IMMA (Interactive Multi-Modal Memory Agent) is a modular framework designed to enhance conversational AI with persistent memory. It encodes text, image, and other data from past interactions into an efficient memory store, performs semantic retrieval to provide relevant context during new dialogues, and applies summarization and filtering techniques to maintain coherence. IMMA’s APIs enable developers to define custom memory insertion and retrieval policies, integrate multi-modal embeddings, and fine-tune the agent for domain-specific tasks. By managing long-term user context, IMMA supports use cases that require continuity, personalization, and multi-turn reasoning over extended sessions.

The Azure AI Travel Agents sample is an end-to-end reference implementation of a conversational agent that helps users plan trips by generating personalized travel itineraries, sourcing flight and hotel options, and answering travel-related questions. Built on the Azure AI Agent framework, it integrates OpenAI’s GPT models for natural language understanding and generation, uses Azure Functions for hosting skills such as weather lookup, and connects to external APIs for real-time booking information. Developers can run the sample locally or deploy it to Azure, extend existing skills or add new ones for currency conversion, local attraction recommendations, or travel alerts. This sample highlights how to orchestrate multiple AI-powered skills and manage context state across turns, enabling a robust, scalable travel assistant solution.