DNA Insider
繁中
Back
Official Source· AWS Artificial Intelligence· AI· Published Oct 7, 2026

AWS Shows How to Build a Context-Aware Assistant With OpenClaw and AgentCore

In a technical guide published October 6, 2026, AWS demonstrates a personal assistant that uses OpenClaw and Amazon Bedrock AgentCore to retain structured conversational context. Its gardening example, Sprout, illustrates the memory design, request paths, and model routing.

AWS Shows How to Build a Context-Aware Assistant With OpenClaw and AgentCore

Full Report

AWS published a technical guide on October 6, 2026, showing how to run OpenClaw on Amazon Bedrock AgentCore runtime and use AgentCore memory to turn conversations into structured knowledge retrievable with metadata filters. The example assistant, Sprout, is designed for gardening. AWS describes the architecture as domain-agnostic: changing the persona and skills manifest can adapt the same pipeline for a support bot, fitness coach, or internal help desk.

The system is packaged in a single AWS CloudFormation template. Requests can arrive as Telegram messages or scheduled jobs, with both paths invoking the same AgentCore runtime agent. Telegram traffic passes through Amazon API Gateway and a webhook Lambda; scheduled work uses Amazon EventBridge Scheduler and a cronjob Lambda. Inside the runtime, server.py coordinates the OpenClaw gateway, AgentCore memory, and the Amazon Bedrock Converse API.

The example also routes text and image requests differently. Text turns use Claude Haiku 4.5, while image understanding uses Claude Sonnet 4.5. Text passes through the OpenClaw gateway; image turns are sent directly to Bedrock by server.py with the image content. AWS introduced AgentCore Memory as an agent memory-management service in 2025; this guide shows how it fits into a deployable assistant architecture.

Why This Matters

The guide makes persistent conversational memory concrete by showing how it connects with messaging, scheduled tasks, and separate text and image paths. For developers assessing personalized assistants, it offers an implementation pattern that AWS says can be adapted to several assistant roles.

Evidence

Start with the primary evidence, then review supporting sources and context.

1 items

Primary Evidence

1
  • OfficialAWS Artificial IntelligenceDocumentOriginal

    Building a context-aware AI assistant on AgentCore and OpenClaw

    Thiago Verney

    “Off-the-shelf AI assistants forget you between conversations. This post shows how to build a personal assistant that accumulates context using OpenClaw on Amazon Bedrock AgentCore runtime, with AgentCore memory turning disposable chats into durable, structured knowledge you can retrieve with metadata filters.”

Recommended signals

Recommended by brand, topic, and recent related coverage

No more recommended signals right now

Official statement

Open original source
Back to Live FeedExplore more signals