Hands-on workshop to build a production AI agent with Strands Agents, tools, hooks, memory, multi-agent, evals, and deploy to Amazon Bedrock AgentCore.
-
Updated
Aug 3, 2026
Hands-on workshop to build a production AI agent with Strands Agents, tools, hooks, memory, multi-agent, evals, and deploy to Amazon Bedrock AgentCore.
Pluggable Agentic AI Framework is a hands-on workshop that builds a multi-agent customer support system on AWS using Amazon Bedrock AgentCore. It follows the scenario of AnyCompany, an online retailer, where a supervisor orchestrator dynamically discovers and delegates to specialized agents via harness
Amazon Bedrock AgentCore enterprise platform accelerator with AWS CDK, Terraform organization guardrails, MCP/A2A agents, security, memory, and observability.
Building an AI Agent into Your Service with Strands Agents SDK: A Hands-on Comparison of 3 Multi-Agent Patterns (Agents-as-Tools / Swarm / Graph)
Serverless Telegram AI assistant on Amazon Bedrock AgentCore Runtime + Memory (OpenClaw agent): cross-session memory, vision recognition, and proactive EventBridge reminders.
An enterprise-grade, omnichannel voice assistant for QSRs. Built with 100% serverless AWS architecture, leveraging Amazon Bedrock AgentCore, Nova Sonic v2, and the MCP protocol for ultra-low latency, real-time voice interactions.
Enterprise Supply Chain AI Assistant powered by Amazon Bedrock AgentCore & Strands Framework. Features secure VPC isolation, OpenSearch RAG, and automated CDK deployment.
Open-source memory manager daemon for AI agents. Filesystem-native, LLM-pluggable, framework-agnostic. Works with OpenClaw, Strands, LangChain, AgentCore Runtime or any agent that can write a file.
Enterprise identity on Amazon Bedrock AgentCore with Lark (Feishu) as the IdP. Every turn arrives as a signed per-user JWT, and that user's Lark token lives in the AgentCore Identity Token Vault (OAuth 3LO) — stored and refreshed natively, no self-managed store. MCP tools act as the user against Lark, reaching only what that user can.
A system that generates recorded browser session videos from public webpages, based on a webpage URL and the description of the needed clickthrough recording.
Enterprise identity on Amazon Bedrock AgentCore with Lark (Feishu) as the IdP. A Gateway Request Interceptor forwards the user's identity and injects a per-user credential — the agent never holds it — so downstream MCP tools act as the user against Lark and reach only what that user can.
Hackathon prep material for Twilions
AI incident assistant: a supervisor delegates to specialist agents (observability + web context) on AgentCore and Strands with MCP — fully deployable via AWS CDK.
Run the Claude Code harness on AWS Bedrock AgentCore Runtime.
Deploy OpenClaw on AWS — an AI agent that codes, researches, analyzes, creates, and automates. Multiple deployment options from serverless to persistent.
Reference repository for deploying and integrating Strands Agents in TypeScript with Amazon Bedrock AgentCore Runtime.
This code demonstrates building production-grade agentic applications with Strands Agents SDK, Amazon Bedrock AgentCore Memory, and AgentCore Runtime — from local prototyping through to cloud-hosted deployment.
AWS Bedrock AgentCore Runtime and Memory
Transform unstructured media contracts into searchable metadata using multi-modal AI. Extracts territory grants, compensation terms, expiration dates, and clause relationships from rights deals, licenses, and talent agreements at scale.
The neural control plane for enterprise LLMs
To associate your repository with the agentcore-runtime topic, visit your repo's landing page and select "manage topics."