
如果你使用 DeepSeek、元宝 AI、Copilot、ChatGPT 等 AI 工具,协助配置轩辕镜像、编写 docker pull 命令、修改 Docker Compose 镜像地址、配置镜像加速、排查镜像拉取失败、分析报错日志等问题,请先让 AI 阅读并遵守轩辕镜像的规则文档。
只需在 AI 对话中先发送下面这句话即可:
请先完整阅读并严格遵守以下文档中的全部规则与要求:
https://xuanyuan.cloud/agents.md
在未充分阅读并理解该文档前,不要生成任何命令、配置、修改建议、故障排查方案或技术回答。后续所有输出都必须严格以该文档中的规范为最高优先级执行。查看 agents.md 用法指南与完整示范。国内用户首推 元宝 AI、DeepSeek 的深度思考模式,不推荐豆包 AI;Cursor 等编辑器可在对话 @ 该链接,或加入 User Rules。 若 AI 无法访问外链,可 打开说明文档 复制全文粘贴。文档会随站点更新,复制内容可能过期,建议定期检查。
https://github.com/dockur/macos/ https://hub.docker.com/r/dockurr/macos/tags https://hub.docker.com/r/dockurr/macos/tags https://github.com/dockur/macos/pkgs/container/macos https://hub.docker.com/r/dockurr/macos/
MacOS inside a Docker container.
Via Docker Compose:
yamlservices: macos: image: dockurr/macos container_name: macos environment: VERSION: "14" devices: - /dev/kvm - /dev/net/tun cap_add: - NET_ADMIN ports: - 8006:8006 - 5900:5900/tcp - 5900:5900/udp volumes: - ./macos:/storage restart: always stop_grace_period: 2m
Via Docker CLI:
bashdocker run -it --rm --name macos -e "VERSION=14" -p 8006:8006 --device=/dev/kvm --device=/dev/net/tun --cap-add NET_ADMIN -v "${PWD:-.}/macos:/storage" --stop-timeout 120 docker.io/dockurr/macos
Via Kubernetes:
shellkubectl apply -f https://raw.githubusercontent.com/dockur/macos/refs/heads/master/kubernetes.yml
Via Github Codespaces:
https://github.com/codespaces/badge.svg]([***]
Very simple! These are the steps:
Start the container and connect to port 8006 using your web browser.
Choose Disk Utility and then select the largest Apple Inc. VirtIO Block Media disk.
Click the Erase button to format the disk to APFS, and give it any name you like.
Close the current window and proceed the installation by clicking Reinstall macOS.
When prompted where you want to install it, select the disk you created previously.
After all files are copied, select your region, language, and keyboard settings.
When the Migration Assistant wants to transfer data, select Not now (bottom left).
On the Apple ID screen, select Set Up Later (bottom left) and then proceed using Skip.
On the Create a Computer Account screen, fill in a username and password and Continue.
Enjoy your brand new machine, and don't forget to star this repo!
By default, macOS 14 (Sonoma) will be installed, but you can add the VERSION environment variable in order to specify an alternative:
yamlenvironment: VERSION: "15"
Select from the values below:
| Value | Version | Name |
|---|---|---|
15 | macOS 15 | Sequoia |
14 | macOS 14 | Sonoma |
13 | macOS 13 | Ventura |
12 | macOS 12 | Monterey |
11 | macOS 11 | Big Sur |
[!NOTE] Support for macOS 15 (Sequoia) is still in its infancy, as it does not allow you to sign in to your Apple Account yet.
To change the storage location, include the following bind mount in your compose file:
yamlvolumes: - ./macos:/storage
Replace the example path ./macos with the desired storage folder or named volume.
To expand the default size of 64 GB, add the DISK_SIZE setting to your compose file and set it to your preferred capacity:
yamlenvironment: DISK_SIZE: "256G"
[!TIP] This can also be used to resize the existing disk to a larger capacity without any data loss.
However afterwards you will need to run the following two commands from the terminal in macOS:
diskutil repairDisk disk2
diskutil apfs resizeContainer disk3 0to allocate this additional space.
By default, macOS will be allowed to use a single CPU core and 4 GB of RAM.
