Amazon Bedrock Foundation models with Amazon Opensearch Serverless as a Vector DB

Building an Intelligent AWS Cloud Engineer Agent with Strands Agents SDK

It shows how to use AgentCore for deploying LangGraph and Strands agents with MCP.

A full-stack web application that conducts comprehensive research using multiple specialized AI agents to gather, analyze, and synthesize information from diverse sources into coherent reports.

It show how to deploy MCP tools using AgentCore.

From Douglas Hofstadter's "Gödel, Escher, Bach" (1979)

CalledIt is a serverless web application that converts natural language predictions into structured, verifiable formats using AI agents. Built on AWS serverless architecture, it provides a robust platform for creating, managing, and validating predictions with intelligent verifiability categorization.

Feedminer is nominally an app to let you analyze your own social media feeds to help you set goals for yourself. In reality, Feedminer is a working demo of how to implement streaming responses from LLMs via Lambda and API Gateway using WebSockets. It's also a demo on how to use AWS streams to switch models quickly in AWS Bedrock.

MCP Server for Strands leveraging ElasticSearch

A simple Python3 script that provides the answers for a range of NYT games.

Early preview of the Bedrock AgentCore HTTP runtime

Algorithmic solvers for popular NYT word puzzles