Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by kensave • Uncategorized
An episodic memory system for AI agents with vector and keyword search, exposed via an MCP server.
Persistent episodic memory storage with vector similarity search.
Isolated workspaces to manage separate memory databases.
Hybrid search combining semantic and keyword-based retrieval.
Agent Memory RS provides a robust episodic memory system that stores and retrieves interaction episodes using vector embeddings and BM25 keyword search. It supports multiple embedding models and workspace isolation, ensuring persistent and isolated memory storage per project. The system is accessible through an MCP server offering learn and search tools, enabling AI agents to efficiently manage and query their memories for improved contextual understanding and long-term interaction.