dsh-memory
TowzaiCross-session memory plugin for DeepSeek Harness (dsh): embedding search + automatic system-prompt injection
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.
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
Set the startup size and position of DeepSeek Harness Desktop: fixed/memory modes, size presets, position memory. | 设置 DSH 桌面版启动窗口大小与位置,支持固定/记忆模式、位置记忆与比例预设。
MemoryHub (mh) plugin for DeepSeek Harness (dsh): auto-loads checkpoint memory on session start, adds mh_* tools and the mh skill, and a Memory tab in the web UI
给 DeepSeek Harness 的记忆骨架:人格注入 + 纯 Markdown 记忆系统(长期记忆 / 日记 / 灵感 / 任务卡),自带检索与看图工具。零依赖,装上即用。
给 DeepSeek Harness 加一套心情系统:33 种心情、跨会话记忆、审美品味库、加密日记、主动开口。日记只由模型自己写,插件只攒素材,没有系统总结模板套话。
基于项目逻辑的dsh记忆系统,项目基于交接文档,知识基于项目沉淀。以人实际工作的逻辑,做知识的聚合和交接。开放书写规范以及全插件提示词的前端编辑(热加载),用户可自行优化,或者让模型帮插件通过修改提示词自进化。
Memory Fortress for DeepSeek Harness: 5-track layered memory, self-evolution, knowledge graph (SQLite+FTS5), status pill. 本地记忆堡垒:五轨记忆·自我进化·知识图谱·状态灯。
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore + feedback learning + audit), not just stored
Long-term cross-session memory plugin for DeepSeek Harness
Chinese web-fiction workflow skills for DeepSeek Harness: planning, file-backed memory, consistency review, rollback, and style profiling.
Native memory plugin for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Cross-session persistent memory for the DeepSeek Harness: a model-facing memory tool, an always-on index section, and a bundled maintenance skill.
面向 Zotero 论文库的浪潮式 RAG 细节检索系统 —— DSH 外部插件。移植 VCPToolBox 浪潮语义动力学思想(标签河道图传播/虫洞跳转/钟型阻尼/Ω重排),配 BM25+RRF 混合检索、claim-evidence 忠实度校验、两级增量索引
Observational memory for DeepSeek Harness: background observers distill session work into observations and durable reflections, so long sessions survive compaction with their decisions intact.
User-authored tiered long-term memory for DeepSeek Harness: injected as a system-prompt section, with a Chinese panel to view and edit it. The AI never writes to memory on its own.
DSH 记忆插件:按日/周/月/年分层,记忆有更新就提醒模型按层读一遍、独立复盘一段关系并给出理由。判断只写状态文件,不写进日记。
Dot for DeepSeek Harness: a personal chief-of-staff agent with memory, tasks, safety rules, a session dispatch desk and an on-screen pet. DSH 个人总管插件
dsh (DeepSeek Harness) plugins for project-level persistent context: session archive with a mechanical index, memory consolidation (CONTEXT.md + MEMORY.md), low-frequency skill autolearn, and automatic handoff.
模拟记忆衰退的 DSH 分层上下文压缩插件:原文 → L1 → L2 → L3,越旧分辨率越低,但从不删除。
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
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.
换新对话也不失忆:跨工作区索引最近 N 天的对话,用模糊描述就能召回旧话题与原话;不确定时会反问而不是硬编(DSH 插件)。
DSH插件,以Observational Memory方式管理上下文
dsh 知识库插件,为 dsh 提供轻量级知识管理与智能检索能力/A lightweight knowledge base plugin for dsh, empowering knowledge management and intelligent retrieval
A soul for DeepSeek Harness: an in-character Whale-chan agent preset with layered long-term memory and dream-like consolidation.
Experience Memory for DeepSeek Harness
属于我们的回忆 —— 给 DSH 的分层人格记忆插件
Codex-like persistent memory plugin for DeepSeek Harness: auto-injected memory summary, memory tools, per-session rollout summaries, and a localized Web settings card.
Append-only layered memory plugin for DeepSeek Harness: five-layer partitioning, write gate, keyword recall, claim-anchors verification
Local-first long-term memory for DeepSeek Harness
DeepSeek Harness context manager: auto-records every turn, injects priority-sorted memory + pinned cross-session notes into each request, and folds real conversation history to save tokens. Persistent, restart-safe, MIT.
Memory enforcement plugin for DeepSeek Harness — bridges opencode-memory MCP server with a hard protocol gate
Local knowledge bases with explicit, source-backed retrieval for DeepSeek Harness Web.
Native DeepSeek Harness (dsh) plugin for SodaMem — auto-injects evidence-grounded memory into every turn and ingests each closed turn.
