The DSH Plugin Ecosystem

Openclaw记忆插件Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse

A local-first Markdown notebook where what you write becomes durable agent context: keep requirements, decisions, research and personal knowledge in one place, point an agent at the part it needs, and save the result back into the same note. Tauri desktop app, connected over MCP and CLI.

A pure-plugin implementation that brings cross-session long-term memory and background self-evolution to DSH: five memory tracks, git-branch awareness, in-turn self-review, skill self-evolution with a skill manager, four to-do tracks, COI scheduling, session broadcast and search, and a prompt manager — zero core changes, zero runtime dependencies.

Use this cross-platform skill in Codex or Claude Code to establish repository-local continuity memory so a future agent can recover objective, status, decisions, validation, risks, and next actions without relying on previous chat history.

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

Model-driven context management (Active Context Pruning / ACP) for the DeepSeek Harness — the model decides when and what to compress. Ported from billion-context-pi (ranxianglei); acp-kernel reused verbatim. CompactionEngine backend with compress/decompress/search_context/acp_status tools.

Agent-agnostic workflow skill for maintaining Obsidian knowledge bases

DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.

Mneme · DeepSeek Harness 的跨会话记忆插件 —— 记忆主权归还于你：SQLite + 可编辑 Markdown 双写，autoDream 梦境巩固，本地离线语义检索（Embedding / Rerank / 聚类）

LLM-free lossless* compaction engine for DeepSeek Harness

DSH 自动记忆插件:三层记忆(用户级/项目笔记/每日日志)自动注入与检索、每日反思、可视化面板与设置页,支持继承其他 AI 工具的历史记忆。An auto-memory plugin for the DeepSeek Harness Web GUI: three-layer memory (user-level / project notes / daily logs) with automatic injection and retrieval, daily reflections, a visual panel and settings page, and inheritance of memories from other AI tools.

Bridge Claude Code memory, skills, and config into DeepSeek Harness

Open task handoff protocol for DeepSeek Harness, WorkBuddy, Claude Code and Codex — verified state, not chat logs

Nowledge Mem community plugin bundle for DeepSeek Harness

DSH 项目持久化记忆插件（TypeScript）：会话归纳 + 经验教训沉淀，写入 PROJECT_MEMORY.md 与全局索引；每轮工作结束自动提醒蒸馏、自动注入未来 AGENTS；附 Web GUI 记忆面板（项目/全局 tab、检索、手动记录/删除）。dsh-plugin

reSanity 散修 — 散户的认知组合管理：查证、避坑、记忆、复盘。一份 SKILL.md，零依赖。

Noema long-term memory plugin for DSH: durable, inspectable agent memory with recall tools and a settings page.

Per-host personalization for DSH: custom instructions, local long-term memory, and reply-tone presets.

Windows-friendly full-minimal DeepSeek Harness agent preset (Minimal V3): minimal persona, platform shell (pwsh/bash), common file/search tools, no auto-inject/compaction.

Task planning with experience muscle-memory for DeepSeek Harness: condition-reflex recall + LLM capability matching + auto-persisted lessons

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.

Git-native AI learning OS with a GitLearnOS-exclusive DeepSeek Harness panel, targeted practice, local RAG, and learner-owned memory.

DeepSeek Harness 用户记忆插件

为dsh构建持久化跨工作区记忆的插件

DeepSeek Harness (dsh) plugin: migrate Claude Code sessions, memory, skills and CLAUDE.md into DSH with seamless resume (claude_scan / import_claude / resume-claude / web panel)

Terminal-style input history for the DeepSeek Harness web composer: edge-first arrows with exact draft/caret restore, browser-local persisted history, Ctrl+R reverse search, workspace recall - and sliding-context awareness (compaction summaries in recall/search, compaction notice with one-click /compact fill).

