Back to Home
cordlesssteve icon

layered-memory-mcp

Verified Safe

by cordlesssteve

Overview

A hierarchical, intelligent memory system for AI agents, specifically tailored for software engineering knowledge. It proactively manages, correlates, and evolves memories, offering advanced search, graph-based insights, and predictive analytics, while prioritizing security and compliance.

Installation

Run Command
node dist/src/index.js

Environment Variables

  • OPENAI_API_KEY
  • AUTH_SECRET
  • JWT_SECRET
  • NEO4J_URI
  • NEO4J_USER
  • NEO4J_PASSWORD
  • DATABASE_URL
  • REDIS_URL
  • LOG_LEVEL
  • NODE_ENV

Security Notes

The project demonstrates a robust and proactive approach to security. It includes comprehensive input validation using Zod and a custom `RequestValidator` with content sanitization to prevent XSS/injection attacks. Authentication is JWT-based with `bcrypt` for password hashing, and authorization uses RBAC with clear permission structures. Rate limiting is implemented for various operations. Critical environment variables like `AUTH_SECRET`/`JWT_SECRET` are explicitly checked in production, with the system designed to exit if not properly configured, preventing hardcoded production secrets. Default admin/user credentials ('admin123', 'user123') exist for initial setup in development environments but are hashed. Error handling is structured with recovery mechanisms and circuit breakers. External dependencies like Neo4j and FAISS are integrated with appropriate error handling. The extensive compliance documentation (`README`) reflects a strong security-first mindset.

Similar Servers

Stats

Interest Score0
Security Score10
Cost ClassHigh
Avg Tokens1000
Stars0
Forks0
Last Update2025-11-26

Tags

AI-memoryknowledge-basesemantic-searchgraph-databasesoftware-intelligencecomplianceobservabilitysecuritymulti-tenancydeveloper-toolsLLM-integration