AWS context layer (beta)

AWS Continuum is an AI-powered security service from Amazon Web Services that scans customer environments for vulnerabilities and prioritizes them using context about each customer's setup. The service uses AI models to help determine which vulnerabilities require attention.

Amazon AgentCore is a set of AWS building blocks for constructing AI agents with any model, whether used inside or outside Amazon Bedrock.

Amazon Aurora is a managed relational database service from Amazon Web Services (AWS). In the cited discussion, it is described as a database for short-lived instances that agents can create and dispose of, with AWS rethinking the service for faster instance creation and disposal.

An AWS service for building AI agents. AgentCore provides building blocks for developing agents with different underlying models and is offered alongside Amazon Bedrock as part of AWS's agent-development services.

Context Ontology Accelerator is an open-source semantic context layer for AWS and AI agents. It combines knowledge graphs, formal ontologies, rule-based systems, and modern AI in a Scan → Model → Serve workflow: it connects data sources, discovers schemas, enriches metadata, and ingests documents; induces and manages ontologies, defines metrics, and builds a unified semantic graph; then serves context through SPARQL federation using a Virtual Knowledge Graph, knowledge-graph traversal, queries, and MCP tools. The repository includes source-ingestion services for databases and documents, ontology induction and reasoning with HermiT and ELK, an Ontop-based Virtual Knowledge Graph, a context manager for query orchestration, and a React frontend. Access is controlled through namespace isolation and role-based authorization, with namespace-scoped roles and platform-level roles. The implementation uses Python and TypeScript, AWS CDK, Smithy-generated API contracts, and an Nx-managed monorepo; the project is licensed under Apache License 2.0.