Module @metreeca/muse - v0.1.1
@metreeca/muse
AI tasks and shared services for @metreeca/muse.
A consumer sets up a @metreeca/gear executor, binding the models a job relies on to the implementations chosen for the run. The job's tasks then resolve each model through the locator, naming it by its contract rather than importing a concrete client.
Binding a different implementation leaves the job unchanged: the same job runs against a live provider, against recorded responses, or against any custom client honouring the same contracts.
Installation
npm install @metreeca/gear # the job executor
npm install @metreeca/muse # this package
Important
Node.js 22 or later is required.
Warning
TypeScript consumers must use "moduleResolution": "nodenext"/"node16"/"bundler" in tsconfig.json.
The legacy "node" resolver is not supported.
Usage
| Module | Description |
|---|---|
| @metreeca/muse | Model access contracts and shared services |
Support
- open an issue to report a problem or to suggest a new feature
- start a discussion to ask a how-to question or to share an idea
License
This project is licensed under the Apache 2.0 License – see LICENSE file for details.
AI tasks and shared services.
Defines the model facilities an AI job draws on, keeping the job independent of the provider it reaches: a job names a model by its contract rather than importing a concrete client, and a binding substitutes a stubbed, throttled or recorded implementation for the duration of an execution.
Jobs are set up and run with the executor, binder and service locator from @metreeca/gear: this package contributes the model services those primitives bind and resolve, not an execution runtime of its own.