ODS names three machines and seven capabilities in one sentence. That gives you a grid with twenty one cells and no information about which of them are filled, so this page draws the grid and leaves it empty on purpose.
The first sentence puts the whole stack on hardware you already own, which is the difference between a subscription and a machine you can unplug.
Inference, chat, voice, agents, workflows, RAG, and images are seven separate engineering problems. Naming them all in one line sets a high bar for the install.
No model list, no hardware floor, no per-platform support table, no screenshot. The trending description publishes none of it.
Concept mock, not affiliated with the project. The GitHub Trending description on 31 August 2026 reads "Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation." The seven rows and three columns are those names in the order given. Every cell is left blank because the description does not say which capability runs on which platform.