Create multimodal AI agents with persistent memory | DEMSP390
Multimodal AI agents Persistent memory Napster omniagent api Azure ai foundry Mcp server Microsoft build 2026 Javascript Enterprise ai Ai agent architecture Azure resource provisioning
This advanced demo session from Microsoft Build 2026 shows developers how to build multimodal AI agents with persistent memory using the Napster Omniagent API. Viewers learn how to provision Napster as an Azure resource, embed MCP Server directly in JavaScript for local intelligence, and integrate securely within Azure AI Foundry with minimal roles. Ideal for developers and architects building AI agents that maintain context across customer touchpoints.
Related videos
Microsoft Dataverse plugin: unleashing coding agents on the enterprise | OD849
Google fires Workspace CLI Creator ⟡ GPT 5.6 Is Coming ⟡ Astro 7 Rust Re-write ⌁ Syntax Weekly ⌁
Build connected AI: Orchestrate tools and agents with registries and ADK
From prototype to production: 45 minutes to a reliable Gemini Enterprise Agent Platform agent
Build context-aware agents: From data to decisions | BRK240
Build secure and enterprise-ready agents with Agent 365 | BRK251
Fireworks AI quick take: Live from Microsoft Build | LIVESP125
Organizational intelligence in action — with Anthropic | LIVESP129
Build context-aware agents: From data to decisions | BRK240
Build work-ready agents with Foundry + Work IQ, govern with Agent 365 | DEM340
Azure DevOps meets GitHub, the path to AI powered SDLC | BRK202
