Skip to documentation
Documentation navigation

Documentation navigation

Documentation / modules

Inference

Invoke and stream model requests through explicit descriptors, codecs, retries, and a local gateway.

developer

Repository

FieldValue
Repositorygithub.com/looprig/inference
Versionv0.12.0
GitHublooprig/inference

Description

Invoke and stream model requests through explicit descriptors, codecs, retries, and a local gateway.

Where it fits

Inference is useful on its own when a Go application needs provider-neutral model requests, streaming, codecs, retries, routing, or a local model gateway. Within Looprig, it supplies the model boundary for Harness, Eval, Tools, and Workflows. Inference moves model data; it does not own agent sessions or provider credential catalogs.

Dependencies

Dependents

← back to documentation