From the source

Building a context-aware AI assistant on AgentCore and OpenClaw

Guide to building a memory-equipped assistant using AgentCore and OpenClaw

Amazon published a guide showing how to build a context-aware AI assistant using OpenClaw on Amazon Bedrock AgentCore runtime.

The assistant accumulates user context via AgentCore memory and can route text and image tasks to different Claude models (Haiku 4.5 for text, Sonnet 4.5 for vision).

The architecture deploys from a single CloudFormation template and uses consumption-based pricing estimated at $1–2/month for light personal use.

From the source
AgentCore memory, a capability of Amazon Bedrock AgentCore, turns disposable chats into durable knowledge.
aws.amazon.com

Other stories

Amazon · 6 OctResponsible AI governance: How AWS positions customers to align with ISO/IEC 42005:2025

Amazon · 6 OctBest practices for Amazon SageMaker HyperPod administration and governance

Amazon · 6 OctCapability changeManage Amazon SageMaker HyperPod Spaces directly from SageMaker Studio

Amazon · 6 OctBuild a voice travel concierge with Amazon Bedrock AgentCore, Managed Knowledge Base and Nova Sonic

Announced: 06 Oct 2026 19:19 UTC
Detected: 06 Oct 2026 19:24 UTC (+5m after)
Pricing: consumption-based pricing. You’re billed for the compute your agent actively consumes, not for wall-clock uptime, and you don’t pay for the time when waiting for I/O such as model response. For a personal assistant used in short bursts, that is the difference between an approximately $1–2/month baseline and an approximately $35/month always-on Amazon Elastic Compute Cloud (Amazon EC2) instance. These figures are estimates for light personal use as of July 2026.

ModelsClaude Haiku 4.5, Claude Sonnet 4.5

Visit source ↗aws.amazon.com

Amazon · 5 OctModel update

Introducing GLM 5.3 on Amazon Bedrock

Amazon · 5 OctSupercharge regulated workloads with Claude Code and Amazon Bedrock