generative-ai-cdk-constructs and generative-ai-application-builder-on-aws
These are ecosystem siblings—the CDK constructs provide reusable infrastructure components that the Application Builder can leverage to deploy generative AI solutions more rapidly.
About generative-ai-cdk-constructs
awslabs/generative-ai-cdk-constructs
AWS Generative AI CDK Constructs are sample implementations of AWS CDK for common generative AI patterns.
Provides pre-built, multi-service L3 constructs for generative AI architectures—including SageMaker model deployments (JumpStart, Hugging Face, custom), Amazon Bedrock integration, and vector databases—with sensible defaults aligned to AWS best practices. Supports TypeScript, Python, Java, Go, and C# via JSII cross-language bindings, enabling infrastructure-as-code for common patterns like RAG systems and model serving without manual orchestration.
About generative-ai-application-builder-on-aws
aws-solutions/generative-ai-application-builder-on-aws
Generative AI Application Builder on AWS facilitates the development, rapid experimentation, and deployment of generative artificial intelligence (AI) applications without requiring deep experience in AI. The solution includes integrations with Amazon Bedrock and its included LLMs, such as Amazon Titan, and pre-built connectors for 3rd-party LLMs.
Provides a web-based dashboard for multi-persona LLM experimentation using nested CloudFormation stacks, enabling admin users to rapidly configure and compare different LLM combinations with production-ready infrastructure including VPC isolation options. Built on LangChain, it supports both Bedrock and SageMaker LLM providers alongside third-party models, with real-time metric tracking via CloudWatch dashboards. Deploys chat interfaces with enterprise data integration and REST/WebSocket APIs for custom implementations, managing configurations through DynamoDB and Lambda-backed automation.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work