Optimized Memory
About
Integrates with SQLite to provide a persistent knowledge graph for efficient memory management and relationship modeling across conversations.
Details
- Author
- agentwong
- Repository
- AgentWong/optimized-memory-mcp-server
- GitHub stars
- 7
- Downloads
- 352
- License
- MIT License
- Categories
- Developer Tools, Design, File Management, AI, Community, Search, Communication, Knowledge Base, Frontend, Database
Jump to
- Persistent memory via local knowledge
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Optimized MemoryCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
@modelcontextprotocol/server-memory
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Add it to your Claude Desktop configuration (claude_desktop_config.json) using either Docker (docker run -i --rm mcp/memory) or NPX (npx -y @modelcontextprotocol/server-memory). Optionally, customize the included system prompt to control how memories are created and retrieved. The server can also be built locally with Docker.
create_entities
Create multiple new entities in the knowledge graph. Input: entities (array of objects) where each object contains name (string), entityType (string), and observations (string[]). Ignores entities with existing names.
create_relations
Create multiple new relations between entities. Input: relations (array of objects) where each object contains from (string), to (string), and relationType (string). Skips duplicate relations.
add_observations
Add new observations to existing entities. Input: observations (array of objects) where each object contains entityName (string) and contents (string[]). Returns added observations per entity. Fails if entity doesn't exist.
delete_entities
Remove entities and their relations. Input: entityNames (string[]). Cascading deletion of associated relations. Silent operation if entity doesn't exist.
delete_observations
Remove specific observations from entities. Input: deletions (array of objects) where each object contains entityName (string) and observations (string[]). Silent operation if observation doesn't exist.
delete_relations
Remove specific relations from the graph. Input: relations (array of objects) where each object contains from (string), to (string), and relationType (string). Silent operation if relation doesn't exist.
read_graph
Read the entire knowledge graph. No input required. Returns complete graph structure with all entities and relations.
search_nodes
Search for nodes based on query. Input: query (string). Searches across entity names, entity types, and observation content. Returns matching entities and their relations.
open_nodes
Retrieve specific nodes by name. Input: names (string[]). Returns requested entities and relations between requested entities. Silently skips non-existent nodes.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"optimized memory": {
"env": {},
"args": [
"-y",
"@modelcontextprotocol/server-memory"
],
"command": "npx"
}
}
}Linux
{
"env": [],
"args": [
"-y",
"@modelcontextprotocol/server-memory"
],
"command": "npx"
}Macos
{
"env": [],
"args": [
"-y",
"@modelcontextprotocol/server-memory"
],
"command": "npx"
}Windows
{
"env": [],
"args": [
"/c",
"npx",
"-y",
"@modelcontextprotocol/server-memory"
],
"command": "cmd"
}optimized-memory-mcp-server
This is to test and demonstrate Claude AI's coding abilities, as well as good AI workflows and prompt design.
This is a fork of a Python Memory MCP Server (I believe the official one is in Java) which uses SQLite for a backend.
Knowledge Graph Memory Server
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.Core Concepts
Entities
Entities are the primary nodes in the knowledge graph. Each entity has: - A unique name (identifier) - An entity type (e.g., "person", "organization", "event") - A list of observationsSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
