Back to Home
bobmatnyc icon

kuzu-memory

Verified Safe

by bobmatnyc

Overview

KuzuMemory is a lightweight, embedded graph-based memory system designed to provide fast, offline contextual memory and knowledge retrieval for AI applications and agents, primarily through pattern matching without direct LLM API calls. It enhances prompts, stores learning, and manages project context.

Installation

Run Command
python -m kuzu_memory.mcp.run_server

Environment Variables

  • KUZU_MEMORY_DB
  • KUZU_HOOK_LOG_DIR
  • KUZU_CLI_PATH
  • CLAUDE_CONFIG_DIR
  • CLAUDE_GLOBAL_CONFIG_PATH

Security Notes

The server heavily leverages `subprocess` for core functionalities such as interacting with the Git CLI for synchronization, optionally using the Kuzu CLI adapter for database operations, and for its self-update mechanism (via the vendored `py-mcp-installer-service`). While extensive use of subprocess can introduce risks, the implementation appears to handle commands with explicit arguments and includes error handling and timeouts. No direct execution of arbitrary user input via `eval` or similar dangerous patterns was found. The system relies on environment variables (e.g., KUZU_MEMORY_DB) for sensitive paths, mitigating hardcoded secrets. The primary security considerations would be the integrity of external tools (`git`, `kuzu`) and the execution environment.

Similar Servers

Stats

Interest Score39
Security Score8
Cost ClassLow
Stars12
Forks1
Last Update2026-01-17

Tags

AI memoryGraph databaseKuzuDBContext managementOfflineAgent memoryJSON-RPCMCP ServerNLPSelf-update