知识点关联图：用 Agent Skill 把零散概念收成文字版知识图谱
SkillHub 社区 Skill「知识点关联图」（@user_70c2f807/knowledge-connection-map，v1.0.1）面向知识管理场景，在用户给出主题或概念后，按 SKILL.md 流程分析层级、因果、并列与对比关系，输出缩进与符号构成的文字版图谱、关系说明与学习路径。无需 API Key。安装需 skillhub CLI 并将包放入 Agent 的 skills 目录。适合复习与体系化梳理，不适合替代教材、百科查询或直接生成可视化导图图片。
Read Moreontology：用类型化知识图为 Agent 做结构化记忆
ontology（@user_b634fbfe/002，v1.0.4）是 SkillHub 社区 ai-agent 类 Skill，用带类型的知识图组织 Agent 记忆与可组合 Skill 的共享状态。支持 Person、Project、Task、Event、Document 等实体的创建与查询、对象关联、约束校验，并将多步动作表达为图变换，适用于 remember、查已知信息、link 依赖与跨 Skill 数据访问等场景。无需 API Key。可通过 SkillHub 安装文档用 CLI 或提示词安装到 Cursor、Claude Code、Codex 等对应 skills 目录。
Read More九天-知识图谱（含知识卡片）：把概念做成 HTML 图谱与卡片
九天-知识图谱（含知识卡片）是 SkillHub 社区技能（v1.0.1，knowledge-management），无需 API Key。它将用户提供的主题或内容检索整合后，生成 17 种模板（8 卡片+9 图谱）的 HTML 知识卡片或图谱，支持手机紧凑版与桌面版，具备关系抽取与节点建模，可浏览器打开、截图或 PNG 导出。通过「知识图谱」「一页纸总结」「做成卡片」等自然语言即可触发。文章说明安装命令、典型对话用法及与长文报告、纯图表场景的边界。
Read More即作记忆：创作记忆、设定与知识图谱查询
即作记忆插件是 DeepSeek Harness Desktop 的创作辅助插件，旨在解决小说与视频创作者管理记忆、设定及知识图谱的痛点。它提供统一工作区、知识图谱查询、媒体模型配置、浏览器登录账号模型及视频导出功能。安装需特定版本并支持命令行或页面方式。使用时需手动安装 FFmpeg 等系统依赖，且媒体服务可能产生计费。该插件不提供旧章节工作流。
Read More通用知识图谱构建器：把文档目录变成可交互的知识图谱页面
介绍 SkillHub 社区 Skill「通用知识图谱构建器」（@user_19a6d235/knowledge-graph-builder v1.0.6）：在 Agent 中完成环境检查、文档分析、graphifyy 抽取与生成本地可打开的 D3 知识图谱页面。说明 OpenAI 兼容 API 配置、skillhub 安装路径、典型对话流程与增量更新，并列出 requires_api_key 与 Python 依赖等注意事项。
Read More知识图谱可视化生成专家：把主题与文档变成可交互 HTML 图谱
知识图谱可视化生成专家是 SkillHub 社区 Skill（@user_52a81e7a/knowledge-graph-pro，v1.2.5），无需 API Key。输入主题词或 Markdown，输出可交互 HTML 知识图谱，支持力导向与辐射状布局及 4 套主题。适合梳理概念关系、把文档做成关系网。安装时让 Agent 按 skillhub.md 安装上述坐标；触发词含知识图谱、关系图谱、HTML 图谱等。
Read More长期记忆 / 知识图谱 会思考的进化 AI：为 Agent 搭统一记忆底座
SkillHub 社区 Skill「长期记忆 / 知识图谱 会思考的进化 AI」（@user_1a470ba8/zwjh-skill，v2.6.0）面向 AI Agent，提供跨会话长期记忆、实体关系图谱、自动沉淀，以及语义与时间线检索、记忆健康度审计和本地备份（可接百度网盘）。标注 requires_api_key=false，强调纯本地与零密钥。文章说明其解决上下文断裂的痛点，列出官方核实功能，并给出基于 skillhub CLI 在 Cursor、Claude Code、Codex 等目录下的安装命令与 SkillHub 安装文档链接。
Read Moredsh-plugin-graphify-watch：为每个项目自动重建 Graphify 知识图谱
`dsh-plugin-graphify-watch` 专为解决 DeepSeek Harness（DSH）中代码修改后图谱不同步的问题设计。该插件通过接管 `graphify watch` 的进程生命周期，实现自动启动、崩溃恢复及资源清理。它支持代码变更触发图谱重建，文档变更则生成标记提示手动更新，确保插件零依赖且兼容性良好，需通过 DSH 应用程序安装并配置项目路径。
Read Morememory-systems: A Design Guide for Agent Persistent Memory and Retrieval Architectures
memory-systems is the Memory System Design guide in the Agent Skills for Context Engineering collection, covering cross-session semantic memory, entity consistency, temporal validity, graph/vector and hybrid retrieval, and memory consolidation. The article explains its positioning, activation boundaries, memory hierarchy and framework selection table, and principles for consolidation and JIT loading. It also provides official examples using Mem0, temporal graphs, and Cognee, along with loading methods via Claude Code and npx skills, emphasizing starting with a shallow design, validating it with LoCoMo/LongMemEval, and then deepening the architecture.
