MCPFast / Tools / Persistent knowledge graph for Claude Code
A knowledge graph for Claude Code enabling persistent memory and auto-compaction, improving context retention across sessions.
View on GitHub→This tool provides a persistent knowledge graph for Claude Code, enhancing its ability to retain context across sessions. By implementing a knowledge graph, Claude Code can build and access a structured representation of information, leading to more consistent and informed interactions. This is particularly beneficial for complex development tasks where maintaining a deep understanding of project history and dependencies is crucial.
The Persistent Knowledge Graph for Claude Code acts as an external memory system. It allows Claude Code to store and retrieve information in a structured, graph-based format. This means that instead of relying solely on the immediate conversation history, Claude Code can access a persistent repository of knowledge. The tool also incorporates auto-compaction mechanisms to manage the size and relevance of the knowledge graph, ensuring efficient performance and preventing information overload.
This tool is intended for developers and AI engineers who are leveraging Claude Code for complex projects. It is especially valuable for those working on applications that require long-term memory, such as: