AI Stays Local

DocumentationTrust

Troubleshooting

The failures worth naming before you meet them.

The runtime is not readyA large model takes time to load. Ask the health endpoint rather than restarting: it distinguishes a slow start from a dead process.
Out of memoryThe model is larger than the machine can hold. Move to a smaller validated profile.
The port is busySomething else holds 5000. Map a different host port; the container keeps its own.
Authorisation failedThe token is per-machine. Re-read it from the machine running the runtime rather than reusing another.
Docker cannot see the GPUThe NVIDIA container runtime has to be installed and passed through. Without it the container runs on CPU.
macOS containers are slowA container on macOS cannot reach Metal, so it is CPU-bound. The desktop application is the right route on a Mac.
A document search finds nothingRetrieval is lexical. Try the words the document itself would use. Check the collection indexed the folder you meant.
Streaming looks stuckDelivery is buffered rather than token-native, so text can arrive in groups.

When sending logs, read them first. Remove tokens, file paths and anything from a client document before it leaves your machine.

Last updated 2026-09-22T10:05:46-04:00 · Request access

These pages describe the contract: ports, endpoints, volumes, the permission model and the behaviour you can expect. The command reference for the CLI is published with the build each tester receives, so that it matches the binary in their hands rather than a page written ahead of it.

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