Read More@lovedolove/dsh-codebase-memory-mcp
`@lovedolove/dsh-codebase-memory-mcp` is a DeepSeek Harness plugin designed to enhance an agent's deep understanding of codebases using knowledge graphs, under the philosophy that “everything is a plugin.” It injects the capabilities of `codebase-memory-mcp` into the DSH toolchain, automatically starts the backend service and visualization interface, and registers six tools—including symbol search, call-chain tracing, and architecture overview—as well as the `/cbm` status check command. Before installation, ensure the environment meets the requirements and that the required executable files are preinstalled. After installation, the agent can efficiently invoke the graph-based tools as an alternative to traditional search.
Read Moredsh-plugin-sirchmunk: Native DSH Sirchmunk Configuration and Monitoring Plugin
The native Web plugin `dsh-plugin-sirchmunk` for DeepSeek Harness (DSH), built on the core design philosophy of “everything is a plugin,” introduces a centralized management area named Sirchmunk into the DSH settings interface. It primarily provides knowledge graph visualization and export, cluster management (including permission control), runtime monitoring, shared history tracking, and de-identification of privacy data. In addition, it includes a built-in Agent Skill named `sirchmunk-search`, which supports searching local documents in over 100 formats via MCP tools. Implemented using a Host/Client architecture, the plugin relies on a local Sirchmunk service and takes effect after restarting the DSH host once installed.
Read Morexby-ancient-poetry-kg: Ancient Poetry Knowledge Graph Plugin
The `xby-ancient-poetry-kg` plugin by DSH aims to provide agents with structured knowledge retrieval capabilities in the domain of classical Chinese poetry. Built on knowledge graph technology, it covers data such as poem titles, authors, and dynasties, helping address the challenges models face when handling complex entity relationships. Core capabilities include setting a persistent API key, retrieving the graph schema, and executing Cypher queries. Developers must first register on the official website to obtain an API key and install the plugin via GitHub, after which they can use tools such as `set_xby_apikey`, `get_schema`, and `execute_read_cypher` to read and interact with graph data.
Read Moredsh-plugin-memory: DeepSeek Harness Long-Term Memory and Knowledge Graph Plugin
dsh-plugin-memory is a plugin for DeepSeek Harness (dsh) designed to address the lack of long-term memory in AI agents. It uses a persistent knowledge graph to store user preferences, facts, and coding conventions across sessions, and supports both semantic and keyword-based retrieval. The plugin offers CLI management and native integration with the Cordis framework, automatically exposing memory read/write tools to agents. Through simple commands or API calls, users can build user profiles and historical knowledge bases for agents, enabling consistent context across multi-turn conversations.
Read Moredsh-industry-graph-mcp: Zero-Dependency A-Share Industry Chain Knowledge Graph
`dsh-industry-graph-mcp` is a Node.js-based A-share knowledge graph MCP server. It provides 7 local tools for querying individual stock industries, industrial chain positions, peer competitors, and concept constituents. With zero dependencies and no API required, the plugin uses a local graph service to provide Agents with factual grounding for quantitative investment research, supporting seamless integration into DeepSeek Harness.
