Neo4j Knowledge Graph Memory
MCP ServerFreeStore and retrieve user-specific memories across sessions using Neo4j graph database. This MCP memory infrastructure enables AI assistants to maintain context, recall past interactions, and manage memories with semantic search capabilities. Transform your agent's conversations into a searchable memo
Capabilities5 decomposed
persistent memory storage
Medium confidenceThis capability allows the system to store user-specific memories in a Neo4j graph database, ensuring that data is preserved across multiple sessions. It utilizes the graph database's inherent structure to maintain relationships between entities, enabling efficient storage and retrieval of contextually relevant information. By leveraging Neo4j's ACID compliance, it guarantees data integrity and reliability.
Utilizes Neo4j's graph structure to create a highly interconnected memory system, allowing for complex relationships between memories.
More efficient in managing relationships between memories compared to traditional key-value stores.
hybrid semantic and exact search
Medium confidenceThis capability enables the retrieval of stored memories using both semantic search and exact matching techniques. It combines vector embeddings for semantic understanding with traditional indexing for exact matches, allowing users to find relevant memories based on context or specific queries. The integration of these two approaches ensures that users can retrieve information effectively, regardless of how they phrase their queries.
Combines semantic search with exact search capabilities, providing a more comprehensive retrieval system than typical memory solutions.
Offers a dual approach to search that outperforms single-method systems in accuracy and relevance.
memory bank management
Medium confidenceThis capability allows users to manage multiple memory banks within a single Neo4j instance, facilitating project isolation and organization. By utilizing separate namespaces for different projects, it enables developers to maintain distinct sets of memories, which is particularly useful for applications with varying user contexts or requirements. This organizational structure is implemented through Neo4j's labeling and relationship features.
Utilizes Neo4j's labeling system to create isolated memory banks, allowing for organized and context-specific memory management.
More flexible than traditional databases in managing multiple contexts without data overlap.
vector-based information recall
Medium confidenceThis capability leverages vector embeddings to recall information from the memory bank, allowing for contextually relevant responses based on past interactions. By transforming memories into vector representations, it enables the AI to perform efficient similarity searches, retrieving memories that are semantically related to the current conversation. The integration of graph traversal techniques enhances this capability, allowing for deeper contextual understanding.
Combines vector embeddings with graph traversal to enhance the relevance and accuracy of memory recall, surpassing traditional methods.
Provides a more nuanced understanding of context compared to standard keyword-based recall systems.
temporal memory tracking
Medium confidenceThis capability allows the system to track the temporal aspects of memories, enabling the AI to understand when specific interactions occurred. By incorporating timestamps and temporal relationships within the Neo4j graph, it can prioritize or filter memories based on recency or historical relevance. This feature is particularly useful for applications that need to adapt to changing user preferences over time.
Utilizes Neo4j's graph capabilities to incorporate temporal relationships, allowing for sophisticated memory management based on time.
Offers a more dynamic approach to memory management than static systems that do not account for time.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with Neo4j Knowledge Graph Memory, ranked by overlap. Discovered automatically through the match graph.
Memory Box MCP Server
Save, search, and format memories with semantic understanding. Enhance your memory management by leveraging advanced semantic search capabilities directly from Cline. Organize and retrieve your memories efficiently with structured formatting and detailed context.
mem0ai
Long-term memory for AI Agents
Mem0 Memory Server
Enable AI agents to store, search, and delete persistent memories across sessions to enhance context retention and recall. Integrate seamlessly with Mem0.ai's cloud or self-hosted Supabase storage for scalable and reliable memory management. Optimize your LLM applications with advanced filtering, se
agent-recall-core
Core memory palace engine for AgentRecall
agents-towards-production
End-to-end, code-first tutorials for building production-grade GenAI agents. From prototype to enterprise deployment.
Eidolon
Multi Agent SDK with pluggable, modular components
Best For
- ✓developers building AI assistants with long-term memory capabilities
- ✓AI developers needing efficient memory retrieval for conversational agents
- ✓teams developing multiple AI applications requiring distinct memory contexts
- ✓developers building conversational AI that requires contextual awareness
- ✓developers creating AI systems that need to adapt to user behavior over time
Known Limitations
- ⚠Requires Neo4j database setup; performance may vary based on database size and query complexity
- ⚠Semantic search may require additional computational resources for embedding generation
- ⚠Management complexity increases with the number of memory banks; requires careful design
- ⚠Vector generation and similarity search may introduce latency; requires tuning for optimal performance
- ⚠Requires careful design to manage temporal relationships; may complicate memory queries
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
About
Store and retrieve user-specific memories across sessions using Neo4j graph database. This MCP memory infrastructure enables AI assistants to maintain context, recall past interactions, and manage memories with semantic search capabilities. Transform your agent's conversations into a searchable memory bank with entities and relationships. ### Key capabilities: - **Store memories** persistently across multiple sessions - **Retrieve context** with hybrid semantic and exact search - **Manage memory banks** with multi-database project isolation - **Recall information** through vector embeddings and graph traversal - **Memory extension** for AI agents with temporal tracking - **Knowledge graph** format with intelligent relationships Perfect for building AI assistants with long-term memory, maintaining user context, and creating memory systems that remember preferences and past interactions. Self-hosted memory infrastructure built on Neo4j for reliability and performance.
Categories
Alternatives to Neo4j Knowledge Graph Memory
Search the Supabase docs for up-to-date guidance and troubleshoot errors quickly. Manage organizations, projects, databases, and Edge Functions, including migrations, SQL, logs, advisors, keys, and type generation, in one flow. Create and manage development branches to iterate safely, confirm costs
Compare →AI-optimized web search and content extraction via Tavily MCP.
Compare →Scrape websites and extract structured data via Firecrawl MCP.
Compare →Are you the builder of Neo4j Knowledge Graph Memory?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →