edobez/mcp-memory-py
If you are the rightful owner of mcp-memory-py and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A basic implementation of persistent memory using a local knowledge graph, allowing Claude to remember information about the user across chats.
The Knowledge Graph Memory Server is a Python port of the original reference server, designed to provide persistent memory capabilities using a local knowledge graph. This server allows for the creation, management, and querying of entities, relations, and observations, enabling a system to remember user information across different interactions. The server supports various operations such as creating entities and relations, adding and deleting observations, and reading the entire graph structure. It is particularly useful for applications requiring memory persistence, such as chatbots and virtual assistants, where maintaining context over multiple sessions is crucial. The server is designed to be integrated with platforms like Claude Desktop, providing a seamless experience for developers looking to implement memory features in their applications.
Features
- Entity Management: Create, delete, and manage entities with unique identifiers and associated observations.
- Relation Management: Define and manage directed connections between entities, stored in active voice.
- Observation Handling: Add, remove, and manage discrete pieces of information about entities.
- Graph Querying: Search and retrieve nodes and their relations based on various criteria.
- Integration Support: Easily integrate with platforms like Claude Desktop for enhanced memory capabilities.
Usages
uvx with Claude Desktop
{
"mcpServers": {
"memory-python":
{
"command": "uvx",
"args": [
"--refresh",
"--quiet",
"mcp-memory-py"
],
"env": {
"MEMORY_FILE_PATH": "/path/to/custom/memory.json"
}
}
}
