SourceSage
Caches a codebase as a graph to provide LLMs with efficient code memory.
About
SourceSage is an MCP server designed to efficiently memorize key aspects of a codebase—logic, style, and standards—while allowing dynamic updates and fast retrieval. It leverages the LLM's understanding of code across multiple languages to analyze code files, register entities and relationships, and store this knowledge in a token-efficient graph structure. This allows LLMs to later query this knowledge when needed, enabling more informed and context-aware code analysis and generation.
Key Features
- LLM-Driven Analysis: Relies on the LLM to analyze code and provide insights
- 0 GitHub stars
- Knowledge Graph Storage: Efficiently stores code entities, relationships, patterns, and style conventions
- Incremental Updates: Updates knowledge when code changes without redundant storage
- Language Agnostic: Works with any programming language the LLM understands
- Token-Efficient Storage: Optimizes for minimal token usage while maximizing memory capacity
Use Cases
- Enabling more informed and context-aware code analysis and generation
- Querying the knowledge graph for code details
- Analyzing code files to register entities and relationships
Sponsored