what is zmem?
zmem is a TypeScript-based Model Context Protocol (MCP) server designed to manage project-specific and knowledge graph-based memory for Claude, LLM agents, and other tools. It enables the storage, retrieval, and management of entities, relations, and observations per project, focusing on flexibility and cross-project knowledge sharing.
how to use zmem?
To use zmem, you need to configure it in your MCP setup, install dependencies, build the project, and run it either in development or production mode. You can also use Docker for deployment.
key features of zmem?
- Knowledge graph storage for entities, relations, and observations
- CRUD operations via MCP tools
- Persistence to disk (memory.json)
- Docker and TypeScript support
use cases of zmem?
- Agents and LLMs that require structured memory storage and retrieval per project.
- Cross-project knowledge sharing and migration.
- Scalable, disk-persistent, and queryable memory for agent ecosystems.
FAQ from zmem?
- What is the primary function of zmem?
zmem serves as a memory server for managing project-specific data and knowledge graphs.
- Can zmem be used with Docker?
Yes! zmem supports Docker for easy deployment and management.
- How do I save observations in zmem?
You can save observations using the
save_project_observationstool via the MCP API.