ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.
Python ai-agentsamdcomfyuidockerllama-cppllmlocal-ain8nnvidiaopen-webuiragself-hostedspeech-to-textstrix-halotext-to-speechworkflow-automation
# CPU backend overlay for continue.
# Wait for the containerized llama-server before starting. Kept out of
# base compose.yaml because `depends_on` merges additively across overlays
# and the macOS (apple) backend runs llama-server natively with replicas: 0;
# a service_healthy condition on a 0-replica service would hang forever.
# See sibling compose.apple.yaml for the macOS-specific sidecar wait.
services:
continue:
depends_on:
llama-server:
condition: service_healthy