ai-agent

OmniRouter

Name: OmniRouter
Author: omnilabs-ai

96 stars+13★ this week26 forksPythonUpdated 10/22/2026100% free · open source

What it does

OmniRouter is an AI agent that routes and orchestrates tasks across multiple AI models and services to automate complex workflows.

When to use it

•You need to automate a workflow that involves multiple AI models, such as language translation, text summarization, and sentiment analysis.
•You want to integrate multiple AI services, like language models, computer vision models, and speech recognition models, into a single workflow.
•You need to route tasks to different AI models based on the input data, such as routing text data to a language model and image data to a computer vision model.

Ready-to-paste prompt

python run.py -c config.json -w workflow.json -i 'Hello, how are you?' -m lang_translation -s google_translate

Heads up: You need to have a compatible Python version (3.8 or higher) and install the required dependencies, including `torch` and `transformers`, before running the OmniRouter.

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🔑 Needs an API key

Works after you add credentials — the setup agent will ask you for them.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/omnirouter && curl -fsSL https://workflowstacks.com/api/skills/omnirouter/claude-skill -o ~/.claude/skills/omnirouter/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How OmniRouter works

Codeflow

Free to inspect

OmniRouter is a medium Python project (~4.2k lines across 42 code files, plus 1 test files). Setup is light: installs like a normal app — add your API keys. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size

Medium codebase

~4.2k lines · 42 code files · 35 min skim

Setup

One-command install

Installs like a normal app — add your API keys. Reading the code is optional.

Runs on

Python

Needs API keys (.env)

Python 100%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
pyproject.toml
Dependencies and the commands it exposes
3
.env.example
The API keys and settings you must provide
4
src/omni/__init__.py
Inside src/ — the main logic begins here

What's in each folder

src/Core code — the actual logic2 files

docs/Documentation6 files

serverRouter/Folder38 files

testLib/Folder12 files

.github/CI / automation (GitHub Actions)2 files

tests/Tests — proof it works1 files

READMEHas testsDocumentedCI checksApache-2.0 licenseUpdated this month