Coolify. Cited, not measured by AMDai. Docs checked 2026-10-13. Do not invent a release pin.
Self-hosted artifacts and dashboards. Official Coolify is an open-source control plane for deploying Docker workloads on servers you own. Cited, not measured by AMDai. Not an OpenAI-shaped /v1 chat client.
What it’s for
Host the dashboards and artifacts a lab already produces. Shannon’s write-up is why it sits next to the harness catalog. Not used on the local desktop.
More on the connect page.
Prove http://127.0.0.1:8080/v1/models first.
Coolify — not an LLM /v1 client
# Cited, not measured by AMDai.
# Coolify is a self-hosted control plane for Docker workloads.
# It does not speak llama-server http://127.0.0.1:8080/v1 or Strata.
# Official docs: https://coolify.io/docs/core/what-is-coolify
# Shannon’s lab write-up is why this row exists: /labs/shannon
Not a llama-server /v1 attach. Cited from Shannon’s How I run my Lab — not used on the local desktop.
Coolify — not an LLM /v1 client
# Cited, not measured by AMDai.
# Coolify is a self-hosted control plane for Docker workloads.
# It does not speak llama-server http://127.0.0.1:8083/v1 or Strata.
# Official docs: https://coolify.io/docs/core/what-is-coolify
# Shannon’s lab write-up is why this row exists: /labs/shannon
Not a llama-server /v1 attach. Cited from Shannon’s How I run my Lab — not used on the local desktop.