メモリ・ナレッジ · DeepSeek Harness プラグイン — 47 ページ

DSH Web Project Center — Cowork/WorkBuddy-style projects with folder binding, file browser, and two-way CLAUDE.md memory sync. 侧边栏「项目」入口 + 项目卡片网格 + 新建项目 + 项目详情。

DSH web plugin: bash-like prompt history in the composer — Up/Down arrows recall previously submitted messages, sourced from the session's own message log (zero config, zero extra storage).

Generic per-turn prompt injector for the DeepSeek Harness web profile — manage a list of context prompts (with enable switch) in the settings page; every round of conversation injects each enabled prompt as a notice line (「上下文注入 xxx」) into the model context, exactly like the mem0 recall reminder. Host-only logic + client settings card; zero dsh source changes.

Codex-style up/down input-history recall for the DeepSeek Harness web GUI

DeepSeek Harness 的 QQ 私聊/群聊插件，支持扫码授权、原生 Session、群记忆与工具权限。

A minimal reasoning-effort ruler for the DSH composer: one hairline, a sliding marker, per-model memory, optimistic switching — and a streamlined model picker.

DSH 消息撤回（轻量第一方实现）：工作区文件与对话历史一起回到那条消息之前，消息文本与附件放回输入框。相对上游 dsh-recall-plugin 的核心改动——启动期不再对所有历史工作目录做 eager 预热，改为用到哪个工作区才初始化哪个。

dsh-relationship 关系记忆工作台: a local relationship-memory workbench plugin for DeepSeek Harness. Contacts, confirmable AI memory extraction, pending queue, contact timelines, native relationship preset.

DSH Web 插件：在左侧边栏底部（设置按钮上方）常驻一枚 CPU / 内存占用药丸，点击展开逐核占用、时间片构成、内存细分、交换分区、系统负载与进程 Top5 详情。

Retrace · 回溯 — Recall, edit-and-resend, regenerate, and conversation/artifact versioning (timeline, rollback, fork map) for DeepSeek Harness — Web and Desktop

DeepSeek Harness 经验复盘插件：采集、提炼、人工审阅、经验沉淀与博客联动。

S1CAP for DeepSeek Harness: System-1-governed context lifecycle (association graph recall + Trace-as-State assembly + plan ranking)

DeepSeek Harness bundle: two academic research agent presets — scopus-scholar (搜索驱动模式, Scopus/OpenAlex search with a claim-verify loop) and scopus-knowledge (知识驱动模式, a code-enforced knowledge pipeline consulting a tool-free 科学顾问 persona)

Give the agent eyes on the screen: capture the whole desktop, one window, or one region and hand the IMAGE ITSELF to the session model (no second model, no description layer), plus an exact local pixel diff that locates what actually changed between two images instead of asking a model to guess. Windows only.

Yogacara eight-consciousness agent society for DeepSeek Harness: auditable double-loop runtime bridge, mneme memory consolidation tuning, MCP society tools, and six seed skills

DeepSeek Harness 长期记忆与自进化插件：L0 对话捕获 → L1 记忆提取 → L2 场景归纳 → L3 用户画像，自动召回注入 + 技能合成，纯本地。

DSH 自记忆插件 v3（P0 升级）：在 v2（加权关键词/泛化/倒排索引/前提感知/同义词规范化）之上增加事件驱动自动采集（会话轨迹落盘）、pre-step 自动召回注入（<selfmem_memory> 围栏）、写路径可靠队列（失败入 pending 重放）、CJK 感知 token 预算。

DSH 自记忆插件 v2：加权关键词关联度、问题泛化（隐去细节）、倒排索引快速检索、前提条件感知（矛盾方案区分）、关键词规范统一。记录问题、多种解决方法、脚本文件与模型调用全过程，新会话先检索再执行再回写，支持外部导入。

DSH plugin: context archiving + historical retrieval — archive_session / search_archive tools over the session-archive skill (zstd session-log decode).

DSH plugin: Session Git — export DSH sessions of a workspace as JSON files under <project>/.dsh-sessions/ so they can be committed to Git, and import them back as fully continuable sessions. Makes AI collaboration knowledge a versioned, shareable team asset.

Session KB for DeepSeek Harness: full-text search across all past sessions and recall them as @references. 会话库：全文搜索历史会话，一键以 @引用 召回给 AI（session search / recall / knowledge base）.

One-click session memory for DeepSeek Harness: mounts the official session-query tools and auto-injects a digest of prior sessions at session start.

Cross-session full-text recall for DeepSeek Harness: the model-facing `recall` tool searches past session transcripts through ctx.sessionQuery

跨对话记忆系统 v2：分层记忆（MEMORY.md + USER.md 常驻注入 + topics/ 主题库按需加载），memory 工具（target 支持 topic） + 可视化记忆面板（笔记/画像/主题库）