AWS Samples ORG

Example projects using the AWS CDK

This is a workshop designed for Amazon Bedrock a foundational model service.

Provide JSON file template that demonstrate how to create customize Well-Architected reviews using Custom lenses.

Serverless patterns. Learn more at the website: https://serverlessland.com/patterns.

AWS Glue code samples

This repository contains examples for customers to get started using the Amazon Bedrock Service. This contains examples for all available foundational models

Application implementation with business use cases for safely utilizing generative AI in business operations

AWS-native chatbot using Bedrock

Serverless Ecommerce Platform is a sample implementation of a serverless backend for an e-commerce website. This sample is not meant to be used as an e-commerce platform as-is, but as an inspiration on how to build event-driven serverless microservices on AWS.

Example solutions demonstrating how to implement patterns within the AWS Security Reference Architecture guide using CloudFormation (including Customizations for AWS Control Tower) and Terraform.

No description.

Machine Learning University: Accelerated Tabular Data Class

Visual, Interactive Articles About Machine Learning: https://mlu-explain.github.io/

A lightning-fast, cross-platform mobile AI Assistant App built with React Native.

aws2tf - automates the importing of existing AWS resources into Terraform and outputs the Terraform HCL code.

Samples and template scenarios for AWS CodeDeploy

Hands-on labs for Amazon EKS

DynamoDB Examples

Open-source temporary elevated access solution for AWS IAM Identity Center.

No description.

Sample Generative AI tool for evaluating Infrastructure as Code and architecture diagrams against AWS Well-Architected best practices.

A native macOS client that brings Amazon Bedrock's AI models directly to your desktop. Access Claude Opus 4.8, Sonnet 4.6, and other foundation models through a clean interface designed for macOS, with system-wide quick access and full AWS integration.

No description.

No description.

Samples and documentation for using the Amazon Neptune graph database service

No description.

This repository contains samples of Serverless application code.

No description.

An example of using AWS Lambda with Go

Sample microservice based application demonstrating observability capabilities on AWS

A comprehensive COBOL mainframe credit card management application designed to showcase AWS mainframe modernization technologies and migration patterns.

Reference Architectures for Graph Databases on AWS

This repository contains guidance related to SageMaker AI Projects. SageMaker Projects help organizations set up and standardize developer environments for data scientists and CI/CD systems for MLOps engineers.

Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, 14 supported tools.

Repository for training and deploying Generative AI models, including text-text, text-to-image generation and prompt engineering playground using SageMaker Studio.

Fully managed RAG solution implemented using Knowledge Bases for Amazon Bedrock

Example AWS Resource control policies to get started or mature your usage of AWS RCPs.

This repo is a collection of code samples and links to previous twitch live stream sessions. If you have any ideas or suggestions for future episodes, feel free to open an issue.

No description.

ComfyUI on AWS

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.

MLOps End-to-End Example using Amazon SageMaker Pipeline, AWS CodePipeline and AWS CDK

Example of serverless integration for SaaS products listed on the AWS Marketplace.

No description.

This repo provides a managed SageMaker jupyter notebook with a number of notebooks for hands on workshops in data lakes, AI/ML, Batch, IoT, and Genomics.

This is old repo for Serverlesspresso workshop. New location: https://catalog.workshops.aws/serverlesspresso

MCP server for creating, reading, updating AWS Pricing Calculator estimates through natural language.

No description.

Build & Share AI agents with your team. Full AgentCore, Full Serverless, Full TypeScript Sample

Autonomous background coding agents on AWS. Turn tasks into pull requests via isolated runtimes, with built-in orchestration, observability, and governance.

No description.

Amazon SageMaker AI collection of examples, code samples and recipes.

Learn to build AI agents with Strands framework. Covers LLM integration via Amazon Bedrock/Anthropic, AWS service connections, tool implementation with MCP/A2A protocols, and agent evaluation using LangFuse/RAGAS.

No description.

Sample Apache Flink application that can be deployed to Kinesis Analytics for Java. It reads taxi events from a Kinesis data stream, processes and aggregates them, and ingests the result to an Amazon Elasticsearch Service cluster for visualization with Kibana.

A place to add different use cases for different Kinesis Video Stream Assets

A comprehensive toolkit for deploying production-ready Generative AI infrastructure on Amazon EKS. Includes pre-configured components for: 🚀 AI Gateway (LiteLLM) 🤖 LLM Serving (vLLM, SGLang, Ollama) 📊 Vector Databases, 🔍 Embedding Models (TEI) 📈 Observability (Langfuse, Phoenix) etc. Fast-track your GenAI deployment with Kubernetes

No description.

AWS CloudFormation template to deploy the open source strongSwan VPN solution to act as a VPN gateway in support of site-to-site VPN connections.

Deploy a managed FFMPEG with AWS Batch

Bedrock Knowledge Base and Agents for Retrieval Augmented Generation (RAG)

AI-Driven Threat Modeling & Attack Tree Generation with MITRE ATT&CK Integration

No description.

