Mission

Sidekick is a local-first native LLM application for macOS. Its main goal is to make open, local, private, and contextually aware AI applications accessible to more people.

We believe this is critical because using AI locally offers distinct advantages, such as enhanced privacy and the ability to work offline.

For instance, professionals handling sensitive data, such as lawyers or researchers, can use local models to process information securely without cloud exposure. Local LLMs can be used to audit tax documents, without the worry of exfiltrating personal data to the cloud.

Local LLMs also ensure compliance with data sovereignty laws and enable personalized, context-aware interactions by analyzing local files and content.

Sidekick exists to meet the following goals.

• No configuration. Usable by people who haven't heard of models, prompts, or LLMs.
• Performance and simplicity over developer experience or features. Notes not Word, Swift not Electron.
• Local first. Core functionality works without an internet connection, with extensibility options to leverage online models.
• No conversation tracking. Talk about whatever you want with Sidekick, just like Notes.
• Context aware. Understands and accesses your files, folders, and even content on the web.
• Open source. What's the point of running local LLMs if you can't audit that it's actually running locally?

Sidekick is subject to the MIT License. Source code and license details are available on the application's GitHub page.