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

Agent memory for DeepSeek Harness | DeepSeek Harness 记忆插件

Auxiliary models for DeepSeek Harness: vision understanding and context compression through dedicated model routes.

agentmemory for DeepSeek Harness (dsh): full memory_* tools, capture hooks, and context injection over the local REST server

Ecosystem plugins for DeepSeek Harness: bounded cross-session memory and skill lifecycle curation, ported from hermes-agent. Tagged dsh-plugin.

DeepSeek Harness 插件（Cordis toolset）：操作本地 Obsidian 知识库（vault），提供搜索、读写笔记、双向链接 / 关系图谱、批量整理，并通过 Obsidian 的 "Local REST API" 社区插件调用高级能力（高速全文搜索、触发命令 / 模板）。

DSH host plugin - smart outbound HTTP(S) routing: named proxies (http/https/socks4/4a/5/5h), per-host/provider/plugin rules, direct-first fallback with health memory (global fetch + node http/https)

把「记忆」带进 DeepSeek Harness：极简文本记忆系统，双轨记忆（流水日志 + 人物/产品实体画像），大模型为核心驱动。无需安装其他软件，无需编译，无第三方依赖。

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

Headroom context-compression proxy integration for DeepSeek Harness: detect/install/start Headroom, auto-configure the DeepSeek compressed route, one-click route-switch UI. Built on headroomlabs-ai/headroom (Apache-2.0).

DeepSeek 陪伴模式插件 —— 人设、记忆、聊得下去：SOUL 人格 + Hermes 长期记忆，可选 QQ 通道

将千星沙箱（原神千星奇域）知识库接入 Deepseek Harness 的插件

No description

A brain-inspired runtime for DeepSeek Harness agents — remember, self-correct, learn. v0.1 ships memory (injection, notes, recall), 100% covered.

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 integrating claude-mem (memory for dsh)

Cross-session long-term memory plugin for DeepSeek Harness (DSH)

Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore + feedback learning + audit), not just stored

Bridge DeepSeek Harness (DSH) session compaction summaries into Hermes Agent persistent memory. 把 DSH 会话压缩总结自动桥接进 Hermes 永久记忆。

Cited memory over DSH's lossless session log — distilled, human-auditable facts with citations back to the exact source events; memory_read/memory_expand tools, recall index, and a dsh-memory CLI.

/fuck — migrates your Claude Code & Codex habits into DeepSeek Harness. One command, parallel scan, boot-time recall.

DSH plugin: Git-backed project memory with line-addressable evidence, freshness tracking, and audit trail

数据台账：DeepSeek Harness 本地数据统一看板——对话/账本/技能/记忆/日志的来源、位置与内容摘要，回收站删除、浏览器存储清理（dsh-plugin）

Unified fleet-wide agent memory system for DeepSeek Harness — shared Obsidian Vault for dsh, Codex, Claude Code & Hermes with dependency-free Python FTS5 core.

Installable DSH bundle: the dsh-plugin-guide plugin-development knowledge base as an on-demand agent skill. Official docs archive (EN/ZH), Cordis primer, 114-repo community archive, 1654 archived Discussions, 20+ battle-tested pitfalls.

No description

面向 DeepSeek Harness 的 OpenViking 检索、资源管理、自动召回与会话记忆插件

Learning assistant extension for DeepSeek Harness (dsh): brings DeepTutor tutoring to your agent — deep explanations, self-test questions, learning paths, personal knowledge-base search (RAG), and note archiving. | 面向 DeepSeek Harness 的学习辅助扩展:为 agent 接入 DeepTutor 辅导能力 —— 深度讲解、自测题、学习路径规划、个人知识库检索(RAG)与笔记归档。

Memory retrieval plugin for DeepSeek Harness (dsh): wiki double-link memory graph with 9 tools — hybrid search, read, link-scan, remember, forget, compile, health-check, resident retriever subagent

Structured long-term memory system for DeepSeek Harness

Local Markdown wiki as long-term memory for DeepSeek Harness — RRF-fused retrieval (keyword + wikilink graph + temporal), token-budget injection, auto-capture. Ported from llmwiki.

