localai

localai: Self-hosted OpenAI-compatible API for local LLM inference and embeddings

Deploy from this page: TryDirect provisions the server, starts the services, generates the deployment credentials and wires the 1 containers together. Nothing is shared between deployments and no secrets ship with the stack.

What's included

Service	Port	Description
app	8080 (public)	localai/localai:latest

What you configure

• Domain (commonDomain): the hostname the stack is served on
• Defaults provided: DEBUG, MODELS_PATH, THREADS ship prefilled and can be adjusted in the deploy form

Requirements

• A cloud account connected to TryDirect (the deploy form provisions

the server) or one of your own servers

• A server that fits 1 containers (2 GB RAM or more recommended)
• A DNS record for the domain you set in the deploy form

Alternative: deploy with the Stacker CLI

Everything above also works from the command line:

git clone https://github.com/trydirect/awesome-selfhosted-stacker.git
cd awesome-selfhosted-stacker/stacker-projects/localai

# Generate secrets
cp .env.example .env
./scripts/generate-secrets.sh

# Deploy
stacker deploy