AI Memory
A semantic memory system for AI agents that stores and retrieves contextual knowledge across sessions using PostgreSQL vector search. Enables persistent memory with relationships, automatic clustering, and multi-user support.
44509 views5Local (stdio)
What it does
- Store contextual knowledge with vector embeddings
- Retrieve memories using semantic similarity search
- Create relationships between memories (references, contradicts, supports)
- Traverse memory graphs with BFS/DFS algorithms
- Manage memory lifecycle with automatic decay and archiving
- Isolate memory contexts across multiple users
Best for
AI agents needing persistent memory across conversationsMulti-user AI applications with isolated contextsKnowledge management systems with semantic searchAI assistants building long-term understanding
Local embeddings — no API calls requiredProduction-ready with PostgreSQL + RedisGraph-based memory relationships
