dsh-plugin-knowledge-graph
Run the following command in DeepSeek Harness:
dsh plugin install Luke-Yong/dsh-plugin-knowledge-graph
Paste the following prompt into your AI chat to install this plugin:
In DeepSeek Harness, install this plugin using the command 'dsh plugin install Luke-Yong/dsh-plugin-knowledge-graph', with the full source repository at https://github.com/Luke-Yong/dsh-plugin-knowledge-graph.
About this plugin
In modern software development, codebases are often large and complex, making it challenging for developers or AI agents to quickly understand and analyze code structure. Traditional methods like grep or manually reading files are not only time-consuming but also fail to provide a comprehensive view of interdependencies. The dsh-plugin-knowledge-graph addresses this issue by leveraging a knowledge graph approach.
This plugin builds an in-memory knowledge graph that automatically tracks every file, directory, exported symbol, and their relationships within the codebase. It exposes a powerful read_graph tool that enables agents to perform various queries, such as retrieving directory structures, listing exported symbols, analyzing import relationships, and identifying unused imports. The graph model utilizes three node types (dir, file, symbol) and four edge types (CONTAINS, EXPORTS, IMPORTS, IMPORTS_SYMBOL), ensuring precise and efficient querying.
Ideal for developers, AI engineers, or anyone using DeepSeek Harness who needs automated code analysis, this plugin serves as an essential assistant. It not only accelerates the code comprehension process but also empowers agents to make smarter decisions, ultimately boosting development efficiency and code quality.
Use Cases
- Quickly browsing the directory structure and file relationships in large codebases
- Automatically detecting unused imports or finding where symbols are exported
- Providing AI agents with code dependency information to assist refactoring or debugging
Best For
- Developers using DeepSeek Harness for code-related tasks
- AI engineers or researchers needing automated codebase analysis
- Software engineers maintaining complex projects and concerned with code quality and dependencies
Related Plugins
Traceable, searchable cross-session memory for AI agents that turns conversation knowledge into a typed knowledge graph and recalls relevant subgraphs instead of replaying full history, natively integrated with DeepSeek Harness.
Gives DSH AI cross-session long-term memory, to-do and skill management, plus multi-session orchestration, external AI delegation, and an infinite canvas that grows with you.
dsh-mnemon is a three-tier, pluggable, Agent-driven memory system for DeepSeek Harness, combining Runtime memory, Project Documents, and replaceable Memory Spaces with nine long-term providers.
An opinionated, zero-infrastructure file-based memory protocol: human-readable markdown files plus a bounded always-loaded index, curation discipline, and no database or embeddings.