OmniParser Docker & Self-Hosted Deployment

GitHub

A simple screen parsing tool towards pure vision based GUI agent

25,539 stars Jupyter Notebook 3 files · ~3,570 tokens
RAW Compose
1. Pull Image (DOCKERHUB) docker pull library/windows-local
2. Docker Run (1-Click Launch) docker run -d --name omniparser -p 8006:8006 --restart always windows-local
3. Podman Run podman run -d --name omniparser -p 8006:8006 --restart always windows-local
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/library/windows-local:latest
5. ORAS Pull (OCI Artifact) oras pull windows-local
6. Compose Deployment docker compose up -d
omnitool/omnibox/compose.yml
Download .yml 
services:
  windows:
    image: windows-local
    container_name: omni-windows
    privileged: true
    environment:
      RAM_SIZE: "8G"
      CPU_CORES: "4"
      DISK_SIZE: "20G"
    devices:
      - /dev/kvm
      - /dev/net/tun
    cap_add:
      - NET_ADMIN
    ports:
      - 8006:8006                 # Web Viewer access
    volumes:
      - ./vm/win11iso/custom.iso:/custom.iso
      - ./vm/win11setup/firstboot:/oem
      - ./vm/win11setup/setupscripts:/data
      - ./vm/win11storage:/storage