Connect. Build. Keep going.

Practical guides for your chat clients and applications.

Garage is currently available to invited testers. These guides explain the connection path; check model availability and your account before relying on a serving endpoint.

Connect SillyTavern to UnsavedAi

Use a hosted AI model for character conversations without running a GPU yourself.

Connect Open WebUI to a hosted AI API

Keep your chat interface in Open WebUI and use UnsavedAi as a custom model provider.

Use UnsavedAi with LibreChat

Configure a custom Chat Completions provider for your LibreChat installation.

Build an app with the Chat Completions API

Understand the request shape, authentication, and model selection for a custom chat application.

Manage context for AI roleplay and long conversations

Budget conversation history, character cards, and response length within a model context window.

Handle streaming, queues, and API retries

Build a chat experience that handles waiting, cancellation, and temporary capacity errors.

Manage API keys across your chat apps

Use separate named credentials for different clients while keeping one UnsavedAi account.