dsh-obsidian-board：把本地 Obsidian 变成 DSH 的本地知识库对话面板
`dsh-obsidian-board` 是 DeepSeek Harness 的本地检索插件，将 Obsidian vault 变成 RAG 面板。它采用双半架构：宿主端负责 BM25 索引与检索，浏览器端负责 UI 交互。具备极快的增量索引速度、点击引用跳转原文、可随时停止生成、以及完全的本地安全隔离（历史存储在浏览器本地，优先检索自有笔记）等特点。安装后配置 vault 路径，即可实现针对笔记内容的问答与总结。
Read Moredsh-knowledge-lite: A Local Markdown Knowledge Base Plugin
dsh-knowledge-lite is a local knowledge base plugin designed specifically for DeepSeek Harness. It stores notes locally as Markdown files and supports full-text search, hierarchical directory management, and drag-and-drop file movement. The plugin provides robust attachment handling, automatically parses Office documents and code files, and allows users to organize conversations into notes. It can be installed via the plugin marketplace or manually; note the default path configuration on Windows systems and host version compatibility requirements.
Read MoreDeepSeek Harness Plugin: dsh-save-chat — Local Markdown Chat Memory Library
`dsh-save-chat` is a DeepSeek Harness plugin designed to address the issue of losing conversation turns after a session ends. It saves conversations as local Markdown files, provides a two-tier storage structure (project-level collections and a personal knowledge base), and offers model retrieval interfaces with support for full-text search and image preservation. The plugin is dependency-free and database-free, storing data only locally. Users can save conversations with a heart button and add them to a knowledge base for on-demand retrieval by the model, making it suitable for developers who need localized knowledge management.
Read MoreDSH-RAG: Local Knowledge Base and Explicit Retrieval Plugin for DeepSeek Harness Web
DSH-RAG, a plugin for DeepSeek Harness (DSH), enables developers to convert local folders into retrievable knowledge bases. It supports formats such as PDF and DOCX and offers features including explicit `/rag` command retrieval, source traceability, hybrid retrieval with offline BM25, and session-scoped switching. Users need to install Node.js and pnpm and can use the plugin through commands to obtain evidence-based answers grounded in local documents during conversations.
Read MoreDeepSeek Harness Plugin: coolgech/dsh-siyuan
`coolgech/dsh-siyuan` is a SiYuan Note plugin designed specifically for DeepSeek Harness, aiming to enable reading, writing, and management of local knowledge bases through a unified interface. Built on the DSH protocol with zero dependencies and instant configuration, it offers 30+ tools, including document CRUD, full-text search, SQL queries, backlink analysis, and batch import/export. Users only need to install SiYuan Note and enable the kernel HTTP API to invoke it securely within an agent, making it well suited for building private, self-hosted agents.
Read Moredsh-intelhub: The First zvec-Native Intelligence Hub
The DSH plugin `dsh-intelhub` is the first localized intelligence-hub plugin built on zvec, designed to transform dynamic information into retrievable knowledge. It uses the RRF algorithm to implement hybrid retrieval and supports collecting local files, web pages, and text. All data is processed locally, with zero API calls and support for exporting to Obsidian. The plugin offers scheduled tasks and metadata filtering, making it suitable for privacy-focused DeepSeek developers who prefer local workflows. However, users should note the model’s granularity in distinguishing specific concepts and potential version compatibility issues.
Read MoreDeepSeek Harness Local Desktop Knowledge Base Plugin
`dsh-move-rag` is a Windows desktop plugin for DeepSeek Harness that requires no model weights or cloud services and supports local knowledge base management. Through a topmost WinForms panel, it allows users to drag and drop PDF, Word, image, and other files for rapid ingestion. The plugin uses hash embedding techniques to enable offline, fast local RAG retrieval and exposes the results as tools to Agents. This solution is suitable for Windows users who want to quickly build a local knowledge base, but images are indexed by file name only and the implementation relies on the desktop panel.
Read MoreDeepSeek Harness Local Knowledge Base Management Plugin: dsh-kb-manager
dsh-kb-manager is a local knowledge base lifecycle plugin for DeepSeek Harness, designed to provide agents with a lightweight, auditable long-term memory solution. Built on native SQLite indexing and hybrid retrieval (BM25 + vector search), it supports multi-format import, intelligent chunking, and asynchronous task management. It includes security features such as SSRF protection, audit logging, and a web-based management panel, offering complete capabilities for creation, retrieval, deletion, and snapshot management to ensure that agents can manage document data securely and efficiently.
