DeepSeek Harness プラグイン — 804 ページ

Layered memory plugin for DeepSeek Harness: strictly separated project/global memory, host-driven recall before tasks and continuous learning after them.

DSH 长期记忆插件（多 provider）：OpenAI 兼容的云端嵌入 + Qdrant 向量库，自动记录对话要点与图片概览、自动召回，提供 memory_search/save/forget 工具，并在设置页提供 provider 管理、记忆管理与定期维护。

DSH 长期记忆增强插件：文档索引 + 语义检索 + 跨会话 KV 记忆（agent 工具）

Persistent long-term memory plugin for DeepSeek Harness (dsh): single memory tool, markdown storage, auto session summary, curator governance, user-profile injection.

DSH 本体（web/headless profile）的跨会话语义记忆工具：memory_add / memory_search。智谱 embedding-3 向量 + SQLite + 余弦相似度。配置可选、绝不因缺 key / 缺库 / 缺服务而崩。

Long-term memory for the DeepSeek Harness Web GUI: project-scoped and global memory stores, a Memory view tab beside Trajectory with one-item-per-row list and an Obsidian-style link graph, automatic per-turn memory extraction, automatic memory briefing injection into every request, and small-model periodic consolidation (dedupe / merge / link / archive).

Long-term memory for DeepSeek Harness agents: user preferences, project facts, session summaries, and knowledge entries, with auto-injection at session start.

受 CC-HAHA 启发、面向 DeepSeek Harness 的项目隔离持久记忆插件

DSH 记忆库：并入的提示词查看器（看每次模型请求真正发出的全文）+ 阅读优先界面（连续滚动读摘要与原文、全屏）+ 真名解析（工作区 catalog.json 的角色名/周目名/周目↔会话映射与多级回退）+ 提示词面板（压缩指令/收纳占位可编辑落盘）；会话与工作区两种根模式，只读会话与归档，复用 DSH 自身的压缩机制与检索索引。

Memory Tree bridge for DeepSeek Harness — search/persist memory, manage the memory tree, and drive the local/cloud extraction backends. · 记忆树桥接：检索/落盘记忆、管理记忆树、本地/云端提取开关。

DSH plugin: offload bulky tool logs to refs/*.md and keep a Mermaid canvas. Don't pip the wrong dsh.

DeepSeek Harness 长期记忆插件：四通道检索 + 演化闭环 + 分层治理（SQLite 单一事实源 + Markdown 快照）

Memory recall + affect state for DeepSeek Harness: BM25-lite recall with source markers, consolidation to structured memory, and a two-scalar affect state.

Curated durable memory for DeepSeek Harness: automatic capture of decisions/corrections/prohibitions/open work, progressive-disclosure recall, duplicate consolidation, old-vs-new conflict resolution, and a sidebar management panel.

DeepSeek Harness 内嵌的本地四层记忆浏览器

Layered, auto-injected cross-session memory for AI coding agents: a DSH plugin plus a standalone zero-dependency CLI. Borrows the spec/change/archive discipline from OpenSpec (MIT), but pushes instead of pulls.

从原生会话整理日常记忆、Dream 与每周复查，保留出处并审阅长期事实。

记忆核心（Memory Eternal）· fork 维护版：DeepSeek Harness 记忆插件——对话结束后自动沉淀知识卡到本地 Markdown Vault（自研去重、自研 CJK 检索、可 git 管理），设置页提供图形化知识库（统计 / 搜索 / 知识图谱 + 侧边栏嵌入式卡片），Agent 通过 memory_recall 工具按需召回历史上下文。原项目由 EternalNight996 创建并维护：https://github.com/EternalNight996/dsh-memory-eternal ；本 fork 由 pokiimon 维护，聚焦 DSH 0.2.0-rc.x 兼容性修复与界面改进，遵循 MIT、保留原作者署名。

为 DeepSeek Harness 带来分层记忆（全局 / 用户 / 项目 / GIT 分支 / 每日）与自我进化（经验沉淀 + 技能自动创建）和技能管理、待办管理、CLI 调度（kimi/codex/grok/hermes 等外部 AI 统一调度）、临时信息便签，带 WebUI 管理界面。Hermes-style long-term memory, self-evolution, skills, todos and external CLI agent dispatch for DeepSeek Harness.

为 DeepSeek Harness 带来分层记忆（全局 / 用户 / 项目 / GIT 分支 / 每日）与自我进化（经验沉淀 + 技能自动创建）和技能管理、待办管理、CLI 调度（kimi/codex/grok/hermes 等外部 AI 统一调度）、临时信息便签，带 WebUI 管理界面。Hermes-style long-term memory, self-evolution, skills, todos and external CLI agent dispatch for DeepSeek Harness. 本构建另内置三份记忆运维技能（压缩 / 整理 / 注入轨毒源取证）。

DSH plugin that extracts long-term facts from completed turns into an append-only Markdown memory inbox.

File-backed memory for DeepSeek Harness: injects your own Markdown memory file each session, adds read/write tools, and reports DSH_HOME drift so session history never silently disappears. Never reads conversations, never opens a network connection.

Gated GA-style layered memory for DeepSeek Harness: hard-injected L1, working checkpoint, settlement to Skills/L1/L2 — no silent auto-retain.

Non-invasive SQLite hybrid memory and knowledge-graph plugin for DeepSeek Harness