OmniRouter

@OMNIDIMEN

Unify multiple model services into a local interface.

You can first add model services, API Keys and model groups to the OmniRouter web backend, and then fill in a fixed address it provides into the companion front end. All subsequent requests go through this address, and OmniRouter decides which model to hand it over to.

Project address (can be copied to AI):https://github.com/OmniDimen/OmniRouter

PROJECT INTRO

Project introduction

OmniRouter is a model relay station that you install on your own computer. You can add OpenAI, OpenRouter, DeepSeek and other compatible services to its web backend, and uniformly save different model addresses and API Keys.

After the setup is complete, the companion front-end only needs to fill in a fixed API address provided by OmniRouter. Each chat request comes here first, and then it selects the model that is actually responsible for answering based on model grouping, task type, order, randomness or weight.

Suitable for:People who use multiple model services at the same time and do not want to repeatedly configure and manually change lines in each companion front end.
Usage:Add Provider, API Key, model and group, and then fill in the unified API address displayed on the dashboard into the companion front end.
Automatic selection:Model groups can be selected by problem type, and sequential, random, and weight rotation are also supported.
Safety reminder:The API Key is currently stored in the local SQLite database in clear text; do not share the database or expose the service directly to the public network.

◌

COMMENTS & FEEDBACK

Comments and Feedback

Guest message · Will be published after review

People who have used this project can come back and tell newcomers: which platform it ran on, whether there were any pitfalls during the installation, and what the actual experience was like. The current version is in guest mode, and you do not need to register an account to leave a message.

Reading public comments...

SOURCE & CREDIT

Atlas is responsible for the introduction and navigation, and the use still returns to the original author.

We do not mirror project files, nor do we intercept author traffic. For installation, download, version updates and the latest instructions, please refer to the project page provided by the original author.

Project link ↗