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
# macOS Apple Silicon overlay for continue.
# On macOS, llama-server runs natively on the host (replicas: 0 in Docker).
# The macOS core overlay provides a `llama-server-ready` sidecar that polls
# the native llama-server via host.docker.internal. Containers that would
# normally depend on `llama-server: service_healthy` must instead wait on
# the sidecar, mirroring the open-webui pattern in
# ods/installers/macos/docker-compose.macos.yml.
services:
continue:
depends_on:
llama-server-ready:
condition: service_healthy