AI Stays Local

Docker edition

The same runtime, in a container you control.

Docker is a first-class way to run AI Stays Local, not a technical footnote. The same runtime that powers the desktop app runs in a container with explicit volumes, explicit limits and a loopback port.

How it is put together

Application image

Immutable. Updating means running a new tag; rolling back means running the previous one.

Model volume

Weights live in a volume you control, so a container rebuild does not re-download gigabytes.

Document mounts

Mounted read-only. The runtime can read what you grant and cannot write to it.

Index volume

The local index is a separate volume, so you can remove it without touching your documents.

Loopback port

Bound to localhost by default. Exposing it on a network is a decision you make explicitly.

Optional NVIDIA runtime

GPU where it is available and validated; CPU mode otherwise.

Health endpoint

So an orchestrator can tell a slow start from a failed one.

Resource ceilings

Memory and CPU limits, because an inference process without a ceiling will find one.

Preview interface

What running it looks like.

Preview interface — image access is currently invite-only.

Run the runtime with your models and documents
docker run -d --name aisl \
-p 127.0.0.1:11434:11434 \
-v aisl-models:/models \
-v aisl-index:/data \
-v /path/to/documents:/documents:ro \
--memory 32g --cpus 16 \
aistayslocal/runtime:<tag>
Preview interface — image access is currently invite-only.
With a supported NVIDIA accelerator
docker run -d --gpus all \
...same volumes and limits... \
aistayslocal/runtime:<tag>
Preview interface — image access is currently invite-only.
Targets

Where the container runs, and where it does not.

Linux ARM64

The validated platform. Measurements on this site were taken here.

Validated

Linux x86-64

Target for the same image. Under validation.

Under validation

NVIDIA GPU

Where the accelerator is present and the profile has been validated.

Under validation

CPU mode

Available wherever the container runs; speed depends on the machine.

Validated

macOS via Docker Desktop

Containers on macOS cannot reach Metal acceleration, so a container is CPU-bound there. The desktop app is the right route on a Mac.

Known limitation

Windows via WSL2

Subject to validation.

Under validation
Available through a controlled private beta. Larger model profiles are added as they complete hardware validation.