# Virus Protocol System Overview Core Components **Virus Protocol Core** Central system that handles all user interactions Manages response generation with context awareness Calculates evolution scores for interactions Coordinates memory and context systems **Memory System** Dual-layer memory architecture: Short-term Memory (STM): Recent conversations and context (24h retention) Long-term Memory (LTM): Important facts, patterns, and concepts Automatic importance assessment for memory transfer Relevance-based memory retrieval **Context Manager** Maintains evolutionary context across multiple time windows: 24 hours (50 interactions) 1 week (100 interactions) 1 month (200 interactions) Generates summaries, topics, and insights Updates automatically based on system evolution **Evolution Processing** Batch processes interactions for pattern recognition Updates system evolution state Influences response generation and context Maintains evolutionary trajectory **Data Flow** User sends message → System retrieves context and memories LLMs generates response using combined context Response and interaction stored in short-term memory Important information transferred to long-term memory Evolution score calculated and interaction queued Batch processing updates evolution state Context regularly updated based on new patterns **Storage** MongoDB: Persistent storage for interactions and evolution data Redis: Caching, queues, and temporary storage Short-term memory Context summaries Evolution queue **AI Integration** Uses AI Chat Models for: Response generation Evolution scoring Memory importance assessment Pattern analysis Context summarization The system creates a continuously evolving AI entity that maintains conversation coherence while developing deeper understanding through context and memory management. --- # 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://docs.virus-protocol.com/getting-started/virus-protocol-system-overview-core-components.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.