unknown

AIOps Sherlock is an open-source diagnostics assistant that uses multi-agent AI architecture to troubleshoot Kubernetes workloads on Amazon EKS. The system employs specialized AI agents (Diagnostic, Observability, and Persistence) that collaborate using the Swarm pattern to analyze pod health, CloudWatch metrics, and DynamoDB performance. Built with Strands Agents SDK, Model Context Protocol (MCP) servers, and Amazon Bedrock, it demonstrates how AI can augment platform engineers and SREs by providing intelligent automation and expert-level analysis. The project includes a complete evaluation framework with OpenTelemetry integration and Langfuse observability, tested against the AWS Retail Store sample application to showcase real-world troubleshooting scenarios.

aws-samples/sample-agentic-aiops-k8s-sherlock: Agentic AIOps Kubernetes Sherlock (or in short "AIOps Sherlock") is a Diagnostics Assistant for Kubernetes workloads on Amazon EKS

Space dedicated to sharing content related to the fascinating world of AWS. Here you will find articles, tools and resources that I personally find interesting and useful.