DSH Cordis plugin: turn any source text into an AI knowledge graph (facts/inferences/concepts/definitions/examples/counter-examples/rules) with two-way linking between the graph and the original text.

Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy

Local system resource monitor (CPU / memory / disk / load / uptime) for the DeepSeek Harness bottom status bar.

Forge-plus: math/logic/regex/eprover/system/repair gates + TCM diagnosis + memory recall plugins for DeepSeek Harness (dsh)

Agent-driven long-term memory for DeepSeek Harness (DSH)

Read-only Windows device info tools for DeepSeek Harness: 12 win_* tools (time, system, CPU, memory, disk, GPU, network/WiFi, battery, processes, USB, audio, printers) via Node os + WMI/CIM. Bundle-form dsh plugin.

Complement to DSH Creator mode: stage, score, and solidify in-memory plugin trials to disk.

dsh的记忆管理

Turn-granular context memory for DeepSeek Harness.

人格化伴侣插件 for DeepSeek Harness：角色卡、语音、Live2D、本地记忆与工作陪伴。

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

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

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.

Local-first persistent memory infrastructure for DeepSeek Harness: hot bootstrap, Chinese-BM25 cold recall, lease-lock transactional writes, read-only governance

ProactiveAgent × DeepSeek Harness 插件组：把主动记忆 + 主动建议接入 DSH（6 个 cordis 插件，引擎零重写）

Multi-agent spatiotemporal memory graph for DeepSeek Harness.Cross-session persistence, knowledge flywheel, importance-gated memory — trust governed by an auditable charter.

The first collision-based memory system: it doesn't retrieve old ideas — it smashes old cards into new ones.

Mneme: DSH-native memory system built on Memory-as-Compilation. DeepSeek Harness plugin suite (dsh-plugin).

A DeepSeek Harness (DSH) agent preset for institutional multi-factor stock-selection research: methodology knowledge base + zero-dependency factor statistics.

No description

dsh memory: Nocturne Memory client for DeepSeek Harness

VSCode-like bottom status bar for DSH Web: token usage, CPU/memory char bars, session stats, live TPS, per-item config

Editable, session-isolated personalization memory for DeepSeek Harness

agent memory plugin based on CLP

Cross-session memory plugin for DeepSeek Harness (dsh): embedding search + automatic system-prompt injection

Local knowledge base RAG for DeepSeek Harness

dsh plugin bridging agentmemory REST API: memory_search / memory_remember / memory_forget / memory_health

Durable cross-session SQLite memory for DeepSeek Harness

为deepseek-harness添加向量化跨会话记忆插件

Eight DeepSeek Harness plugins: persona, language guard, per-request vision fallback, python/windows write guards, cross-agent memory, image generation, and skill shell injection.

你的 AI，从此记得你——拾光记忆引擎，它记得你们聊过的每一件事，还会主动关心你。

A governed long-term memory core for AI agents, with technical-preview adapter contracts for DeepSeek Harness integration.

Agent-driven compaction for DeepSeek Harness: the agent summarizes its own conversation (KV-cache friendly, no giant replay). Verified in production at ~460k-token sessions.

No description

No description

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.

DSH (DeepSeek Harness) agent preset + plugin: Hermes-style cross-session memory & autonomous skill learning.

Folio (兰亭): consulting document-generation engine with 5-stage pipeline (intake, memory, methodology, deliverable, proof). Native DSH plugin stack: 15 tools, session-protocol events, L0 guard, agent preset. Swappable methodology packs, zero-key start.

DeepSeek 深度调校的沉浸式角色扮演 Agent 预设（dsh）——零工具纯对话、酒馆式演出格式、文件记忆库

TMCRA × DeepSeek Harness：跨软件、跨会话召回与更新项目记忆，切换工具无需重新介绍项目。

AI-native engineering environment management that makes your codebase agent-ready.

