# Amazon — Building a context-aware AI assistant on AgentCore and OpenClaw

- Company: Amazon (amazon.com)
- Announced: 2026-10-06T19:19:15+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/building-a-context-aware-ai-assistant-on-agentcore-and-openclaw/
- Record: https://forck.live/items/16256-building-a-context-aware-ai-assistant-on-agentcore-and-openclaw
- Subject: Bedrock / Nova
- Models affected: Claude Haiku 4.5, Claude Sonnet 4.5
- 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.

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.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/building-a-context-aware-ai-assistant-on-agentcore-and-openclaw/:

> AgentCore memory, a capability of Amazon Bedrock AgentCore, turns disposable chats into durable knowledge.

---

Record: https://forck.live/items/16256-building-a-context-aware-ai-assistant-on-agentcore-and-openclaw
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md