Actual AI
A self-hosted AI & Machine Learning app you can run on your own server.
Actual AI is a self-hosted AI and machine-learning tool that you run on your own server instead of renting it as a cloud service. Self-hosting it means no per-user subscription and no third-party cloud holding your information.
Development happens in the open on GitHub; the repository has collected 521 stars so far. Repository activity was last recorded on Sep 7, 2026, and the project is classed as actively maintained in our snapshot. It is listed as a companion app — a tool that extends or helps you manage a self-hosted service rather than replacing it. It is available for Server.
Before you switch
Self-hosted AI tools reward a quick hardware check: chat interfaces are light, but local model runners need RAM and, ideally, a GPU. Start with a small model, confirm the interface connects to it, and only then scale up. Running AI on your own server keeps prompts and documents on hardware you control.
Like every project listed on SelfHosted, Actual AI is developed in the open — you can read the code, follow development, and even contribute. Check the system requirements and the project’s own documentation linked on this page before installing.