Read Moredsh-plugin-rag: DeepSeek Harness Local Knowledge Base Retrieval Plugin
The DSH Harness framework provides the `dsh-plugin-rag` plugin, designed to address local codebase retrieval needs for agents while avoiding the latency, cost, and privacy risks associated with external APIs. The plugin supports indexing Markdown, code, and configuration files, using a purely local TF-IDF algorithm for keyword matching without additional dependencies. Once installed and enabled, it can search files locally or display index statistics through the `rag` command, making it suitable for agent scenarios that require decision-making based on local data.
Read Moredsh-memoryleak: Local Markdown Memory Store
dsh-memoryleak is a DSH plugin focused on local memory management. It requires no external services, and all data is stored as Markdown files in a user-specified Vault folder, making it easy to manage with Git and edit locally. The plugin provides core functionality through the `/ml` command system: it supports journaling, managing to-do items (including due dates and wake-up dates), turning conversations into a knowledge base, retrieving local knowledge, reading emails incrementally, and opening files with fuzzy matching. It also includes a persistent notes panel in the right-side Dock. With an emphasis on privacy and security, raw emails are stored only in a temporary directory, making it suitable for developers who value data control and privacy.
Read MoreDeepSeek Harness Plugin Introduction: dsh-llm-wiki (A Local-First, Workspace-Level LLM Knowledge Base)
`dsh-llm-wiki` is a local-first memory plugin for DeepSeek Harness, designed to solve the challenges of AI-maintained knowledge bases. It builds indexes based on the workspace directory structure and supports hybrid search (including vector, full-text, and graph retrieval) along with agent-based maintenance tools. The plugin keeps all data fully local and securely isolated, making it suitable for privacy-sensitive or offline scenarios. The current version has no Web UI and supports Markdown/TXT files only.
Read Moredsh-doc-index: Local Knowledge Base Index
`dsh-doc-index` is the local document index bundle for DeepSeek Harness, designed to enable semantic search over local documents. It supports Markdown, PDF, Office, and other formats, as well as Chinese word segmentation, through hybrid retrieval (BM25 + embedding vectors). The plugin supports incremental updates and precise line-number citations, and provides a command-line tool (such as `docindex query`) and a DSH service interface for model invocation. Installation requires Node.js 22.5+. By default, it uses a zero-dependency n-gram algorithm and can optionally use a Transformers model, with capacity limits and exclusion rules.
Read Moredsh-kb-rag: A Local-First RAG Knowledge Base Toolkit
The DSH plugin `yumu247/dsh-kb-rag` provides a local-first RAG knowledge base toolset for DSH, designed for zero-cost, local deployment. The plugin wraps four core commands: `kb_query` for semantic retrieval, `kb_ingest` for incremental ingestion, `kb_crawl` for web scraping using Scrapling, and `kb_related` for graph-based related recommendations. Before installation, ensure the host is configured with a Python environment, an Ollama model (such as `bge-m3`), and the `kb-rag` pipeline. During installation, specify the `kbRagDir` path, which the plugin relies on to run. When in use, `kb_query` returns results in JSON format, and `kb_inge
Read Moredsh-philosophy-terms: Philosophy Term Lookup Plugin
The DSH plugin `dsh-philosophy-terms` is designed to provide agents with knowledge of philosophical terms in local offline environments. Maintained by uckkk and implemented in pure Node.js, it has no network dependencies. Once installed and enabled, it registers two tools: `list_philosophy` for listing entries and `get_philosophy` for querying details by ID or name. It is suitable for scenarios requiring quick retrieval of philosophical terminology and for local deployment.
Read Moredsh-literature-terms: Local Literature Terms Retrieval Plugin
The `dsh-literature-terms` plugin for DeepSeek Harness (DSH) is designed to address the high cost and instability that agents face when relying on external APIs to handle literary terms. By encapsulating local data, it provides offline literary knowledge lookup. Core features include listing all terms and retrieving details for a single term. Once installed, the plugin automatically registers as a tool, supporting processing of literary text and explanation of concepts. Implemented entirely in Node.js, it has no network dependency at runtime and is suitable for building a lightweight literary knowledge base.
Read MoreDisney's 12 Animation Principles Knowledge Base
The DeepSeek Harness plugin **dsh-animation-principles**, maintained by uckkk, is a local tool designed to provide developers with a reference to Disney's 12 principles of animation. Implemented entirely in Node.js, the plugin runs without network access, ensuring privacy protection and offline availability. Users must install it via the command line and enable it in their profile configuration. Since the plugin runs with the permissions of the current process, developers are advised to review the source code before installation, enabling quick retrieval of the core principles of animation production in offline or privacy-sensitive scenarios.
Read MoreDeepSeek Harness Local Knowledge Base Plugin
modole/dsh-plugin-knowledge-laoboshi is a local knowledge base and document management plugin for DSH Agent. It originates from Laoboshi Agent Studio and primarily provides knowledge base management, retrieval, and document management capabilities. Installation requires running specific commands and restarting the service. This plugin is suitable for developers who need to provide local contextual memory for agents, but note that it runs with the current user's permissions, the source code should be reviewed before installation, and sensitive information should not be included in issues.
