호환 프로그램
omm이 설치하거나 연결할 수 있는 로컬 AI 러너와 플랫폼별 자동화 범위를 README에서 미러링합니다.
raw.githubusercontent.com에서 실시간 동기화
omm이 설치하거나 연결할 수 있는 로컬 AI 러너와 플랫폼별 자동화 범위를 README에서 미러링합니다.
raw.githubusercontent.com에서 실시간 동기화
The first bare omm run on a fresh install (or omm setup any time after) shows a hardware summary and a checklist of local AI runners. Checking one that omm knows how to install runs its official installer with live progress in the terminal; checking one it doesn't yet automate on your platform prints a link instead. Automation coverage today:
| Runner | Automated on | Manual elsewhere |
|---|---|---|
| Ollama | macOS (Homebrew), Windows (WinGet) | Linux |
| LM Studio | macOS (Homebrew), Windows (WinGet) | Linux |
| Jan | macOS (Homebrew), Windows (winget), Linux (Flatpak) | wherever that package manager isn't installed |
| AnythingLLM | macOS (Homebrew) | Linux, Windows |
| Msty | macOS (Homebrew) | Linux, Windows |
| KoboldCpp | — | All platforms; automatic artifacts lack a pinned checksum |
| text-generation-webui | — | All platforms; install manually from the official releases |
Every currently-installed runner is also listed (marked as already installed, not selectable) rather than hidden, so the checklist always reflects what omm actually detects on the machine.
See engine management for operation previews, package ownership checks, and verification limits.