# Memory Management Levia's memory system is multi-layered and hierarchical, designed to store and manage various types of information. It segments: * Contextual interactions with specific users * Semantic meaning of concepts * Factual knowledge * Stored pathways and actions for goal achievement Levia's memory architecture consists of five key components: 1. **Episodic Memory** - Stores procedures, workflows, and connections between tool functions 2. **Factual Memory** - Stores objective knowledge and facts. 3. **Short-Term Memory** - Captures contextual interactions and experiences. 4. **External Memory (Storage)** - Archives large datasets for retrieval. 5. **Key and Secrets Vault** - Securely stores sensitive information. Through these structured layers, Levia ensures efficient retrieval and long-term adaptability of AI agents, fostering continuous learning and improvement. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://leviaprotocol.gitbook.io/leviaprotocol/core-concepts/memory-management.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.