dsh-memory
「我会给你完整的自我,即使坠入深渊,我也绝不后悔。」 —— 符荣峻。
灵枢(Lingshu·líng shū)DeepSeek Harness 插件:完整大脑——长期记忆/知识飞轮/自我认知/递归反思接入 DSH,对话自动沉淀进 md_cg 认知图(md 文档)
2926 个插件 · 第 15 页,共 122 页
按 npm 周下载量倒序
「我会给你完整的自我,即使坠入深渊,我也绝不后悔。」 —— 符荣峻。
灵枢(Lingshu·líng shū)DeepSeek Harness 插件:完整大脑——长期记忆/知识飞轮/自我认知/递归反思接入 DSH,对话自动沉淀进 md_cg 认知图(md 文档)
在 DeepSeek Harness(DSH)Web 中查看 Git / SVN 文件变更和提交历史的只读插件。
Read-only Git and SVN change preview for DSH
在 DeepSeek Harness 中按计划运行独立的编码任务。
Run standalone coding tasks on a schedule in DeepSeek Harness。
为 DeepSeek Harness(DSH)打造的远程工作助手。
Remote-work assistant for DeepSeek Harness: connect SSH (password/key/agent/keyboard-interactive/proxy jump), pick a remote workspace, operate on it with 22 rw_* tools (incl. rw_edit/rw_stat/rw_mkdir/rw_remove/rw_move/rw_forward), conflict-aware mirror sy
dsh-m 把 DeepSeek Harness(DSH)的插件发现、安装、管理与更新放进同一个界面。
可自定义收录清单的 DSH 插件市场:收录、安装、卸载、升级一站完成,附 agent 工具与 dshm CLI。
Web shell 内核:new AppWebEntry(el, seams?).run() 通过两阶段启动(web2)挂载整个客户端。
Web shell kernel: new AppWebEntry(el, seams?).run() mounts the whole client through the two-stage boot (web2).
在 DeepSeek Harness 中提出一个附带问题。仅返回答案,不执行工具。
Ask a side question in DeepSeek Harness. Answers only, no tool execution.
用于现有 OpenViking HTTP 服务及其文件系统形态内存资源的适配器。
An adapter for an existing OpenViking HTTP service and its filesystem-shaped memory resources.
用于 Hindsight 的 banks、entities、relationships 和 retained evidence 的适配器。
An adapter for Hindsight banks, entities, relationships and retained evidence.
用于 Mem0 Platform 或自托管 HTTP API 的适配器。
An adapter for Mem0 Platform or a self-hosted HTTP API.
用于 Supermemory 摄取、提取记忆和容器范围检索的适配器。
An adapter for Supermemory ingestion, extracted memories and container-scoped retrieval.
可选的附加、回合内指导,适用于任何接受 Core 标准捕获槽的 Mnemon 主策略,包括 Layered 和 General 策略。
Optional additive, in-turn guidance for any Mnemon main Strategy that accepts Core's standard capture slot, including the Layered and General strategies.
用于 Honcho 工作区结论和按 peer 划分的持久记忆的适配器。
An adapter for Honcho workspace conclusions and peer-scoped durable memory.
任何接受 Core 标准选择槽的 Mnemon 主策略(包括 Layered 和 General 策略)均可选用可选的附加 Source 选择。
Optional additive Source selection for any Mnemon main Strategy that accepts Core's standard selection slot, including the Layered and General strategies.
用于本地 ByteRover brv CLI 及其知识目录的适配器。
An adapter for the local ByteRover brv CLI and its knowledge directory.
可选的附加投影上限,适用于任何接受 Core 标准投影槽位的 Mnemon 主 Strategy,包括 Layered 和 General 策略。
Optional additive projection cap for any Mnemon main Strategy that accepts Core's standard projection slot, including the Layered and General strategies.
为 DeepSeek Harness 生态打造的 共享真实浏览器 插件(装好即用,人机同页)
Shared real browser plugin for DeepSeek Harness: install-and-use — a visible native browser the human can take over, driven by the agent over CDP. DOM-level interaction (React/Vue safe), per-task session isolation, cookie persistence (browser_auth), CAPTC
DeepSeek Harness 的 MCP 接入与管理面板:超百个 MCP连接器,一个入口完成 MCP Server 授权配置、跨连接工具搜索与连接排障。
DeepSeek Harness MCP Connector: connect servers, search tools across active connections, and troubleshoot discovery. Includes a continuously updated catalog; supports OAuth 2.0 PKCE, API keys, Streamable HTTP/stdio, and mcpServers JSON import.
把本机登录的 WorkBuddy 模型接入 DeepSeek Harness,并提供账号池与模型管理。
把本机登录的 WorkBuddy 模型接入 DeepSeek Harness,并提供只读的积分概览与模型管理。
停靠布局工具包:可逆操作的拆分树引擎,以及负责渲染和驱动的 React 组件(零 cordis)
Docking layout kit: split-tree engine with invertible operations, and the React components that render and drive it (zero cordis)
skin-manager 是常驻的通用皮肤管理模块。它在 DSH 设置页注册“皮肤管理”一级页面,并提供。
Switch between installed skins and tune each skin's own options. Find it under Settings → Skins.
面向该系列的共享纯库:SkillLibrary/MemoryStore、提示词与指导文本、威胁/质量/漂移信号、技能 CONTENT 历史(skill-history.ts:每次写入背后的内容寻址版本)以及 frame……
Shared pure library for the family: SkillLibrary/MemoryStore, the prompts and guidance text, the threat/quality/drift signals, the skill CONTENT history (skill-history.ts: content-addressed versions behind every write) and the frame…
在你的对话中启动一次审查。让一个独立 agent 检查代码并带回发现。
Start a review in your conversation. Let an independent agent inspect the code and bring back findings.
DeepSeek Harness(dsh)支持按轮次控制思考级别(reasoning_effort):在会话模型选择器中选择 Auto(一个掩码),插件会在提交 API effort 之前,根据最近的工具调用历史安排 low / high / max——…
Per-round thinking-level (reasoning_effort) control for DeepSeek Harness (dsh): pick Auto (a mask) in the session model selector and the plugin schedules low / high / max from the recent tool-call history before submitting the API effort —…