Building Memory Augmented Agents with MemoRizz
summary
Workshop shows how MemoRizz becomes a runnable memory stack: code builds a single agent plus a multi‑agent deep research flow with a root, delegates and a synthesis agent, stores tools as JSON schemas, and uses Oracle AI Database as the memory core. Examples use OpenAI embeddings for vector retrieval, Tavi for web search, Docker for local Oracle, and a semantic cache that returns cached LLM responses by embedding similarity. Demonstrations include entity/persona memory, tool calling (weather API), and auto‑summarization to avoid context bloat.
AI-written summary · about
chapters (7)
- 0:00Introduction and setup
- 15:26What is an AI agent
- 20:04Agent memory explained
- 44:50Memory engineering vs context engineering
- 1:00:04Building agents with MemoRizz
- 1:33:35Deep research with multiple agents
- 1:45:08Q&A and closing remarks
related talks
54mThe Anatomy of Memory in Humans and AI Agents
18mArchitecting Agent Memory: Principles, Patterns, and Best Practices
58mAdvanced Autonomous AI Agents: Memory, Collaboration and Evolution in Action
15mMemory-Augmented AI Agents: Enhancing Long-Term Reasoning and Context Awareness
51mMemory Masterclass: Make Your AI Agents Remember What They Do!
01h 34mHands-on AI workshop: Graph RAG, Memory & Multimodal Agents
25mWhat does it take to build long-term state for AI agents?
28mAI Agents That Remember, Share, and Cost Less with Meko | Introducing Meko