Why Magnitude?
- Fully private and offline Everything stays on your machine, including the models.
- Models for every machine Profiles your hardware and recommends the best models.
- Works out of the box No Ollama, model server, or inference setup to configure.
- Skills Extend Magnitude to work with Excel, PDFs, Chrome, and more.
- Free to run No token costs, API keys, subscriptions, or rate limits.
- Open source Apache 2.0 licensed, fully inspectable, and yours to modify.
The best local models. One agent.
FAQ
What is Magnitude?
Magnitude is an open source agent with local models built in. Everything runs directly on your machine.
How is Magnitude different from Ollama or Hermes?
Ollama runs local models. Hermes is an agent that can use local models. Magnitude combines both in one: it profiles your hardware, recommends and downloads models, then configures and runs them inside the agent. Nothing else to set up.
What hardware do I need?
There’s no fixed minimum. Magnitude profiles your hardware and recommends the best models for your machine. More memory lets you run larger models.
Does my data go to the cloud?
No. Your prompts and files stay on your machine.
Can Magnitude run completely offline?
Yes. Once Magnitude and a model are downloaded, you can use it without an internet connection.
Can I use models outside the catalog?
Yes. You can download compatible GGUF models from Hugging Face and use them in Magnitude.
Can I use my own inference server?
Yes. You can connect an OpenAI-compatible endpoint and use its models in Magnitude.
Put an agent on your machine.
npm install -g @magnitudedev/cli Backed by 