codegraph
Run the following command in DeepSeek Harness:
dsh plugin install JohnXu22786/codegraph
Paste the following prompt into your AI chat to install this plugin:
To install the codegraph plugin in DeepSeek Harness, use the command 'dsh plugin install JohnXu22786/codegraph', with the full source code at https://github.com/JohnXu22786/codegraph.
About this plugin
Navigating large codebases and understanding dependency relationships can be daunting. The codegraph plugin parses code into a knowledge graph, giving agents the ability to query structural questions like call chains and impact analysis, making it easier to grasp complex structures quickly.
Its core capabilities include building call and dependency graphs, full-text search, impact analysis, and incremental indexing for efficient updates. With CLI and tool server interfaces, it integrates smoothly into development workflows or automated pipelines.
Ideal for developers working with complex code, AI agent builders, and teams assessing change risks. Whether for daily development, code reviews, or automated analysis, codegraph enhances efficiency and reduces risks by providing clear structural insights.
Use Cases
- Quickly understand the structure and dependencies of a new codebase
- Analyze the impact scope of code changes to assess risks
- Integrate into AI agents for intelligent code querying
Best For
- Software developers and code maintainers
- AI agent and automation tool developers
- Technical team leads for code reviews
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.