> ## Documentation Index
> Fetch the complete documentation index at: https://omniference.henrikdev.xyz/llms.txt
> Use this file to discover all available pages before exploring further.

# Omniference

> A multi-protocol inference engine with provider adapters

Omniference is a flexible, multi-protocol inference engine written in Rust. It gives you one unified interface to AI model providers such as Ollama and OpenAI.

## Features

* **Multi-provider support:** Ollama, OpenAI and an extensible adapter architecture
* **Streaming:** real-time streaming responses from models
* **OpenAI-compatible API:** a drop-in replacement for OpenAI's API
* **Multiple interfaces:** HTTP server, Discord bot, CLI and library usage
* **Embeddable:** integrates into existing Axum applications
* **Type-safe:** strong typing throughout, built on Tokio

## Architecture

* **Core layer:** router, adapters and types (pure inference logic)
* **Service layer:** provider management and model resolution
* **Interface layer:** HTTP APIs, Discord bot, CLI
* **Application layer:** full server or embeddable components

> [card] [Quickstart](https://omniference.henrikdev.xyz/quickstart.md)
>
> Add Omniference to your project.

> [card] [Source code](https://github.com/Henrik-3/omniference)
>
> Omniference on GitHub (MIT license).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.