Read Morexby-traditional-chinese-medicine-kg: DeepSeek Harness Traditional Chinese Medicine Knowledge Graph Plugin
`xby-traditional-chinese-medicine-kg` is a DeepSeek Harness (DSH) plugin for traditional Chinese medicine (TCM). It stores knowledge of Chinese herbal medicine in a graph database and enables developers to execute Cypher queries. After installation, users must configure an API key in DSH and use tools such as `get_schema` and `execute_read_cypher` to connect to the database and perform read-only queries. The plugin relies on an external graph database service and is currently intended mainly for preliminary research, providing interface support for scenarios that require structured reasoning over TCM knowledge.
Read Morexby-traditional-chinese-medicine-formulas-kG: TCM Formula Knowledge Graph Plugin
xby-traditional-chinese-medicine-formulas-kG is a memory plugin in DeepSeek Harness (DSH) designed to transform unstructured data in traditional Chinese medicine, such as formulas and herbal medicines, into a structured knowledge graph, enabling agents to perform domain-specific querying and reasoning. It provides core functions including API key setup, graph schema retrieval, and execution of Cypher read queries. Users must first register to obtain and configure the API key, then use `execute_read_cypher` for data retrieval. The plugin is open source and easy to install, allowing developers to quickly integrate with a traditional Chinese medicine knowledge base.
Read Moredsh-hindsight: Hindsight Memory Bridging Plugin for DeepSeek Harness
dsh-hindsight is an official-grade plugin maintained by Ryu6Zero, designed to provide cross-session memory capabilities for stateless DeepSeek Harness Agents. It does not rely on heavy orchestration layers and functions solely as a standalone HTTP client bridging to the Hindsight REST API. The plugin supports memory retrieval, knowledge graph traversal, proactive memory prompting, and asynchronous operation monitoring via slash commands and six model tools. It features hot configuration, batch deduplication, recall caching, and other capabilities, enabling Agents to access long-term memory and associated decisions, making it ideal for developers who want to add lightweight long-term memory functionality to DSH Agents.
Read Moredsh-codebase-memory-mcp: DeepSeek Harness Codebase Memory Connector Plugin
`dsh-codebase-memory-mcp` is a DeepSeek Harness (DSH) plugin designed to bridge the local `codebase-memory-mcp` knowledge graph service into the DSH environment. It reuses DSH's built-in bridging layer, registers 14 MCP tools and two host-level monitoring tools, and supports configuring server paths, environment variables, and more. Users can check the status via `codebase_memory_status` and, in case of errors, fix the configuration or restart the service. This plugin depends on `@deepseek-ai/dsh-mcp-client` and includes robust error handling, seamlessly integrating code memory capabilities into agent or code review tasks.
Read MoreIntroduction to the dsh-ontology-kernel Plugin
dsh-ontology-kernel is a client plugin in the DeepSeek Harness ecosystem, designed to address historical version control and source code archiving for ontology data in agent development. The plugin is maintained by aiko-dsh-plugins; current active development takes place in the `dsh-ontology-kernel-source` repository, while this repository only provides historical source code and release versions. Before adopting the plugin, users should review the source code and license to ensure compliance.
Read Moredsh-knowledge-graph: Visualizing DSH Plugins and Call Traces
The DeepSeek Harness plugin aims to address the challenge of disorganized plugin management in AI environments through graph visualization. Its core features include: a force-directed graph providing a global view and dependencies of plugins, skills, and tools; bubble highlights visualizing the reasoning process and tool-call trace for each conversation turn; a list view for precise search and filtering; and statistics on usage frequency and health status (such as loading failures) with Markdown report export. The plugin runs fully offline and persists data in local files, helping users clean up unused plugins and optimize their environment configuration.
Read MoreDSH Research Graph: DeepSeek Harness Research Workbench Plugin
The DeepSeek Harness Research Graph plugin aims to address the pain points of scattered AI chat logs, difficulty in structuring them, and challenges in tracing their sources, guided by the “everything is a plugin” philosophy. It offers features such as visualized research graphs, source tracing, knowledge capture, AI analysis, and export, helping developers efficiently organize research topics, iterate on knowledge, and manage research deliverables. Installation requires a specific Node.js version, and data is stored on the DSH Host.
