dsh-mnemosyne
rebron1900Mnemosyne 记忆层在 DeepSeek Harness 中的插件 — 本地优先、SQLite 支持的跨会话记忆。
DSH memory plugins give DeepSeek Harness persistent recall across sessions — storing notes, indexing a codebase or knowledge base, and retrieving the right context back into a conversation.
Repositories with traceable evidence of a DeepSeek Harness relationship. They have not been reviewed, install tested, or security checked — the signal below each one is the whole of what the registry currently knows.
Mnemosyne 记忆层在 DeepSeek Harness 中的插件 — 本地优先、SQLite 支持的跨会话记忆。
给 DeepSeek Harness 的三层记忆:常驻事实 + 会话摘要 + 全文检索。注入不花任何模型调用,写回用你当前选的模型。
RiverMind:基于 DeepSeek Harness 的德州扑克 AI 陪练,支持双人对局、长期公开行为记忆与可追溯的决策复盘。
Deepseek harness memory
Per-host personalization for DSH: custom instructions, local long-term memory, and reply-tone presets.
DSH bundle that bridges the Codebase Memory MCP code knowledge graph into DSH via the official @deepseek-ai/dsh-mcp-client.
Long-term memory for AI agents on Jev. Keep raw records, judge them with a fast System 1 model and answer from under 4k tokens of context.
语织:中文优先、用户可控的 AI 写作风格记忆层,让 AI 学会你的表达,需要时再调用。Chinese-first style memory for AI; DeepSeek Harness adapter included.
Memory and token-optimization plugin toolkit for DeepSeek Harness: cross-session knowledge graph memory + five-layer token-saving orchestration.
DeepSeek Harness (dsh) 插件开发知识库:官方文档完整镜像 + 主题导航与检索。Plugin development knowledge base for dsh.
住进 DeepSeek Harness 的 Instagram 助理:带着人格与记忆,把真实的 DSH 使用数据变成 Story / Note 节奏,只有主人自己的私信能指挥它。An Instagram assistant that lives inside DeepSeek Harness: persona-driven Stories & Notes from your real DSH usage, controlled only by your own Instagram DMs.
DeepSeek Harness 插件:跨会话持久记忆(Hermes 式)
Obsidian-compatible long-term memory vault plugin for DeepSeek Harness (DSH): local Markdown storage, sidebar management page, token-budgeted recall, durable journal outbox.
VRChat creator toolkit for DeepSeek Harness (DSH): 415-page knowledge base, 9 tools, 6 skills. / VRChat 创作者工具链:知识库 + 红线注入 + 专用工具 + 随包技能
Two-layer long-term memory for DeepSeek Harness (DSH): global + per-project markdown, live re-read, zero extra LLM cost, with a Settings panel. 给 DSH 的两层长期记忆。
DSH 长期记忆插件:上下文超过阈值时把最早的一段对话归档到 memory/ 回忆文件夹,之后按关键词与重要度概率自动回忆。Host-only, zero-dependency memory engine for DeepSeek Harness.
🧠 Cross-session memory for DeepSeek Harness backed by Hindsight. Self-contained dsh-plugin: /hindsight commands + hindsight_recall/remember/status/list/forget agent tools. Lightweight, no dsh-mnemon, no orchestrator.
dsh-plugin-memory: a persistent 5-layer memory system plugin for DeepSeek Harness (DSH) — index+topics split, truncation budget, relevance injection, idle LLM auto-extraction, and 6 agent tools.
Local personality, memory and distillation layer for DeepSeek Harness — SOUL/IDENTITY/USER/STATE persona files, cross-session memory and LLM distillation, auto-loaded on startup.
DSH 原生 Cordis 插件:知识库(FTS5)、路由强制、会话记忆、沙箱执行(Think-in-Code)——context-window 减负
Cairn — long-term memory for the DeepSeek Harness (@chenhw7/dsh-memory). Persistent cross-session memory: facts, preferences, corrections, lessons. BM25 retrieval, three-layer scoping, human-confirmed writes.
LMA (Layered Memory Architecture) 是一个为 DeepSeek Harness 设计的地基插件(Foundation Plugin)。它定义了 “记忆体(Memory Body)” 这一抽象概念及其挂载/卸载协议。 它与其他记忆插件的本质区别在于:LMA 是一个容器和载体,让 dsh-memory-evolve、EchoCore 等“能力性插件”可以挂载其上,它本身也内置了一套可开关的基础记忆流程,作为可选能力。LMA结束记忆功能的“一锅乱炖”,实现跨会话的结构化记忆机制。(目前功能还在持续完善以及测试,对于其他插件的接口在构想完整后逐步推动)
Intelligent memory system for DSH - Track user preferences, tool usage, and project context to provide personalized recommendations
Long-term memory and self-evolving skills for the DeepSeek Harness · DeepSeek Harness 的长期记忆与自我演进能力 —— Plain Markdown on disk, no vector store
DSH 生态中最好的文本编辑插件:撤销重做、Ctrl+S 保存、未保存确认、二进制检测、悬浮窗几何记忆,dock-files 的默认文本查看器;依赖 dock 与 dock-files | The best text editor for DSH: undo/redo, Ctrl+S save, unsaved-change confirmation, binary detection, window geometry memory; the default dock-files viewer; requires dock and dock-files
DeepSeek Harness 用户记忆插件
面向个人用户、安装在 dsh 中的 Chat Memory+Skill 自动演化插件
Editable, session-isolated personalization memory for DeepSeek Harness
删掉不喜欢的 AI 回复,或删掉已发送的错误提示词 —— 每条消息可撤回 / 删除 / 删除此处及之后(DSH 插件,append-only 墓碑,模型上下文与界面同步)。Per-message recall & delete for DeepSeek Harness. Requires dsh >= 0.1.7.
