ConfigureOptions
Properties
Section titled “Properties”allowDirectOpenAIEndpoint?
Section titled “allowDirectOpenAIEndpoint?”
optionalallowDirectOpenAIEndpoint?:boolean
modelProfiles?
Section titled “modelProfiles?”
optionalmodelProfiles?:Record<string,string[]>
Named model profiles: a profile name mapped to an ordered list of target ids
(openai:gpt-5.2, or an on-device provider’s id). A request opts in with
TaskRequest.modelProfile; routing then stays within that list, in that order after
placement constraints. Omitted, every request routes within the built-in auto profile —
every registered target — and naming any other profile fails the request.
auto cannot be redefined, and a profile must list at least one target, each once;
configure() rejects a configuration that breaks either rule.
optionalonnx?:OnnxProviderBootstrapOptions
Web only; native registers its own on-device provider.
openAI?
Section titled “openAI?”
optionalopenAI?:OpenAIProviderBootstrapOptions
systemModel?
Section titled “systemModel?”
optionalsystemModel?:SystemModelProviderBootstrapOptions
Web only; native registers its own on-device provider.
IndeRun — open-source AI execution for cross-platform apps. Built and maintained by Independo GmbH (opens in new tab), supported by netidee (opens in new tab).
MIT-licensed SDK · No SDK usage telemetry.
© 2025–2026 Independo GmbH