namzu.ai
Integration · @namzu/bedrock

Namzu × AWS Bedrock. Managed model API on AWS.

@namzu/bedrock authenticates with AWS Bedrock via standard SigV4 and exposes the same kernel-level tool, streaming, and vision primitives as every other provider package.

01 · Install
$ pnpm add @namzu/sdk @namzu/bedrock
02 · Why pair the kernel with AWS Bedrock

Regulated and enterprise workloads frequently mandate a specific cloud and a specific model-host arrangement. Bedrock satisfies the procurement and data-residency story; Namzu adds the runtime layer enterprise platforms also need (sandbox, scheduler, checkpoint).

  • Anthropic, Meta, Mistral, Cohere, Amazon Nova models — same agent code
  • IAM-based credentials, no separate API key management
  • VPC and PrivateLink compatible deployments
  • Region pinning enforced at the provider boundary
03 · Example
import { createKernel } from '@namzu/sdk'
import { bedrock } from '@namzu/bedrock'

const kernel = createKernel({
  provider: bedrock({
    region: 'us-east-1',
    model: 'anthropic.claude-sonnet-4-6-20260219-v1:0',
  }),
})

Ship AWS Bedrock agents on a runtime you can own.

AWS Bedrock owns the model. Namzu owns the runtime. The provider package is a thin adapter, not a wrapper, so you keep everything AWS Bedrock ships and add the kernel concerns you do not get from the model API alone.