Amazon Bedrock#

You can use Amazon Bedrock models with kagent by leveraging AWS Bedrock's OpenAI Chat Completions API.

Step 1: Prepare your AWS details#

1. Follow the AWS Bedrock API keys guide to create the API key needed for authentication.

2. Choose the AWS region and Bedrock model you want to use. Refer to the AWS Bedrock supported models documentation.

   • Example Regions: us-west-2 or us-east-1
   • Example model IDs: amazon.titan-text-express-v1 or openai.gpt-oss-20b-1:0. Ensure your AWS account has access to the chosen model. Some models, like Anthropic models, may require additional access controls. For more information, see the AWS Bedrock model access docs.

3. Save your AWS API key as an environment variable.

   export AWS_API_KEY=<your-aws-api-key>

4. Create a Kubernetes secret that stores your AWS API key in the same namespace as your agent, typically kagent.

   kubectl create secret generic kagent-bedrock -n kagent --from-literal AWS_API_KEY=$AWS_API_KEY

Step 2: Create the ModelConfig#

1. Create a ModelConfig resource that uses the OpenAI-compatible API interface.

   kubectl apply -f - <<EOF
   apiVersion: kagent.dev/v1alpha2
   kind: ModelConfig
   metadata:
     name: bedrock-config
     namespace: kagent
   spec:
     apiKeySecret: kagent-bedrock
     apiKeySecretKey: AWS_API_KEY
     model: amazon.titan-text-express-v1
     provider: OpenAI
     openAI:
       baseUrl: "https://bedrock-runtime.us-west-2.amazonaws.com/openai/v1"
   EOF

   Setting	Description
   apiKeySecret	The name of the Kubernetes secret storing your AWS API key.
   apiKeySecretKey	The key in the secret that stores your AWS API key.
   model	The Bedrock model ID to use, such as amazon.titan-text-express-v1 or openai.gpt-oss-20b-1:0.
   provider	Set to OpenAI to use the OpenAI-compatible API interface.
   openAI.baseUrl	The Bedrock OpenAI-compatible endpoint URL for your chosen region. The baseUrl format is: https://bedrock-runtime.<region>.amazonaws.com/openai/v1.

Next Steps#

Now that you configured your Bedrock model, you can create or update an agent to use this model configuration.