Productivity · DeepSeek Harness plugins — Page 188

Session-end memory for DeepSeek Harness: distils each turn's new dialogue into durable notes, then recalls the global set plus the current workspace's in a per-agent prompt section.

DeepSeek Harness 共享持久记忆插件：所有会话共享一个记忆库，提供 memory_add / memory_search / memory_list / memory_remove 工具，并在 Web 侧边栏提供 Memory 面板

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

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。

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.

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.

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.

On-demand memory for AI agents: distill session logs into layered markdown, and let queries return only the matched snippets. Ships as both a DSH plugin (mem_query tool) and a zero-dependency CLI.

Lightweight cross-session memory for DeepSeek Harness: one `memory` tool with save/recall/list/forget operations plus a Settings-card UI, persisted to ~/.dsh/memory-lite.json.

Deterministic two-level memory injection for DeepSeek Harness: global and project MEMORY.md plus today's notes, auto-loaded into every new session.

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。

Memory protocol enforcement plugin for DeepSeek Harness — forces memory_weave before tool calls, auto-ingests session turns, injects memory context into agent steps. Bridges the opencode-memory MCP server with a hard protocol gate.

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.

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

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

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

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

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.