Overview
AI Stays Local runs an open-weight model on hardware you control. You grant access to folders you choose, ask questions in ordinary language, and check each answer against the file and page it cites.
What it is
A local runtime and the product around it: a desktop application, a container image, a command line and an OpenAI-compatible HTTP endpoint that listens on loopback. One runtime, four ways to reach it.
What it is not
- Not a hosted service. There is no account, and no request leaves your machine during local inference.
- Not a wrapper around someone else’s chat interface.
- Not a claim to match a frontier hosted model. Which models run, and how fast, depends on your hardware.
Where things stand
| Surface | State |
|---|---|
| Runtime | Operational for approved testers. Local inference on hardware you control. |
| Cited document answers | Operational for approved testers. Answers that name the file and page, or decline. |
| Desktop app | Planned. The guided experience. Not built yet; no installer exists. |
| Docker | Planned. Not published yet; no image exists. |
| CLI and local API | Private beta. Distributed to selected testers. |
| Consumer macOS build | Planned. Not built, and not measured. |
| Consumer Windows build | Planned. Not built, and not measured. |
| Enterprise deployment | Planned. On infrastructure the customer owns. Not offered yet. |
| Qwen3.5 122B-A10B | Private validation only. Interactive, validated on the recorded professional hardware profile. Not available to obtain. |
| GLM-5.2 744B | Research demonstration. Executed by AI Stays Local at 0.17 tokens per second. Not usable interactively, and not available. |