Read Moredsh-ontology: A Typed Ontology Memory Plugin for DeepSeek Harness
dsh-ontology is a structured knowledge framework plugin for DeepSeek Harness, designed to address fragmentation and inconsistencies in agent textual memory. It includes a TBox (schema definitions) and an ABox (fact assertions), supporting schema-constraint-based validation, automatic inference (e.g., transitivity and symmetry), and dependency-aware retraction. The plugin enables agents to define classes, relations, and assert facts, upgrading bag-of-texts memory into a controlled, reliable knowledge graph, suitable for scenarios that require handling complex dependencies.
Read Moredsh-memory-graph: Local Knowledge Graph and Long-Term Memory Plugin for DSH
`dsh-memory-graph` is a localized, non-intrusive plugin designed for DeepSeek Harness that provides long-term memory and temporal knowledge graph capabilities. The SQLite-based plugin supports Chinese retrieval, hybrid relevance recall, and per-turn control, helping keep the graph maintainable and efficient across long conversations. Installation is simple and can be enabled by linking a local checkout, while the DSH Web interface supports visual inspection and management. Uninstallation only removes configuration and does not delete local databases or backup files, making it suitable for developers who need auditable, maintainable persistent storage.
Read Moredsh-hypatia: A DeepSeek Harness Memory Plugin Based on the Hypatia Knowledge Graph
`dsh-hypatia` is a memory plugin for DeepSeek Harness (DSH) that leverages the Hypatia knowledge graph to provide models with long-term memory. The plugin runs the Hypatia CLI as a host process, handling complexities such as database orchestration within the plugin, while the model focuses solely on memory proposals. Its core features include recall within the same request, precise project scoping, verified writes, two-stage forgetting, and session support without Bash. Installation requires Hypatia CLI 0.1.4 and Node.js 22.5+, and can be completed via the command line. Configuration supports multiple memory presets, authorization, and recall strategies. The plugin provides tools for memory storage, retrieval, forgetting, and knowledge graph queries, but has a single-process limitation and version requirements.
Read MoreIntroducing the DSH Plugin: satan9394/dsh-knowledge-brain
`dsh-knowledge-brain` is a plugin in the DeepSeek Harness ecosystem focused on long-term memory, designed to address the high cost and high latency of traditional solutions. It can build self-connecting knowledge graphs without invoking an LLM, and offers core features such as answer citation for synthesized responses, gap analysis, data isolation, and continuous operation. The plugin is suitable for enterprise scenarios that require a stable memory layer and knowledge association; its source code security should be carefully reviewed before installation.
Read Moredsh-kgraph-plugin: Project Knowledge Graph Visualization Plugin
dsh-kgraph-plugin is a read-only bundle plugin for DeepSeek Harness, designed to help developers quickly understand the architecture, dependencies, and layered design of complex projects by automatically generating module-level and file-level knowledge graphs. It supports multiple languages (Java, TypeScript, Python, Go, etc.) and multi-module recognition, providing a visual dashboard and the `project_kgraph` tool to help users refactor and optimize code more efficiently. After installation, users can simply input a project path to scan it and view the module dependency graph and file-level layered structure, without modifying the source code at any stage.
Read Moredsh-obsidian: Connecting Local Projects to Obsidian's Knowledge Graph
`dsh-obsidian` is a standalone plugin intended to address Obsidian's inability to directly scan code repositories. It uses DSH to scan local project metadata, generate corresponding notes and graph edges, and automatically surface knowledge associations between projects. Core features include native DSH integration, local project scanning, deterministic knowledge graph generation, dual transport modes, and incremental writes. After installation, users can configure environment variables, run scanning and graph generation in DSH, and view associations in Obsidian's graph view. The plugin runs entirely offline, is secure, does not affect manual notes, and does not require an additional REST plugin for basic functionality.
Read Moredsh-understand-anything: A DeepSeek Harness Plugin for Generating Codebase Knowledge Graphs
`dsh-understand-anything` is the codebase analysis plugin for DeepSeek Harness. By generating structured knowledge graphs, it addresses the issues of traditional RAG consuming excessive amounts of tokens and easily losing architectural details. The plugin supports architecture understanding, change impact analysis, onboarding guides, and multi-domain extraction without requiring raw files to be stuffed into the context. Installation requires Node.js ≥ 22 and pnpm ≥ 10. Please note that, due to plugin compatibility limitations, Web applications, Claude Code–specific features, and the analysis engine have not been translated.
