编辑。

MemoryHub (mh) integration for DeepSeek Harness: loads .memoryhub checkpoint memory on session start, saves dsh sessions back into checkpoints, and registers the mh workflow skill and tools

Notes and todos as plain Markdown in your DSH workspace: /ml jots into today's journal, todos come in deadline/sleep-until/anytime flavors with auto-wakeup, /ml view fuzzy-opens any file — zero-token slash commands, notes stay plain files.