AWS Gateway Load Balancer Tunnel Handler. See the blog post linked below for more information.

This project demonstrates how to use AWS Bedrock with Anthropic Claude and Amazon Nova models to create a web automation assistant with tool use, human-in-the-loop interaction, and vision capabilities.

This repository contains examples and sample code to help customers get started with using Amazon Neptune in Generative AI applications.

Sample Apache Beam pipeline that can be deployed to Amazon Managed Service for Apache Flink. It reads taxi events from a Kinesis data stream, processes and aggregates them, and ingests the result to Amazon CloudWatch for visualization.

No description.

No description.

No description.

No description.

Code samples for building AI applications on AWS with Amazon Bedrock, including Converse API, tool use, RAG with Knowledge Bases, guardrails, and a full agent built with the Strands Agents SDK.

No description.

Deployable code samples demonstrating how generative AI transforms cloud operations. Deploy as-is with one click, or adapt to your specific environment with minimal customization effort.

Manage AWS IAM Identity Center permission sets and account assignments with Terraform.

No description.

No description.

A platfrom to Plan, Build, Operate, Secure, and Govern AI Systems for Financial Services on AWS

No description.

AI-DLC: Collaborative AI-Driven Development Lifecycle

Curated agentic AI skills for AWS platform engineering, delivered through any coding agent

This code sample deploy a realistic simulated Manufacturing Execution System hosted on SQLite and a companion chatbot application powered by Amazon Bedrock to query data from the MES using natural language

No description.

End-to-end Intelligent Document Processing (IDP) pipeline using Amazon Bedrock, LanceDB, Lambda, Strands Agents, and Step Functions. Supports multimodal document analysis for PDFs, images, videos, and audio.

A curated collection of ready-to-use agent skills covering AWS development, security scanning, testing, and AI coding workflows.

Multi-tenant AI assistant platform on Amazon EKS. One-command deploy, scale-to-zero per user, powered by Amazon Bedrock.

🚀 Experimental AI demos showcasing Amazon Bedrock, open-source LLMs & creative possibilities. AI Agents, RAG systems, streaming agents & more!

Custom kube-scheduler for binpacking targeting Spark on EKS and other jobs workloads

Benchmark framework that measures cost, quality, and duration of coding agents across any AI Coding Assistant CLI, any model, and any use case — with pluggable verification and real-repo support.

No description.

This repo contains examples of high throughput ingestion using Apache Spark and Apache Iceberg. These examples cover IoT and CDC scenarios using best practices. The code can be deployed into any Spark compatible engine like Amazon EMR Serverless or AWS Glue. A fully local developer environment is also provided.

Learn EKS Auto Mode through deployable Terraform examples

No description.

No description.

Curated archive of agentic AI samples, reference implementations, and tooling from the Agentic AI Acceleration program in Korea. AWS-native patterns covering Bedrock, AgentCore, and end-to-end agentic AI pipelines.

No description.

An open-source, serverless, EVM-compatible design for generating digital asset invoices, tracking payments, and sweeping funds into an offline treasury wallet.

MCP server for automated AWS network architecture reviews - DX resiliency scoring, TGW topology, Cloud WAN discovery. 13 tools, boto3 only

This project uses the open-source model Mistral Small, deployed in Amazon SageMaker or invoked via API on Amazon Bedrock, to enable users to chat with their database using natural language, without writing any code or SQL query.

Fullstack AgentCore Solution Template samples repository. See what others have built with FAST!

No description.

Open-source tools for AWS DevOps Agent - extend DevOps Agent with ready-to-use skills, custom agents, and other tools, for incident response, root cause analysis, and operational troubleshooting

No description.

No description.

An optimized sample code for SHA256 and SHA512 using C intrinsic

Serverless AWS platform for ingesting, processing, and analyzing customer feedback from multiple sources using AI-powered insights with Amazon Bedrock — built as part of the AI-assisted Product Development Lifecycle Initiative (AI PDLC).

No description.

AI agent that scans CloudFormation docs and generates cfn-guard security rules. Powered by Amazon Bedrock AgentCore.

No description.

A full-stack agentic harness on AWS — spin up multi-agent chatbots, voice-to-voice AI, RAG, and an Agent Factory on Bedrock AgentCore. From idea to deployed agent, fast.

No description.

Script to collect Pod related information from EKS Cluster

No description.

No description.

This repository contains a complete solution for detecting toxicity across voice and text chats, cost efficiently and at scale, in near real time. It makes use of a number of Serverless and Fully Managed AWS services, including Amazon SageMaker, Amazon Cognito, AWS Lambda, AWS Amplify, and Amazon Transcribe

No description.

No description.

No description.

A Serverless tool to automate Grafana components Backup and Restore.

No description.

No description.

No description.

Build a graph application with Amazon Neptune and AWS Amplify.

No description.

Automate the deployment of the AWS DataSync Agent on Azure with this easy-to-use script. Convert the VHDX file to VHD and create an Azure VM to host the DataSync Agent.

