Skip to content

AI Platform

Full AI platform with HTTP service, LLM gateway, vector store, data pipeline, auth, billing, monitoring, and a Platform tenant chart whose ModelGateway serves the gateway's and the pipeline's model routes. Everything needed to ship a production AI product with usage-based billing and operational visibility.

Nameai-platform
Version0.1.0
Tagsai, platform, fullstack, billing, typescript
Sourcecomposites/ai-platform.yaml

Render it

# CLI
npx @nanohype/sdk render-composite ai-platform --out ./my-app

# SDK
import { LocalSource, renderComposite } from "@nanohype/sdk";
const result = await renderComposite(source, "ai-platform", variables);

# MCP — from an agent
get_composite({ name: "ai-platform" })

What it draws together

TemplateRendered atNotes
monoreporootthe root project
ts-serviceapps/api
module-llm-gatewaypackages/gateway
module-vector-storepackages/vectors
data-pipelinepackages/pipeline
module-auth-tspackages/auth
module-billing-tspackages/billingonly when IncludeBilling
module-database-tspackages/db
monitoring-stackinfra/monitoring
k8s-app-tenantinfra

Variables

Required

ProjectName string
Project name used across all templates Must be lowercase kebab-case.

Optional

LlmProvider string — defaults to gateway
LLM provider the packages deployed on the substrate call: gateway, the Platform ModelGateway, which holds the Bedrock role there, so none of them holds a model credential
DatabaseDriver string — defaults to postgres
Database driver
IncludeBilling bool — defaults to true
Include billing and usage tracking
Tenant string — defaults to ${ProjectName}
Owning team: the tenants-<team> namespace the Platform, BudgetPolicy and ModelGateway CRs are applied in, the Platform's spec.tenant, and the team label on the tenant chart's resources and telemetry
Image string — defaults to ${ProjectName}
Container image repository the tenant chart deploys, without a tag; each values-<env>.yaml pins one
AppMetric string — defaults to http
Prefix of the RED series the tenant chart's Grafana dashboard reads: <prefix>_requests_total, <prefix>_errors_total and <prefix>_request_duration_seconds. The default, http, is the prefix apps/api (a ts-service) emits them under