AI Agent Hub
Back to plugins
🧠

dsh-plugin-knowledge-graph

Memory Updated 2026.08.17

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