Skip to content

Deployment Guide ​

GhostAI supports five deployment targets, each with different trade-offs for complexity, cost, and data residency. This guide covers every option with architecture diagrams and complete .env examples.

Deployment Targets at a Glance ​

TargetInfrastructureDatabaseLLM OptionsBest For
Native (Mac/Linux)Local processes + Docker PostgreSQLPostgreSQLOllama, llama-cppSolo development, air-gapped demos
Docker ComposeDocker containersPostgreSQL + RedisAny providerTeam development, on-premise
Production DockerDocker + Caddy (HTTPS)PostgreSQL + RedisAny providerSelf-hosted production
AWS ECSECS Fargate, RDS, ElastiCachePostgreSQL (RDS)Cloud providersEnterprise cloud
KubernetesHelm charts, K8sPostgreSQL + RedisAny providerMulti-tenant, high scale

Choosing a Deployment ​

LLM Provider Architecture ​

Every deployment uses the same three-layer LLM architecture. Each layer is independently configurable. GhostAI supports a multi-provider architecture with 11 direct providers, OpenRouter, and three local backends (Ollama, vLLM, llama-cpp):

Key insight: You can mix cloud and local. For example, use OpenAI for chat but llama-cpp for PII -- your sensitive data never leaves the machine even though chat uses the cloud.

Next Steps ​

SOC 2 Type II Certified | BAA Available | HIPAA-Ready