Self-Hosting

Deploy Adaptive Engine on your own infrastructure using the Helm chart.

Self-hosted deployments have no external connectivity or telemetry requirements.

Prerequisites

Infrastructure

Kubernetes cluster with:
- GPU VM(s) for harmony compute plane
- CPU VM(s) for control-plane and recipe-runner
PostgreSQL 16+ (local or remote)
Redis (local or remote)
Shared storage (POSIX or S3-compatible)
OIDC provider (Google Workspace, Azure Entra ID, Cognito, Keycloak, etc.)
Domain name routing to the deployment

Kubernetes Requirements

Kubernetes 1.28+
Helm 3.8.0+
NVIDIA GPU operator
CUDA 12.8+ with driver 570.172.08+

Deployment Checklist

Verify GPU quota

Ensure cloud GPU quotas accommodate your instance types and counts.

Provision infrastructure

Deploy Kubernetes cluster, database, Redis, storage, and configure OIDC.

Get container registry access

Obtain access to Adaptive Engine private registry (requires commercial contract).

Configure Helm values

Pull the chart and customize values.yaml.

Deploy

Run helm install.

Set administrator emails in values.yaml before those users first log in.

Helm Configuration

Container Registry

containerRegistry: <aws_account_id>.dkr.ecr.<region>.amazonaws.com
harmony:
  image:
    repository: adaptive-repository
    tag: harmony:latest
controlPlane:
  image:
    repository: adaptive-repository
    tag: control-plane:latest

Resource Limits

harmony:
  replicaCount: 1
  gpusPerReplica: 8  # Match available GPUs per node
  resources:
    limits:
      cpu: 8
      memory: 64Gi
    requests:
      cpu: 8
      memory: 60Gi

Secrets

secrets:
  modelRegistryUrl: "s3://bucket-name/model_registry"
  sharedDirectoryUrl: "s3://bucket-name/shared"
  dbUrl: "postgres://user:password@host:5432/db_name"
  cookiesSecret: "must-be-64-chars-or-more-change-me-secret-abc123..."

  auth:
    oidc:
      providers:
        - name: "Google"
          key: "google"
          issuer_url: "https://accounts.google.com"
          client_id: "your-client-id"
          client_secret: "your-client-secret"
          scopes: ["email", "profile"]
          pkce: true
          allow_sign_up: true

If allow_sign_up: true, any OIDC member can access Adaptive Engine. Set to false and create users via SDK to restrict access.

Shared Cluster Configuration

Separate Namespace

helm install adaptive adaptive/adaptive \
  --values ./values.yaml \
  --namespace adaptive-engine \
  --create-namespace

Node Selectors

Schedule Harmony on specific GPU nodes:

harmony:
  nodeSelector:
    eks.amazonaws.com/nodegroup: p5-h100

Dedicated GPU Nodes

Taint GPU nodes to prevent other workloads:

kubectl taint nodes <node_name> dedicated=adaptive-engine:NoSchedule

Add matching toleration in values.yaml:

harmony:
  tolerations:
  - key: dedicated
    operator: Equal
    value: adaptive-engine
    effect: NoSchedule

Database TLS

Basic Encryption

dbUrl: "postgres://user:password@host/db?sslmode=require"

Certificate Verification

For full verification (sslmode=verify-full):

Download the database server certificate

Create a ConfigMap:

kubectl create configmap -n <namespace> db-ca --from-file=rds-ca-rsa2048-g1.pem

Mount in values.yaml:

volumes:
  - name: db-ca
    configMap:
      name: db-ca
volumeMounts:
  - name: db-ca
    mountPath: /mnt/db-ca/
    readOnly: true

Reference in connection string:

dbUrl: "postgres://user:password@host/db?sslmode=verify-full&sslrootcert=/mnt/db-ca/rds-ca-rsa2048-g1.pem"

Start

Core

Advanced

Deploy

Updates

Prerequisites

Infrastructure

Kubernetes Requirements

Deployment Checklist

Helm Configuration

Container Registry

Resource Limits

Secrets

Shared Cluster Configuration

Separate Namespace

Node Selectors

Dedicated GPU Nodes

Database TLS

Basic Encryption

Certificate Verification

​Prerequisites

​Infrastructure

​Kubernetes Requirements

​Deployment Checklist

​Helm Configuration

​Container Registry

​Resource Limits

​Secrets

​Shared Cluster Configuration

​Separate Namespace

​Node Selectors

​Dedicated GPU Nodes

​Database TLS

​Basic Encryption

​Certificate Verification

Prerequisites

Infrastructure

Kubernetes Requirements

Deployment Checklist

Helm Configuration

Container Registry

Resource Limits

Secrets

Shared Cluster Configuration

Separate Namespace

Node Selectors

Dedicated GPU Nodes

Database TLS

Basic Encryption

Certificate Verification