Memory and knowledge · DeepSeek Harness plugins — Page 39

生成式引擎优化（GEO）DeepSeek Harness plugin for SEO, GEO and AEO analysis of Markdown knowledge bases.

几何论（共扼谱几何 CSG）知识库插件 for DeepSeek Harness：以 Markdown 文章为唯一真源，程序自动重建 BM25 索引、类型化主张依赖图与修复工作单并做一致性审计，附 869 条真理层与 SymPy 公式验证。开箱即用的离线知识库（31 个 geo_* 工具），零运行时依赖。Conjugate Spectral Geometry knowledge base plugin for DeepSeek Harness: offline BM25 retrieval, typed claim graph, consistency audit and SymPy formula verification.

DSH 全局记忆插件：侧边栏「全局记忆」页，直接查看/编辑 ~/.dsh/AGENTS.md 与 ~/.dsh/memory/*.md。Host 半边注册 /api/dsh-memory 路由（回环限制），client 半边注入侧边栏入口与中心面板。热插拔挂载，不改 DSH 源码。

Automatic cross-session GoodMemory recall and writeback for DeepSeek Harness

Governed long-term memory core and DSH technical-preview adapter contracts.

HarmonyOS NEXT / ArkTS development skills for DeepSeek Harness — ArkTS/ArkUI coding knowledge and ArkTS code review.

Hermes-style persistent memory for DeepSeek Harness (DSH) — a faithful port of the hermes-agent MEMORY.md / USER.md mechanism: bounded dual-bank memory, one `memory` tool (add/replace/remove/batch), frozen-snapshot injection, nudge reminders. Zero external dependencies, zero LLM cost.

Official-grade DeepSeek Harness memory plugin backed by Hindsight (vectorize-io). Add /hindsight commands and model tools that recall, remember, inspect and forget through a Hindsight memory bank.

Hindsight long-term memory for DeepSeek Harness: auto-recall context injection before each agent step (agent/pre-step) and auto-retain of each finished turn (session/event).

DSH plugin: honcho long-term memory tools (memory_store / memory_search) over a self-hosted Honcho v3 backend

Project the Mnemon runtime memory files (USER.md / MEMORY.md) into every session's system prompt as one lazy section, independent of dsh-mnemon's lifecycle gate.

Gives the DeepSeek Harness agent a configurable humanized whale-girl maid persona (address, self-name, speaking mode), an immersive no-plugin-meta rule, and a lightweight layered memory with query-triggered recall.

Hypatia skills for DeepSeek Harness: knowledge-graph query skill plus automatic conversation-memory bridge. Requires the `hypatia` CLI on PATH.

Deterministic, zero-LLM, byte-budget context compaction for DeepSeek Harness, with byte-exact recall of compacted history.

Install iHow Memory as a local-first shared memory plugin for DeepSeek Harness.

DSH IMA Copilot 插件：通过 ima_ask 深度问答腾讯 IMA 知识库，含 Web 配置界面

Tencent ima (ima.copilot) knowledge-base tools for DeepSeek Harness: list, cross-knowledge-base fan-out search, browse, URL import, file upload and notes, over the official ima OpenAPI.

零依赖、本地优先的 A股 产业链 / 申万行业 / 概念板块 知识图谱 MCP server —— 查询个股所属行业、同业竞品、产业链上下游、概念成分与交叉选股。无需 API key、无网络依赖。

DeepSeek Harness plugin: multi-tier memory management, semantic retrieval, structured memory, and model-context awareness for infinite context.

User-only instruction memory for DSH: long-term instructions maintained in the settings UI and auto-injected into every conversation — the model has no write access. 指令记忆：只由用户在设置页维护的长期指令，自动注入此后每轮对话；模型没有任何写入口。

第一个 zvec 原生情报站:刷到的信息自动沉淀(采集/文件夹/网页/笔记),agent 语义+关键词混合检索带出处,零守护进程、零 API key、文档不出本机;支持 Obsidian 反哺与定时自动化

Typed, auditable long-term memory for the DeepSeek Harness: a turn-end write hook, a judgement layer (Jev or a deterministic fallback), a local store, and per-session recall injection.

K12 capability substrate for DeepSeek Harness: 143 objectively-decidable capability anchors and 6,091 list items extracted from China's MOE 2022 curriculum standards, with local-only learner profiles

DeepSeek Harness (DSH) plugin — inject context when user input or model output hits configured keywords, with toggleable/configurable rules and model-editable memory.