Read Moredsh-knowledge: DeepSeek Harness Local Knowledge Base and Experience Accumulation
The DeepSeek Harness (DSH) Knowledge Base plugin is a fully local, zero-dependency solution designed to address challenges in unstructured text retrieval and the loss of accumulated experience. Built on Node 24 built-in modules, it uses the FTS5 algorithm to support full-text search across Chinese text, code, and mixed content, and provides source attribution, preservation of conversational insights, web clipping, and knowledge graph visualization. Users can import documents with `kb_add`, clip web pages with `kb_add_url`, record experiences via `kb_remember`, and enforce source citations in responses. All data is stored in `~/.dsh/knowledge/kb.sqlite`. After installation, restart `dsh web` to apply changes. The plugin supports viewing a force-directed knowledge graph via a floating button in the bottom-right corner.
Read Moredsh-self-memory: A Local Offline Closed Loop for DSH Experience Memory
`dsh-self-memory` is a zero-dependency offline plugin developed for DeepSeek Harness (DSH), designed to address the problem of agents repeatedly explaining background context during debugging. It enables the automatic accumulation and reuse of experience by structurally recording issues, solutions, script paths, and model calls during sessions. The plugin provides core capabilities such as automatic retrieval and injection, external import, premise-aware retrieval, and generalized normalization. Users can retrieve history, record new solutions, mark hits or failures, and import data via the command line. Currently, it only supports keyword search, and storage performance may be limited with tens of thousands of records, but it can effectively reduce the cost of repetitive work for agents.
Read Moredsh-notebook-knowledge-studio: Run a NotebookLM-style local knowledge workbench in DSH Web UI
# Introduction Intelligent agent developers typically accumulate a wealth of materials locally: documents, scraped webpages, and pasted snippets. To use them for Q&A and organization, the common approach is to upload them to an online note-taking service and rely on its AI features—the trade-off being that the data leaves your local machine. If you are already using DeepSeek Harness (dsh) and agree with its "everything is a plugin" philosophy, you can actually mount a local-first knowledge workbench directly in the Web UI. The `iZY3/dsh-notebook-knowledge-studio` introduced below is exactly such a plugin: its workflow mimics NotebookLM, and data is stored in local Markdown files.
Read Moredsh-project-knowledge-review: A local knowledge review plugin for Chinese DSH users
dsh-project-knowledge-review is a local knowledge review plugin for Chinese DSH users, designed to store study materials, text, and audio transcriptions into a local library for review. Its core features include zero-config automatic creation of v2 storage, evidence-first Q&A, explicit refusal to answer when evidence is insufficient in strict mode, and automatic generation of Markdown summaries and two-level classification management. The plugin offers a sidebar knowledge base workspace, supports safe Markdown preview (without executing HTML/scripts), and is compatible with v1 legacy library migration. It requires no database or login after installation; OCR/ASR features are disabled by default and require explicit credential configuration to enable, and it only accepts public HTTP(S) URLs. Users can add materials via conversation, ask questions based on the knowledge base, or switch between reference/strict modes.
Read Moreobsidian-workbench: Browse, edit, and save Obsidian Markdown repositories in DeepSeek Harness
obsidian-workbench is a plugin maintained by Bob-Bo1 designed to allow Windows users to directly browse, edit, and save their local Obsidian Markdown vaults without leaving the DeepSeek Harness (DSH) Web session. This plugin does not require launching the Obsidian client; instead, by reading the vault path from the local Obsidian configuration, it provides an Obsidian-style three-column workspace within DSH: the left side displays the repository directory and files, the middle provides a CodeMirror 6-based Markdown real-time preview editor with auto-save support, and the right side displays the current DSH session, facilitating user interaction and questioning regarding the note content. Installation Process
Read Moredsh-plugin-dev-kb: Local Official Documentation for Developing dsh Plugins
dsh-plugin-dev-kb is an MIT-licensed plugin maintained by Pasumao, designed to provide a localized portable documentation library for DeepSeek Harness (DSH) plugin development. It does not register tools or generate runtime dependencies; instead, it organizes content from the official documentation site and unreleased development references within the repository into local files. The core content includes a 182-page bilingual (Chinese-English) mirror of the official documentation, 56 supplementary development references (such as glossaries and testing strategies), and a full-text search index and topic navigation covering 241 files. Through built-in skills, this plugin enables agents to automatically load the knowledge base during development tasks, locate documents based on `topics.md`, and read specific files on demand, ensuring that code generation is based on accurate documentation rather than speculation. Installation requires the use of the `dsh plugin` command.
Read More