a private ai assistant for iOS
silo is a privacy-first application that allows you to chat with Large Language Models (LLMs) locally on your device. It ensures absolute privacy and security by keeping all data processing local without any tracking or monitoring. Available on the App Store
- LLM Chat: Works with Open-Source LLM models like Llama, Mistral, Smol, Phi, and even custom GGUF models from Hugging Face.
- Secure: Chat with LLM models locally, ensuring no data leaves your device. Your messages are private and cannot be seen by anyone, including us.
- Offline: Use Silo anytime, anywhere without an internet connection. All information stays on your device; no data is sent to the cloud.
- Anonymous: No login or personal information required. There is no usage statistics or tracking, ensuring absolute anonymity.
- Fast: Provides quick answers through local processing for rapid query responses.
- Xcode installed on macOS
-
Clone the repository:
git clone https://github.com/stevederico/silo.git cd silo -
Build and run the project on your device or simulator.
- Open the Silo application.
- Tap Settings => Download a model. i.e llama3.2-3B
- Tap Load Model and Enjoy instant AI assistance without compromising your privacy.
We welcome contributions from the community! Please follow these guidelines:
- Fork the repository.
- Create a new branch for your feature or bug fix:
git checkout -b feature/your-feature-name
- Make your changes and commit them with descriptive messages.
- Push your branch to your fork:
git push origin feature/your-feature-name
- Open a pull request against the
masterbranch.
This project is licensed under the MIT License. See the LICENSE file for details.
- Based on llama.cpp project founded by Georgi Gerganov.
For any questions or support, please open an issue in this repository.