Private AI

The AI you can tell anything.

Last updated:

Because it runs on your device.

A cloud AI conversation starts by sending your words to a server, where the provider handles them under its own retention, review, and training settings. For a local Loci answer, the model runs on your device; the prompt and reply do not need a remote AI provider.

Incognito hides your history, not your question

A private browser window only hides where you've been from your own device. The question itself still goes out through your internet provider, across the internet, to a server that receives exactly what you typed.

A local Loci chat never makes that trip. No provider receives it, and no account is attached to it.

What runs on the device

  • Chat: understood and answered locally.
  • Voice: speech recognition runs on-device, except Windows voice typing, which may use Microsoft's online service under your Windows privacy settings.
  • Photos: image understanding happens on-device.
  • No account required for any of it.

It also keeps working with no internet connection. Coming from ChatGPT? Here is how a local model compares.

The online features are separate

Core chat and model inference stay on your device. Web search and live information go online: your settings decide whether Loci looks things up when a question needs current information or only when you ask. When it does, your device sends a search drawn from what you asked straight to the service that answers it, and for weather, scores and similar questions only what the request needs, such as a place. Loci may also open a few of the pages it finds, much as a browser would. Those services and websites see ordinary connection details such as your IP address. None of it passes through a Loci server, and your files and the rest of your chat history are not sent. The Privacy Policy explains what each online feature sends.

Where your chat goes
What mattersLociCloud AI
Where chat is processedLocal model inference runs on your device.Sent to remote servers to be answered.
Who receives your chatNo one. The model answers locally.A provider receives the prompt and handles it under its own retention and training settings.
AccountNone required for local AI.Usually tied to an account and an identity.

Choose local AI for your device

The private AI for Mac guide covers compatibility, offline chat and coding-agent access.

Choosing a model? Check measured speeds by device and model, with sample counts and measurement details.

Read how a local AI assistant works, or see how Loci compares with other apps.

Privacy questions

Does Loci send my chats to a server?

Local chats are processed on your device and are not uploaded to a Loci server in ordinary use. Online sources can send relevant question text directly to third-party providers when your source setting or request calls for them.

Can anyone read my conversations?

Local conversations are stored on your device. Loci does not receive your prompts or replies in ordinary use or use them to train AI models. If you use online sources, providers handle the query text they receive under their own policies.

Does local AI protect my chats if someone has my phone?

No. Running the model on your device keeps a chat from being sent to a provider. It does not protect a device that someone else can unlock, or one with malware on it. Use a passcode and keep the device updated.

Is Loci a private LLM app?

Yes. The LLM runs on your own device, so a local chat is answered there and is not uploaded to a Loci server in ordinary use. Web search is separate and goes online.

Do I need an account?

No account is required for local AI.

Is any feature online?

Model downloads and online sources use the internet. Sources may run automatically for eligible questions according to your source setting or when you ask for them. Core chat and model inference stay local.

For sensitive questions

Keep the question on your device.

Use Loci for the things you'd rather not hand to a cloud account.

Get Loci