kuzu-memory
Verified Safeby 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
python -m kuzu_memory.mcp.run_serverEnvironment 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
mcp-memory-service
Provides a persistent, semantic memory system for AI agents, enabling them to store, retrieve, process (consolidation, reasoning), and manage information by acting as an external knowledge base.
memory-graph
A graph-based MCP server that provides intelligent memory capabilities for Claude Code, enabling persistent knowledge tracking, relationship mapping, and contextual development assistance.
memory-mcp-server-go
Provides a persistent knowledge graph server for LLMs to manage and retrieve entities, relations, and observations, acting as long-term memory across conversations.
context-sync
Context Sync provides AI systems with persistent, queryable memory across all development tools, sessions, and projects, allowing AI to remember codebase details, architectural decisions, and conversation history.