Multi Cloud Deployment

Multi-Cloud Deployment

Overview

ADEPT is designed for multi-cloud operation from the ground up. OCI-compliant container images, provider-neutral Helm charts, and pluggable LLM routing allow a single ADEPT deployment to span AWS, Azure, and GCP -- or federate multiple deployments across clouds using the A2A gateway mesh.

Multi-Cloud Strategy

The architecture separates concerns into three layers:

Layer	Portability	Tool
Application	Fully portable	Helm + OCI images
Infrastructure	Provider-specific	CDK / Pulumi / Terraform
LLM Routing	Provider-neutral	LiteLLM abstraction

Provider Matrix

Capability	AWS	Azure	GCP
Kubernetes	EKS	AKS	GKE
IaC Tool	CDK (Python)	Pulumi (Python)	Terraform (HCL)
Managed PostgreSQL	RDS	Flexible Server	Cloud SQL
Managed Redis	ElastiCache	Azure Cache	Memorystore
Container Registry	ECR	ACR	Artifact Registry
Secrets	Secrets Manager	Key Vault	Secret Manager
LLM Provider	Bedrock	Azure OpenAI	Vertex AI
Ingress	ALB	App Gateway	Cloud LB

LLM Provider Configuration

ADEPT routes LLM requests through LiteLLM, supporting multiple providers simultaneously. The model name prefix determines the provider:

# Azure OpenAI
DEFAULT_LLM_MODEL=azure/gpt-4o

# AWS Bedrock
DEFAULT_LLM_MODEL=bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0

# Anthropic Direct
DEFAULT_LLM_MODEL=anthropic/claude-sonnet-4-5-20250929

# Google Vertex AI
DEFAULT_LLM_MODEL=vertex_ai/gemini-2.0-flash

# Local Ollama
DEFAULT_LLM_MODEL=ollama/llama3.1

# NVIDIA NIMs
DEFAULT_LLM_MODEL=nvidia_nim/meta/llama-3.1-70b-instruct

Purpose-Based Routing: Different agent roles can use different providers. A coding agent might use AWS Bedrock Claude while the main agent uses Azure OpenAI. Configure via config/model_catalog.yaml.

Cross-Cloud Federation

The A2A (Agent-to-Agent) protocol enables ADEPT instances in different clouds to communicate. Each gateway registers with a shared Gateway Registry. Agents on one gateway can discover and invoke tools hosted on any federated peer, enabling cross-cloud workflows without data migration.

Deployment Patterns

Pattern 1: Single-Cloud Full Stack

Deploy all components in one cloud provider. Simplest operational model.

cd infra/aws/cdk && cdk deploy --all
helm install adept infra/helm/agentic-framework/ -f values-aws.yaml

Pattern 2: Multi-Cloud Federation

Deploy independent stacks per cloud, federate via A2A:

1. Deploy Stack A in AWS (owns HPC tools)
2. Deploy Stack B in Azure (owns Azure OpenAI models)
3. Register both gateways in shared registry
4. Agents in either stack can invoke tools from both

Pattern 3: Hybrid Cloud + On-Premises

Combine cloud deployments with on-premises Docker Compose instances for air-gapped or data-sovereignty requirements. The A2A mesh treats all gateways identically regardless of hosting.

Network Requirements: Cross-cloud federation requires HTTPS connectivity between gateways on port 443. Configure firewall rules, VPC peering, or VPN tunnels as appropriate for your security posture.