Knowledge Graph Memory Server
About
Enables persistent memory for Claude using a local knowledge graph of entities, relations, and observations.
Details
- Author
- yodakeisuke
- Categories
- Developer Tools, Knowledge Base, AI
Jump to
Setup
Install Knowledge Graph Memory Server in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/yodakeisuke/mcp-memory-domain-knowledge
Follow the installation instructions in the repository README, then restart your MCP client.
Enables persistent memory for Claude using a local knowledge graph of entities, relations, and observations.
forkedhttps://github.com/modelcontextprotocol/servers/tree/main
A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats.
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 observations
{ "name": "John_Smith", "entityType": "person", "observations": ["Speaks fluent Spanish"] }
Relations define directed connections between entities. They are always stored in active voice and describe how entities interact or relate to each other.
{ "from": "John_Smith", "to": "Anthropic", "relationType": "works_at" }
Observations are discrete pieces of information about an entity. They are:
- Stored as strings
- Attached to specific entities
- Can be added or removed independently
- Should be atomic (one fact per observation)
{ "entityName": "John_Smith", "observations": [ "Speaks fluent Spanish", "Graduated in 2019", "Prefers morning meetings" ] }
- Create multiple new entities in the knowledge graph
- Input:entities(array of objects)
- Each object contains:
- name(string): Entity identifier
- entityType(string): Type classification
- observations(string[]): Associated observations
- Create multiple new relations between entities
- Input:relations(array of objects)
- Each object contains:
- from(string): Source entity name
- to(string): Target entity name
- relationType(string): Relationship type in active voice
- Add new observations to existing entities
- Input:observations(array of objects)
- Each object contains:
- entityName(string): Target entity
- contents(string[]): New observations to add
- Remove entities and their relations
- Input:entityNames(string[])
- Cascading deletion of associated relations
- Silent operation if entity doesn't exist
- Remove specific observations from entities
- Input:deletions(array of objects)
- Each object contains:
- entityName(string): Target entity
- observations(string[]): Observations to remove
- Remove specific relations from the graph
- Input:relations(array of objects)
- Each object contains:
- from(string): Source entity name
- to(string): Target entity name
- relationType(string): Relationship type
- Read the entire knowledge graph
- No input required
- Returns complete graph structure with all entities and relations
- Search for nodes based on one or more keywords
- Input:query(string)
- Space-separated keywords (e.g., "budget utility")
- Multiple keywords are treated as OR conditions
- Entity names
- Entity types
- Subdomains
- Observation content
- Case-insensitive
- Partial word matching
- Any keyword can match any field
- Returns entities matching ANY of the keywords
- Single keyword: "budget"
- Multiple keywords: "budget utility"
- With special chars: "budget & utility"
- Retrieve specific nodes by name
- Input:names(string[])
- Returns:
- Requested entities
- Relations between requested entities
Add this to your claude_desktop_config.json:
{ "mcpServers": { "memory": { "command": "docker", "args": ["run", "-i", "--rm", "mcp/memory"] } } }
{ "mcpServers": { "memory": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-memory" ] } } }
The server can be configured using the following environment variables:
{ "mcpServers": { "memory": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-memory" ], "env": { "MEMORY_FILE_PATH": "/path/to/custom/memory.json" } } } }
- MEMORY_FILE_PATH: Path to the memory storage JSON file (default:memory.jsonin the server directory)
The prompt for utilizing memory depends on the use case. Changing the prompt will help the model determine the frequency and types of memories created.
Here is an example prompt for chat personalization. You could use this prompt in the "Custom Instructions" field of aClaude.ai Project.
Follow these steps for each interaction: 1. User Identification: - You should assume that you are interacting with default_user - If you have not identified default_user, proactively try to do so. 2. Memory Retrieval: - Always begin your chat by saying only "Remembering..." and retrieve all relevant information from your knowledge graph - Always refer to your knowledge graph as your "memory" - When searching your memory, you can use multiple keywords to find related information - Example searches: Single concept: "programming" Related concepts: "programming python" * Specific domain with role: "work engineer" 3. Memory Creation: - While conversing with the user, be attentive to any new information that falls into these categories: a) Basic Identity (age, gender, location, job title, education level, etc.) b) Behaviors (interests, habits, etc.) c) Preferences (communication style, preferred language, etc.) d) Goals (goals, targets, aspirations, etc.) e) Relationships (personal and professional relationships up to 3 degrees of separation) - When storing information, use specific and descriptive keywords that will help in future searches 4. Memory Update: - If any new information was gathered during the interaction, update your memory as follows: a) Create entities for recurring organizations, people, and significant events b) Connect them to the current entities using relations c) Store facts about them as observations d) Use clear and searchable terms in entity names and observations to facilitate future retrieval
docker build -t mcp/memory -f src/memory/Dockerfile .
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Enables memory for Claude using a knowledge graph with fuzzy semantic search and persistent storage.
Local-first knowledge graph for developers. Watches project files, extracts entities and relationships via LLMs, and lets you query across projects with natural language and source citations.
A server for CodeFuse-CGM, a graph-integrated large language model designed for repository-level software engineering tasks.
A persistent memory server for Large Language Models, designed to integrate with the Claude desktop application. It supports tiered memory, semantic search, and automatic memory management.
Graph-based long-term memory skill for AI (LLM) coding agents — faster context, fewer tokens, safer refactors
A server that provides a memory system for LLMs, enabling persistent conversations with various providers like OpenAI, Anthropic, and OpenRouter.
Memtrace gives AI coding agents structural memory — your codebase as a live knowledge graph so agents stop re-deriving code structure from scratch and start reasoning from fact.
A framework for developing LLM applications with capabilities like tool usage, planning, and memory, based on the Qwen model.
Smriti is a Model Context Protocol (MCP) server that provides persistent, graph-based memory for LLM applications. Built on LadybugDB (embedded property graph database), it uses EcphoryRAG-inspired multi-stage retrieval - combining cue extraction, graph traversal, vector similarity, and multi-hop association - to deliver human-like memory recall.
Open-source AI memory layer with importance scoring, temporal decay, hierarchical memory, and YMYL prioritization
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
