A.I. designed for you, only for you.
Run powerful language models locally. Keep your conversations private. Switch between models without reinstalling.
See Arbiter in Action
Why cloud AI falls short
Your data leaves your device
Every prompt you send to a cloud AI is processed on someone else's servers, logged, stored, and potentially used to train future models.
Requires internet to function
Cloud AI stops the moment your connection drops. On a flight, in a dead zone, or on a slow network, you are left without assistance.
Expensive and metered
Premium AI is locked behind monthly subscriptions and per-query fees. Your usage is tracked, throttled, and billed at every turn.
Key Features
Fully On-Device AI
Powered by MLX and GGUF frameworks, Arbiter runs open-source models directly on your iPhone's Apple Silicon. No API calls, no server round-trips. Works on airplane mode and in areas with no signal.
Live Web Search
Combine on-device inference with live web results. Arbiter pulls up-to-date information from the web and reasons over it locally, so your searches stay private while your answers stay current.
Flexible Model Management
Download and switch between quantized open-source models: Gemma, LLaMA, Mistral, and more. Balance speed vs. intelligence, manage storage, and tune performance to your device. You own the models.
File Upload & Context
Drop in PDFs, notes, or documents and ask questions about them. Arbiter summarizes and reasons over your files entirely on-device. Your private knowledge assistant, zero cloud required.
Siri & iOS Integration
Trigger Arbiter hands-free via Siri Shortcuts using App Intents. Ask questions by voice and get spoken or text responses, all private and built into your iOS workflow.
Image Understanding
Upload photos directly into your conversations. Arbiter can describe, analyze, and answer questions about your images, processing everything on your device with no data sent to the cloud.
Arbiter vs. Cloud AI
Our Mission
Arbiter is redefining the future of AI chat. We believe in empowering individuals and organizations with tools that offer choice, control, and clarity. By running AI locally and giving users ownership of their data, Arbiter puts privacy and power back into your hands.
FAQ
Is my data private? ⌄
Yes. Everything is processed and stored on your device. Your chats and files never leave your phone unless you explicitly choose to share them. We do not store, log, or sell your data. Your information stays 100% under your control.
Do I need an internet connection to use the app? ⌄
No. Once installed, the app works entirely offline. You can use it on airplanes, in remote areas, or without Wi-Fi, while still getting fast and responsive answers.
How does offline AI work? ⌄
The app uses optimized large language models (LLMs) that run locally on your device's processor. These models are pre-downloaded and don't require server access, which means your requests are processed instantly without sending them to the cloud.
What devices are supported? ⌄
Currently, the app supports modern iPhones and iPads running iOS 16 or later, with best performance on devices equipped with Apple Silicon chips (A14 Bionic or newer). Most models will require a device with more than 4 GB of RAM.
What AI models are available? ⌄
You can choose from a range of open-source LLMs. The app supports switching models at any time so you can balance speed, accuracy, and device performance.