What makes Refact.ai different from Copilot for a developer who cares about privacy?

I work on client projects that involve sensitive codebases and I have always been uncomfortable with the idea of sending proprietary code to a third-party cloud service for AI completions. GitHub Copilot is useful but the fact that code snippets are sent to Microsoft's servers is a hard no for some of the clients I work with, and it is a blocker to adopting AI coding tools more broadly on those projects.

[Refact.ai](http://Refact.ai) has come up as an option that can be self-hosted, which would address the privacy concern entirely. But I want to make sure that the trade-off in terms of completion quality is not so large that the privacy benefit is not worth it. I have seen self-hosted AI coding tools before and some of them have been significantly worse than the cloud alternatives to the point where they create more friction than they remove.

Has anyone run [Refact.ai](http://Refact.ai) on their own infrastructure and found the completion quality acceptable for professional development work? I want to know what the hardware requirements look like for a small team of developers, how the setup and maintenance compares in complexity to just using a cloud service, and whether the fine-tuning feature that lets you train on your own codebase is practical enough to be worth the effort for a team of our size.