Dual-ledger cross-session memory for DeepSeek Harness: auto-extracted long-term facts (MEMORY.md) + living project progress ledger (PROGRESS.md), recalled into every new session. Inspired by OpenAI Codex's memory pipeline.
Cyrene · An Eternal Page Remembrance —— 昔涟的长期记忆插件:四问锚点、日/月/年、夜梦、五育自检、思源备份与余页(DSH 0.2.1+,零依赖)
Cross-session long-term memory plugin for DeepSeek Harness
DeepSeek Harness 的 Work Continuity 插件——跨会话工作状态显式持久化,与通用记忆解耦
DSH 插件:把 openwiki 的代码库知识库能力搬进 DeepSeek Harness —— 一键生成 / 阅读 / 更新仓库 Wiki 与 Grounded Claims(溯源知识卡片),直接复用 DSH 已配置的模型,无需二次填 Key。
可扩展的 DSH QQ 角色集成包 · NapCatQQ / SnowLuma 双后端 · B站浏览、评论与回复 · GPT-SoVITS 语音 · 可塑记忆与日记 · 自主活动与本地控制台(开发预览,组件需配置)
Local-first memory & persona plugin for DeepSeek Harness (DSH): three-layer file memory, SOUL/MOOD persona, zero-LLM capture, BM25 recall, local web panel.
Wangdefa.Memory 是一个为本地数字分身Agent 设计的五层记忆体组件,数据完全保留在本地,不依赖云端,达到轻量、白盒可控、可解释,未来将进一步往企业级原生记忆体方向拓展。
知枢 KnowHub — DSH 全局知识中心与项目长期记忆:知识库、Repo Wiki、审核与版本、增量更新、检索与上下文注入、自动提炼、备份恢复、中文面板
en: 'Backs up DeepSeek Harness sessions, plugin config and workspace memory to Nutstore (Jianguoyun) over WebDAV, with incremental upload, connection test and one-click restore on a new machine.' zh: '把 DeepSeek Harness 的会话记录、插件配置与工作区记忆通过 WebDAV 增量备份到坚果云,支持连接测试与在新机器上一键恢复。'
DeepSeek Harness plugin integrating claude-mem (memory for dsh)
Cross-session memory + a local knowledge base for DeepSeek Harness (DSH 书记官) — local-first by default, cloud optional, migration user-approved
A local-first full-text memory search plugin for DeepSeek Harness, enabling fast cross-conversation search, message-level navigation, and intelligent retrieval of your AI coding history.
灵魂的记忆提取侧·认知循环团队版:判断→捞取→组装→被判定→校准五步闭环,判官/史官/辩手/编辑/书记角色化子智能体承载,BM25 检索 + 时序素材 + LLM 组装「有用素材包」注入 linghun。与 dsh-linghun 组合使用。
🧭 DeepSeek Harness 会话时光机:消息撤回 · 原地编辑重发 · 重新生成 · 对话与产物版本化回退 (Session Time Machine: Recall, Edit-Resend, Artifact Rollback)
换个模型也不丢故事:给 DeepSeek 大鲸鱼装上本地记忆并支持web可视化管理,帮它记住你们的约定和没做完的事,下次打开还能接着聊。
Roleplay companion memory plugin for DeepSeek Harness: per-conversation persona docs, favorability tracking, recent 48h transcript search and a date-archived local knowledge base.
DeepSeek Harness (dsh) ↔ TencentDB Agent Memory (TAM) long-term memory bridge: L0 conversation capture + recall injection via TAM v3 data plane
把 OpenViking 持久记忆接入 DeepSeek Harness(DSH)的插件:自动召回、会话镜像与阈值提交、离线出站队列重放、自研 MCP 工具桥与 viking:// URI 守卫。
Local system resource monitor (CPU / memory / disk / load / uptime) for the DeepSeek Harness bottom status bar.
Claude Code-compatible persistent memory plugin for DeepSeek Harness (DSH) — same MEMORY.md format, shares one memory directory with Claude Code · DeepSeek Harness(DSH)的 Claude Code 兼容持久记忆插件——相同的 MEMORY.md 格式,与 Claude Code 共享同一个记忆目录
Reusable trajectory-tree context, exact-turn forks, and bounded cross-session recall for DeepSeek Harness
Self-evolving memory for DeepSeek Harness: capture → dream consolidation → retrieval injection → evolve. User profile, project memory, correction learning, resume narrative — with provenance back to the replayable session log. 自进化记忆插件。
Three-level source-text pins for DeepSeek Harness that survive context compaction: recall on demand, resident background, or highlighted constraints.
撤回、编辑指令与回复(连思考过程一起改)、用原提问重新生成、会话归档/删除/跨工作区移动与工作区迁移。Recall, edit prompts and replies (reasoning included), regenerate with the original prompt, session archive/delete, cross-workspace move, and workspace migration.