Private AI for your documents

We built an AI assistant that answers questions about your company's documents in English and Arabic, and runs entirely on one computer: nothing is sent to the cloud.

The problem

Most companies would like AI to answer questions about their contracts, leases and policies, but cannot send those documents to a cloud service. Confidential files, client data and local data-protection rules all point the same way: the documents should stay inside the company.

Cloud AI tools are powerful, but every question and every uploaded file leaves your network. For many businesses in the UAE and the wider Gulf, that is the reason they have not started using AI at all.

What the assistant does

The assistant is a chat page, like the AI tools people already know, with one difference: the AI model runs on your own computer and keeps working with the internet switched off.

The assistant's chat page answering questions about a sample lease, in English and in Arabic
Questions about a sample lease, answered from the document in English and Arabic.

How your data stays private

Every step happens on the same computer, so no question or document is sent anywhere.

  1. You upload a PDF. The software reads the text and splits it into short passages.
  2. The passages are indexed. A small search model turns each passage into numbers and stores them in a local database.
  3. You ask a question. The software finds the passages that best match it, and calculates any dates the question needs.
  4. The AI writes the answer. The language model (Qwen3, 8 billion parameters) receives your question together with those passages, and answers from them.
  5. The answer appears word by word on the chat page.

Because the answer is built from your own document, the model does not have to rely on its memory. As our tests below show, that matters a great deal.

What we learned testing on a 10-year-old laptop

Bigger AI models write better Arabic, but none of the sizes we tested knew the facts reliably. We ran three sizes of the same model family (Qwen3) on the same questions: two on a 2014 HP laptop (Intel i5, 8 GB memory, no graphics card) running Ubuntu Linux, and one on a MacBook Pro (M3, 16 GB).

Model sizeMachineWriting speedEnglish questionArabic languageFacts about Abu Dhabi
1.7 billion2014 laptopabout 7 words/sCorrectBroken: mixed Arabic, English and VietnameseInvented
4 billion2014 laptopabout 3–4 words/sCorrectFluent, some errorsInvented
8 billionMacBook Pro M3not measuredCorrectCleanInvented

The lesson for businesses is clear: a private AI model should answer from your own documents, not from its memory. That is exactly how this assistant is designed.

What you need, and what comes next

Today the assistant runs on an Apple Silicon Mac (M1 to M4) with 16 GB of memory. No graphics card, server or cloud account is needed.

UseSuitable machine
English and Arabic, good qualityApple Silicon Mac with 16 GB memory (runs the 8-billion model)
Better answers, larger modelsMac with 24–32 GB memory
English only, simple questionsOlder or low-cost computers, with a smaller model

The project is a work in progress. Next on the roadmap:

Try it, or talk to us

The assistant is open source, built by Appetter co-founder Tariq Mumtaz. Technical readers can see the full code and run it themselves: github.com/tariq-mumtaz/local-ai-assistant.

The code is published under the AGPL-3.0 licence. Companies that want to use it inside their own products without publishing their changes can ask us for a commercial licence.

Want private AI on your own documents? Email [email protected] and we will help you choose the right hardware and set it up.