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 MoreImplementing Traceable Knowledge Graph Memory for DeepSeek Harness with graph-memory
Graph-memory is a DSH memory-type plugin maintained by adoresever, which extracts dialogues into TASK/SKILL/EVENT knowledge graphs, supporting cross-session semantic recall and local SQLite storage. This article introduces its core capabilities, directory page installation commands, source tarball installation steps, gm_* tools and vector retrieval configuration, as well as the plugin permissions, beta version, and the application boundaries of the 75% context compression benchmark.
Read MoreUsing memtrace-public to add codebase structure memory to DeepSeek Harness
# memtrace-public This codebase is compiled into a structured knowledge graph that supports millisecond-level queries, covering functions, classes, call edges and versions, for DeepSeek Harness to use across sessions without repeatedly reading files. Maintained by syncable-dev, the community repository is categorized under the "Memory" category, and it had 454 stars as of August 18, 2026. The indexing is implemented via local Rust + Tree-sitter; the Harness plugin package `dsh-plugin-memtrace` is licensed under MIT, while the core indexer is under a proprietary EULA and is currently in private beta. This article cross-checks the installation commands, MCP tools, Skills, licenses and telemetry boundaries against the GitHub repository page.
Read MoreUsing Graph-Memory to Equip DeepSeek Harness with Traceable Knowledge Graph Memory
Graph-memory is an MIT-licensed open-source memory plugin maintained by adoresever. It extracts conversations into TASK/SKILL/EVENT triples and uses SQLite knowledge graphs for cross-session recall. The community installation command is `dsh plugin add github:adoresever/graph-memory`. The current version 1.6.0-beta.1 has not been published on npm yet, and the DSH acceptance path in the README uses a local tarball. About 75% of the compression comes from the limited workflow comparison, which is not a universal guarantee. The Pro visualization feature has not been delivered yet.
Read MoreAdd persistent memory to DeepSeek Harness agent using mnemon
Mnemon is a persistent memory for LLM supervised agents maintained by mnemon-dev: it uses local SQLite four-graph storage, the host model determines what to remember, and the binary is responsible for indexing and recall. The community directory categorizes it under "Memory" and marks it as featured. This article verifies the installation commands, DSH configuration entry, CLI usage, and the relationship with dsh-mnemon according to the directory page and GitHub.
Read MoreGraphify: Convert code bases, documents and SQL into queryable knowledge graphs to replace traditional vector RAG
Graphify, which has been consistently ranking on GitHub Trending in early August 2026, allows users to build locally queryable knowledge graphs from code, documents, SQL schemas, PDFs and more via the /graphify Skill. It uses tree-sitter AST for deterministic parsing at the code layer and does not rely on vector databases. The edges are labeled EXTRACTED/INFERRED for interpretability. This article introduces its differences compared to vector RAG, the steps to install and integrate it with Claude Code/Cursor, as well as its query, path and explain usages.
Read MoreGraphify: An Agent Skill for Translating Code Repositories, Documents and Schemas into Queryable Knowledge Graphs
Graphify, which trended on GitHub Trending in early August 2026, constructs queryable knowledge graphs from code, documents, SQL schemas, PDFs and more via local AST powered by tree-sitter and Leiden community detection, and integrates with Agent tools including Claude Code, Cursor and Codex through the `/graphify Skill`. This article verifies its Trending background and official capability boundaries, makes a comparison with vector RAG, and provides hands-on steps for installation via uv, Skill registration and querying via query/path/explain, to assist with context engineering选型 in large codebase scenarios.
Read MoreMCP Server codebase-memory-mcp: Enabling AI Agents to Truly "Remember" Your Codebase
In July 2026, the GitHub Trending hot project codebase-memory-mcp (produced by DeusData) indexes codebases into persistent knowledge graphs via the MCP protocol. It supports parsing 158 programming languages and provides 15 MCP tools, enabling agents such as Claude Code and Cursor to replace file-by-file exploration with structured queries. According to official benchmark tests, the token consumption for structural queries can be reduced by about 120 times, and indexing for Linux kernel-level repositories can be completed in approximately 3 minutes. This article introduces its Hybrid LSP semantic enhancement, core tools, installation method and applicable scenarios.
Read More