Cross-session long-term memory plugin for DeepSeek Harness
Turn your local Obsidian vault into a RAG chat panel inside DeepSeek Harness (DSH). 100% local BM25 retrieval, clickable citations. 把本地 Obsidian 变成 DSH 的本地知识库对话面板。
KnowLP-RAG: dual knowledge-graph RAG for Markdown notes — dsh plugin add @eqman00003/knowlp-rag · MCP + native Cordis plugin for DeepSeek Harness (dsh) & Claude Code
Veyra — Engineering Intelligence for Coding Agents. Persistent engineering memory + optional AST code intelligence (Dual-Brain) for DeepSeek Harness. Zero runtime npm dependencies.
DSH plugin — long-term memory as a short, categorized Markdown living document, rewritten in place each turn.
dsh-engram-relay 公开镜像(上游:dsh-external/dsh-engram-relay):跨会话分层记忆 + 哈希×语义×因果超稀疏唤醒,13 个 engram_* 工具,BSD-3-Clause
Fully local vector memory plugin for DeepSeek Harness: local embeddings, SQLite storage, automatic recall injection, dedup with conflict detection, soft-delete recycle bin, online backup.
Memory plugin with built-in curation and governance for DeepSeek Harness: 为你的 DSH 赋予可塑性记忆
DeepSeek Harness 插件:可审计的长期判断记忆、确定性取代、未完成问题、用户确认的人格演化与知识图谱。 Auditable judgment memory for DSH agents.
PR Genius — 提交前改进顾问 + 大型开源项目 PR 知识库
器灵 · 跑在你自己电脑上的记忆与人格助手插件:以「人在循环」的双向复盘为核心回路,人格由共同记忆长出并有定型锁,记忆树可归并、可回溯、每次改动都留痕。 Artifact Spirit — a local-first memory & persona plugin for DeepSeek Harness. A two-way review loop with a human in it; an auditable memory tree; a persona lock you hold.
Deploy a checkpoint as a reachable inference endpoint in DSH: probe, backend select, three-stage health check, registration, auto-degrade (memory/concurrency/precision/port), rollback, teardown — hash-chained audit log. 154 tests.
Personal AI memory semantic layer SDK (Rust + SQLite) — short/mid/long-term memory with hybrid recall
cardian — DeepSeek Harness knowledge-center plugin: RepoWiki notes / flashcards / memory in a local Obsidian vault
Long-term, agentic memory for DeepSeek Harness — A-MEM with prompt-injection defenses, atomic persistence, and native + MCP integration.
DSH 助手人格与长期记忆插件:独立可用,不依赖其它插件。管 AI 自身的名字与角色、对用户的称呼、回复风格与自定义指令;人设支持全局 + 按工作区两级覆盖;长期记忆走三段式(候选捕获 → 待审缓冲区 → 用户裁决才生效),并支持一键导入其它 AI 的历史记忆。
轻量记忆系统插件:四个 Markdown 文件(USER/PROJECT/WORKLOG/CONVENTION)+ append/distill 两个动作,零外部部件,prefix-cache 友好
🌱 BigSeed 闪念记录与人生拼图 - 捕捉生活点滴生成人生故事/自传 | Life story, journal, biography, memory keeper
Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy
DSH 简化版记忆插件:SQLite 条目化记忆(标题/重要程度/来源/内容,增删改查)+ 日历与到点提醒(月视图+时间轴+待执行/已完成双tab),对话面板记忆 tab 与设置二级菜单,中英双语自动跟随。
ARPM-derived local hybrid RAG plugin for DeepSeek Harness
Cross-session memory plugin for DeepSeek Harness (dsh): embedding search + automatic system-prompt injection
Long-term memory for DeepSeek Harness in Claude Code's format: private, overlay, or shared with Claude Code, with provenance on every file
DSH Web 系统状态悬浮窗:实时 CPU/内存/磁盘占用率 | System-status overlay showing live CPU, memory and disk usage for DSH Web
DeepSeek Harness plugin - Thread session memory adapter (dsh-thread)
DeepSeek Harness plugin: render GeoJSON/vector data into an interactive GeoLibre map and let agents operate the live map (layers, styles, view, GeoLibre algorithms and Whitebox WASM tools) through agent tools.
本地长期记忆插件 for DeepSeek Harness:卡片以 Markdown 存在你自己的 Obsidian vault 里 · Local long-term memory as plain Markdown cards in your own Obsidian vault
dsh-pm is the ChunSun × DeepSeek Harness reference plugin: an AI-native project-delivery loop driven by ChunSun. Requirements / Runs / Steps / acceptance scenarios & cases / work-memory, a session delivery panel, and 28 chunsun_* model tools — with the platform as the single source of truth. MIT.
DSH 插件:周报生成器——聚合最近 N 天的 git 提交、会话活动与每日记忆,自动生成 Markdown 周报,全程只读。Weekly Digest Generator for DeepSeek Harness.
🎭 Native immersive RP & companion studio for DeepSeek Harness. Character cards + Hindsight graph memory, per-character memory banks, zero host patching.
Native, per-workspace long-term memory for DeepSeek Harness: approval-gated writes, cited provenance, FTS cross-session recall — no external server, no extra runtime dependency.