oremi-akorin 1.0.0b8

Natural-language gateway for the Oremi ecosystem, routing HTTP and MQTT requests to the appropriate AI-powered services.

Oremi Akọrin

Oremi Akọrin is the natural-language gateway for the Oremi ecosystem. It accepts user requests over HTTP or MQTT, uses a large language model (LLM) to understand, normalize, and classify them, then intelligently routes each request to the appropriate Oremi service. Whether the request concerns weather, reminders, podcasts, radio, smart-home devices, or general conversation, Akọrin preserves the user's original language and returns a natural response while coordinating the underlying services on their behalf.

The name Akọrin comes from the Yoruba language and means "singer" or "one who sings." In the Oremi ecosystem, the name symbolizes a component that gives voice to user intent. Rather than performing every task itself, Akọrin listens, interprets, and orchestrates communication between specialized services, acting as the expressive voice and natural-language entry point of the platform.

Documentation

All project documentation—including architecture details, configuration reference, and the Home Assistant integration guide—can be found at: https://demsking.gitlab.io/oremi-akorin/

Development

Oremi Device is built with Python and uses uv for dependency management. The project follows standard Python development practices with type hints, linting, and automated testing.

For detailed information on setting up your development environment, running tests, code style guidelines, and the pull request process, please refer to CONTRIBUTING.md.

,## Versioning

This project adheres to Semantic Versioning (SemVer). Version numbers follow the MAJOR.MINOR.PATCH format:

• MAJOR version increments for incompatible API changes
• MINOR version increments for backward-compatible new functionality
• PATCH version increments for backward-compatible bug fixes

The current version can be found in pyproject.toml or by running:

oremi-akorin --version

Pre-release versions (alpha, beta, release candidates) may be published to PyPI for testing purposes and are clearly marked with version suffixes.

License

Licensed under the Apache License, Version 2.0. See LICENSE.