AiFP 记忆感知系统｜MCP 服务，一套记忆全 AI 共享。面向中文的 Agent 感知记忆，支持叙事链、语义纠错、感知链图扩散。兼容 DeepSeek‑Harness、Claude Code、Cursor、Codex等全部 MCP 客户端，数据完全本地存储。

No description

Native OpenViking memory integration for DeepSeek Harness: host-plane memory service with automatic session capture (session/event + session/flush hooks), session→peer isolation, memory tools (write/recall/search/profile/forget) and automatic <memory_profile> prompt injection for every agent preset.

Persistent, model-editable memory/notes store for DeepSeek Harness. Adds memory_set/get/delete/search tools backed by ctx.storageDomain so facts survive across sessions (dsh-plugin).

DSH-Plugin: durable agent memory core - mem_save/mem_search/mem_health backed by storageDomain (survives restarts), 記憶 view tab.

跨会话持久记忆（移植自 pi-memory）

Privacy-first task memory and adaptive local desktop observation for DeepSeek Harness

DeepSeek Harness (dsh) ↔ TencentDB Agent Memory (TAM) long-term memory bridge: L0 conversation capture + recall injection via TAM v3 data plane

Semantic long-term memory for DeepSeek Harness: hindsight_retain/recall/reflect tools + auto-recall over local Hindsight daemon (pgvector + DeepSeek embeddings)

Action-State Memory Engine: typed time-series memory (states + actions) with trend/anomaly/causal analysis for DeepSeek Harness

AI patent disclosure drafting plugin for DeepSeek Harness - 8-stage pipeline, LaTeX to OMML, diagram generation, self-improving memory

把零散笔记（文本+图片）保存到语雀知识库，由模型自动分类；图片经 GitHub 图床上传（jsdelivr CDN）| Save messy notes (text + images) to a Yuque knowledge base, auto-classified; images hosted via GitHub repo

No description

Persistent cross-session memory plugin for DeepSeek Harness: workspace-scoped durable facts with memory_write/list/search/forget tools and bounded prompt injection

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.

DSH plugin: shared persistent memory store across all sessions, with memory_* tools and a Web sidebar panel

Task-based AI workbench for indie developers: tasks-as-sessions, comment-as-control, project knowledge base that persists across tasks. Built on DeepSeek Harness.

Import chat history & memory from other AI agents (Claude Code, Codex, Gemini CLI, Aider, Cline, OpenCode, Hermes, OpenClaw) into DeepSeek Harness

No description

AgentFrame compaction backend for DeepSeek Harness: semantic+physical KV compression (35.6x)

MemoryDirector plugin for DeepSeek Harness: LLM-driven remember/forget (official harness has no memory)

入选 DeepSeek Harness 官方精选列表的三个插件：记忆/压缩/主动调度 完整技术文章

Persistent memory layer for AI agent swarms. Postgres-backed retrieval, Markdown as source of truth, sub-second cascade sync. Self-hosted.

Encrypted 4-layer lifelong memory for DeepSeek Harness - powered by MindForge

DeepSeek Harness 插件：跨会话持久记忆（Hermes 式）

DeepSeek Harness plugin: cross-session memory for the model. Full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context — recall earlier decisions, commands, and mistakes.

Workspace-scoped, local-first LLM wiki plugin for DeepSeek Harness.

DeepSeek Harness 自动压缩插件：模型工具 compact_now，回合结束后自动压缩上下文 | Auto compaction plugin for DSH: compact_now tool, compacts context after the turn

生成式引擎优化（GEO）DeepSeek Harness 插件：面向本地 Markdown 知识库的 SEO、GEO 与 AEO 审计工具。

WikiBridge：DSH × Obsidian 知识库桥接插件（约束工具 + 自动词典检索 + 零补丁配置）

Two-phase long-term memory plugin for DeepSeek Harness (DSH): per-session extraction + global consolidation, always-injected summary, and memory_list/read/search/add tools.

Auditable workspace-local project Wiki with a native Web UI for DeepSeek Harness