Nova-LLM-mCP-memory-system
Verified Safeby For-Sunny
Overview
Production-grade GPU-accelerated vector memory for AI applications, providing secure and high-performance vector search.
Installation
npm startEnvironment Variables
- TETHER_HOST
- TETHER_PORT
- TETHER_SECRET
- SOCKET_TIMEOUT
- MAX_TIMESTAMP_DRIFT
- DEBUG
Security Notes
Implements robust HMAC-SHA256 authentication for communication, replay protection via timestamp validation (MAX_TIMESTAMP_DRIFT), and input validation with Zod schemas. Error responses are sanitized (stack traces are suppressed). Relies on a securely generated 'TETHER_SECRET' environment variable for authentication, which is critical for preventing unauthorized access to the underlying Faiss tether. Communication with the Python tether is via TCP socket, making network security important.
Similar Servers
hyper-mcp
A fast, secure Model Context Protocol (MCP) server that extends its capabilities through WebAssembly plugins, enabling AI features in applications like Claude Desktop and Cursor IDE. It provides a flexible runtime for tools, resources, and prompts implemented in various languages.
memorizer-v1
A .NET-based service enabling AI agents to store, retrieve, and semantically search through long-term memories using vector embeddings in PostgreSQL, integrated with a web UI and Model Context Protocol (MCP).
local_faiss_mcp
Provides a local FAISS-based vector database as an MCP server for Retrieval-Augmented Generation (RAG) applications, enabling document ingestion, semantic search, and prompt generation.
post-cortex
Transforms ephemeral AI conversations into persistent, searchable knowledge for AI assistants, enabling memory across sessions with semantic search and automatic knowledge graph construction.