Using AWS Bedrock With Kilo Code

Kilo Code supports accessing models through Amazon Bedrock, a fully managed service that makes a selection of high-performing foundation models (FMs) from leading AI companies available via a single API. This provider connects directly to AWS Bedrock and authenticates with the provided credentials.

Website: https://aws.amazon.com/bedrock/

Prerequisites

• AWS Account: You need an active AWS account.
• Bedrock Access: You must request and be granted access to Amazon Bedrock. See the AWS Bedrock documentation for details on requesting access.
• Model Access: Within Bedrock, you need to request access to the specific models you want to use (e.g., Anthropic Claude).
• AWS CLI (profile authentication only): If you plan to use an AWS profile, install AWS CLI and configure your credentials:

  aws configure
  

Getting Credentials

You have three options for configuring AWS credentials:

1. Bedrock API Key:
   • Create a Bedrock-specific API key in the AWS Console. This is a simple service-specific authentication method.
   • See the AWS documentation on Bedrock credentials for instructions on creating an API key.
2. AWS Access Keys:
   • Create an IAM user with the necessary permissions (at least bedrock:InvokeModel).
   • Generate an access key ID and secret access key for that user.
   • (Optional) Create a session token if required by your IAM configuration.
3. AWS Profile:
   • Configure an AWS profile using the AWS CLI or by manually editing your AWS credentials file. See the AWS CLI documentation for details.

Configuration in Kilo Code

Tips and Notes

• Permissions: Ensure your IAM user or role has the necessary permissions to invoke Bedrock models. The bedrock:InvokeModel permission is required.
• Pricing: Refer to the Amazon Bedrock pricing page for details on model costs.
• Cross-Region Inference: Using cross-region inference may result in higher latency.