Automation framework for managing cleanup of CloudFormation stacks and associated resources

No description.

No description.

No description.

Data Wiki turns AWS Glue databases into portable knowledge bundles following Open Knowledge Format (OKF) and serves them to AI agents over the Model Context Protocol (MCP).

No description.

No description.

Evaluate, compare, and recommend the optimal AWS document processing approach for your use case.

Evaluate your service portfolio's readiness for agentic AI adoption and modernization

a production-grade AI Agent sandbox platform built on AWS, microVM architecture — with lower cost, full data sovereignty, and native Kubernetes integration.

Run Claude Code with any foundation model on Amazon Bedrock (43 models) or a self-hosted model on EC2. Includes a HumanEval benchmark.

A Claude Code skill that performs automated, read-only EKS cluster upgrade readiness assessments. Know what will break before you upgrade.

A side-by-side comparison of popular AI coding tools.

Setup and use Bedrock AgentCore Web Search on your local AI IDE with skills

A live, spatial monitoring panel for Amazon ECS. See task placement across all your clusters and regions at a glance — container instances, capacity providers, AZ distribution, and resource utilisation, all in one view.

Reusable CDK construct — ConnectPattern — for building agentic Amazon Connect experiences with knowledge-base retrieval, MCP tool calling via Bedrock AgentCore Gateways, dynamic multi-language voice, and both inbound and campaign-style outbound flows.

No description.

No description.

No description.

No description.

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

Generate playable arcade games using Kiro and natural language prompts.

No description.

No description.

No description.

This samples provide a read-only Claude Code skill that assesses a live Amazon EKS cluster against AWS best practices and produces a rated, prioritized Markdown/HTML report of gaps and recommended actions. Closing the gap between your existing EKS cluster setup against best practices.

No description.

No description.

No description.

No description.

Kiro skill for end-to-end predictive maintenance: explores raw IoT telemetry in S3, engineers features, trains AutoML models (RUL regression, failure classification, multi-label classification, or survival analysis), and deploys as a real-time SageMaker endpoint or daily batch inference job.

No description.

No description.

No description.

LLM Wiki Skill: build persistent, compounding knowledge bases as interlinked markdown. Includes academic source acquisition (arXiv, Semantic Scholar, OpenAlex, GitHub), a Cloudscape web app for visualization, and a serverless AWS platform for multi-agent wiki collaboration.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

Automatically assess AWS Health event impact using AWS DevOps Agent. Analyzes application topology to determine blast radius, identifies affected teams from resource tags, and routes notifications through team-specific channels (email, Slack, MS Teams, Jira) with OpsCenter integration.

No description.

No description.

No description.

Private AI agent with WebSocket streaming over CloudFront VPC Origins and the next generation of OpenSearch Serverless for knowledge retrieval

No description.

Rust binaries for assembling, validating, and driving simulation scenes of multi-robot industrial cells in Isaac Sim

Deploy an MCP server with MCP Apps (interactive HTML widgets) on Amazon Bedrock AgentCore Runtime, connected to AI hosts like ChatGPT and Claude — demonstrated with a Unicorn Rentals sample.

No description.

No description.

No description.

No description.

No description.

Context-aware AI tool built with Amazon Bedrock Guardrails for responsible, age-appropriate and role-based responses, refer blog post- https://aws.amazon.com/blogs/machine-learning/building-age-responsive-context-aware-ai-with-amazon-bedrock-guardrails/

Enforce 2-of-3 human approval and a transaction-policy engine INSIDE an AWS Nitro Enclave before a blockchain key signs. The enclave decodes ERC-20 calldata and judges the real recipient/amount, and the approver set is baked into PCR0 — so a compromised backend can neither bypass consensus nor inject a fake approver. KMS attestation gates key use

No description.

No description.

No description.

Sample code for two-tier LLM inference (cascading) on Amazon Bedrock, using a single Bedrock Converse API surface. NVIDIA Nemotron Nano handles routine support-ticket classification on every request; Anthropic Claude Sonnet handles cases the routing logic flags as harder. Includes a bake-off harness, sample data, and tests. Next.js + TypeScript.

No description.

No description.

No description.

This demonstrates a serverless solution using AWS Lambda and Amazon EventBridge to continuously capture point-in-time forensic artifacts from RDS/Aurora databases (process lists, engine stats, db session level details etc.,) and store them in S3. These artifacts create a time-series record that AI (Kiro) tools can analyze with the deeper diagnostic

Sample multi-agent AI system for life insurance claims processing using Amazon Bedrock AgentCore. Six specialist agents orchestrate identity verification, document extraction, policy validation, fraud detection, and adjudication with human-in-the-loop governance.

No description.

No description.

Sample multi-service insurance claims processing app on AWS — ECS Fargate, Aurora PostgreSQL, and Amazon Bedrock — used to demonstrate autonomous incident detection and investigation with AWS DevOps Agent.

Track and Optimize Generative AI Spend for Applications, Developers, and Agents on AWS workshop

No description.

No description.

No description.