Explore how to build production-grade AI agents with persistent, context-aware memory using Amazon Bedrock AgentCore. This expert session covers architectural patterns for implementing four memory typesepisodic, semantic, preference, and summaryenabling agents that recall past interactions, recognize cross-session patterns, and maintain conversation context. You'll examine real implementation techniques for long-term memory management, workflow orchestration, and retrieval strategies using Amazon Bedrock. Leave with practical skills to design intelligent agents that deliver faster, more accurate responses in high-stakes applications. Ideal for architects and engineers ready to move beyond stateless AI toward genuinely intelligent, memory-enabled systems.
What this session is about
Live updates related to this session LIVE
Sourced via Parallel AI Monitor — continuous web watch on 21 topical streams. Updated .
- vector-labs.ai Agent memory & RAG architectures
Context Window Management: Hidden AI Coding Costs
VECTOR Labs published a technical analysis of context-window management for AI coding agents. It proposes evaluating compaction by measuring how much decision-relevant information survives summarization or truncation, rather than treating all retained tokens equally. The article
- github.com Agent memory & RAG architectures
volcengine/OpenViking - The Context Database for AI Agents
OpenViking documents a self-evolving context database for AI agents that unifies persistent memories, knowledge resources, and skills in a virtual filesystem using viking:// URIs. Its approach supports hierarchical context loading (L0 abstracts, L1 overviews, and L2 details), dir
- vektormemory.com Agent memory & RAG architectures
Persistent AI Agent Memory | Local-First with VEKTOR
VEKTOR announced that v1.9.7 is live. The release presents a local-first persistent-memory architecture in which raw conversations, tool outputs, and observations pass through AUDN curation—ADD, UPDATE, DELETE, or NO_OP—before being stored in a persistent MAGMA graph. MAGMA uses
- github.com Agent memory & RAG architectures
NousResearch/hermes-agent: The agent that grows with you
AWS published a technical pattern for network-operations agents using Amazon Bedrock AgentCore Memory. The approach persists context across sessions, allowing an agent to learn from prior investigations, while AgentCore Observability records traces, logs, and metrics and the Agen
- businesswire.com high confidence Multi-agent collaboration patterns
ZoomInfo Introduces Agent Teams, Powered by the ...
ZoomInfo announced Agent Teams, a multi-agent orchestration product built on DoubleO.ai. Specialized agents have distinct roles, instructions, and tools; they share context from prior steps and use real-time evaluation of the current record state to choose the next action. The us
External links matched to this session via topic relevance. The KB does not endorse third-party content; verify before citing.