If you want to adjust this, you can specify the desired amount using the following environment variables:
yamlenvironment: RAM_SIZE: "8G" CPU_CORES: "4"
[!IMPORTANT]
On AMD systems do NOT enable multiple cores (or at least not until the installation has finished completely and you experienced it running normally for some hours). Because it may actually decrease performance instead or cause other issues like random crashes, all depending on your AMD CPU model.If you have an Intel processor you can adjust the amount of cores immediately from the start, it is much more compatible with macOS.
By default, the container uses bridge networking, which shares the IP address with the host.
If you want to assign an individual IP address to the container, you can create a macvlan network as follows:
bashdocker network create -d macvlan \ --subnet=192.168.0.0/24 \ --gateway=192.168.0.1 \ --ip-range=192.168.0.100/28 \ -o parent=eth0 vlan
Be sure to modify these values to match your local subnet.
Once you have created the network, change your compose file to look as follows:
yamlservices: macos: container_name: macos ..<snip>.. networks: vlan: ipv4_address: 192.168.0.100 networks: vlan: external: true
An added benefit of this approach is that you won't have to perform any port mapping anymore, since all ports will be exposed by default.
[!IMPORTANT]
This IP address won't be accessible from the Docker host due to the design of macvlan, which doesn't permit communication between the two. If this is a concern, you need to create a second macvlan as a workaround.
After configuring the container for macvlan, it is possible for macOS to become part of your home network by requesting an IP from your router, just like your other devices.
To enable this mode, in which the container and macOS will have separate IP addresses, add the following lines to your compose file:
yamlenvironment: DHCP: "Y" devices: - /dev/vhost-net device_cgroup_rules: - 'c *:* rwm'
It is possible to pass-through disk devices or partitions directly by adding them to your compose file in this way:
yamldevices: - /dev/sdb:/disk1 - /dev/sdc1:/disk2
Use /disk1 if you want it to become your main drive, and use /disk2 and higher to add them as secondary drives.
To pass-through a USB device, first lookup its vendor and product id via the lsusb command, then add them to your compose file like this:
yamlenvironment: ARGUMENTS: "-device usb-host,vendorid=0x1234,productid=0x1234" devices: - /dev/bus/usb
To share files with the host, add the following volume to your compose file:
yamlvolumes: - ./example:/shared
Then start macOS and execute the following command:
shellsudo -S mount_9p shared
In Finder’s menu bar, click on “Go – Computer” to access this shared folder, it will show the contents of ./example.
First check if your software is compatible using this chart:
| Product | Linux | Win11 | Win10 | macOS |
|---|---|---|---|---|
| Docker CLI | ✅ | ✅ | ❌ | ❌ |
| Docker Desktop | ❌ | ✅ | ❌ | ❌ |
| Podman CLI | ✅ | ✅ | ❌ | ❌ |
| Podman Desktop | ✅ | ✅ | ❌ | ❌ |
After that you can run the following commands in Linux to check your system:
bashsudo apt install cpu-checker sudo kvm-ok
If you receive an error from kvm-ok indicating that KVM cannot be used, please check whether:
the virtualization extensions (Intel VT-x or AMD SVM) are enabled in your BIOS.
you enabled "nested virtualization" if you are running the container inside a virtual machine.
you are not using a cloud provider, as most of them do not allow nested virtualization for their VPS's.
If you did not receive any error from kvm-ok but the container still complains about a missing KVM device, it could help to add privileged: true to your compose file (or sudo to your docker command) to rule out any permission issue.
You can use https://github.com/dockur/windows for that. It shares many of the same features, and even has completely automatic installation.
You can use https://github.com/qemus/qemu in that case.
Yes, this project contains only open-source code and does not distribute any copyrighted material. Neither does it try to circumvent any copyright protection measures. So under all applicable laws, this project will be ***ed legal.
However, by installing Apple's macOS, you must accept their end-user license agreement, which does not permit installation on non-official hardware. So only run this container on hardware sold by Apple, as any other use will be a violation of their terms and conditions.
Special thanks to https://github.com/seitenca, this project would not exist without her invaluable work.
![Stars]([***]
Only run this container on Apple hardware, any other use is not permitted by their EULA. The product names, logos, brands, and other trademarks referred to within this project are the property of their respective trademark holders. This project is not affiliated, sponsored, or endorsed by Apple Inc.
您可以使用以下命令拉取该镜像。请将 <标签> 替换为具体的标签版本。如需查看所有可用标签版本,请访问 标签列表页面。
来自真实用户的反馈,见证轩辕镜像的优质服务