Vibe Coding Discovermemento-mcp
View on GitHubMemento MCP: A Knowledge Graph Memory System for LLMs
Memento MCP is a TypeScript MCP server that gives LLM clients (Claude Desktop, Cursor, Copilot) persistent long-term memory backed by Neo4j. It offers a versioned knowledge graph of entities and relations with vector semantic search, point-in-time history, and time-based confidence decay.
Use Cases
Give Claude Desktop/Cursor persistent long-term memory across sessionsStore entities and relations as a queryable knowledge graphSemantic retrieval of past context via vector embeddingsPoint-in-time queries over how knowledge evolvedConfidence decay for stale relationsHybrid keyword + vector search over agent memoryFeed structured ontological context to any MCP-capable LLM client
Built With
- Language
- TypeScript
- Frameworks
- Model Context Protocol SDK · Neo4j Driver · OpenAI Node SDK · Vitest · TypeScript · ESLint · Prettier · Docker Compose · Smithery
Tags
mcp · knowledge-graph · memory · llm-memory · neo4j · vector-search · semantic-search · embeddings · temporal-awareness · claude-desktop · cursor · typescript · long-term-memory · graph-database · context-management