This ongoing Docker Labs GenAI series explores the exciting space of AI developer tools. At Docker, we believe there is a vast scope to explore, openly and without the hype. We will share our explorations and collaborate with the developer community in real time. Although developers have adopted autocomplete tooling like GitHub Copilot and use chat, there is significant potential for AI tools to assist with more specific tasks and interfaces throughout the entire software lifecycle. Therefore, our exploration will be broad. We will be releasing software as open source so you can play, explore, and hack with us, too.
After restarting Claude Desktop, you can ask Claude to take a screenshot of any URL using a Headless Chromium browser running in Docker.
You can do the same thing for a Model Context Protocol (MCP) server that you’ve written. You will then be able to distribute this server to your users without requiring them to have anything besides Docker Desktop.
How to create an MCP server Docker Image
An MCP server can be written in any language. However, most of the examples, including the set of reference servers from Anthropic, are written in either Python or TypeScript and use one of the official SDKs documented on the MCP site.
For typical uv-based Python projects (projects with a pyproject.toml and uv.lock in the root), or npm TypeScript projects, it’s simple to distribute your server as a Docker image.
If you don’t already have Docker Desktop, sign up for a free Docker Personal subscription so that you can push your images to others.
Run docker login from your terminal.
Copy either this npm Dockerfile or this Python Dockerfile template into the root of your project. The Python Dockerfile will need at least one update to the last line.
Run the build with the Docker CLI (instructions below).
The two Dockerfiles shown above are just templates. If your MCP server includes other runtime dependencies, you can update the Dockerfiles to include these additions. The runtime of your MCP server should be self-contained for easy distribution.
If you don’t have an MCP server ready to distribute, you can use a simple mcp-hello-world project to practice. It’s a simple Python codebase containing a server with one tool call. Get started by forking the repo, cloning it to your machine, and then following the following instructions to build the MCP server image.
Building the image
Most sample MCP servers are still designed to run locally (on the same machine as the MCP client, communication over stdio). Over the next few months, you’ll begin to see more clients supporting remote MCP servers but for now, you need to plan for your server running on at least two different architectures (amd64 and arm64). This means that you should always distribute what we call multi-platform images when your target is local MCP servers. Fortunately, this is easy to do.
Create a multi-platform builder
The first step is to create a local builder that will be able to build both platforms. Don’t worry; this builder will use emulation to build the platforms that you don’t have. See the multi-platform documentation for more details.
Once the image is pushed, your users will be able to attach your MCP server to Claude Desktop by adding an entry to claude_desktop_config.json that looks something like:
This is a minimal set of arguments. You may want to pass in additional command-line arguments, environment variables, or volume mounts.
Next steps
The MCP protocol gives us a standard way to extend AI applications. Make sure your extension is easy to distribute by packaging it as a Docker image. Check out the Docker Hub mcp namespace for examples that you can try out in Claude Desktop today.
As always, feel free to follow along in our public repo.
This demo will use the Puppeteer MCP server to take a screenshot of a website and invert the colors using Claude Desktop and Docker Desktop. Doing this witho...
This ongoing Docker Labs GenAI series explores the exciting space of AI developer tools. At Docker, we believe there is a vast scope to explore, openly and without the hype. We will share our explorations and collaborate with the developer community in real time. Although developers have adopted autocomplete tooling like GitHub Copilot and use chat, there is significant potential for AI tools to assist with more specific tasks and interfaces throughout the entire software lifecycle. Therefore, our exploration will be broad. We will be releasing software as open source so you can play, explore, and hack with us, too.
In previous articles, we focused on how AI-based tools can help developers streamline tasks and offered ideas for enabling agentic workflows, like reviewing branches and understanding code changes.
In this article, we’ll explore our experiments around the idea of creating a Docker AI Agent — something that could both help new users learn about our tools and products and help power users get things done faster.
During our explorations around this Docker Agent and AI-based tools, we noticed that the main pain points we encountered were often the same:
LLMs need good context to provide good answers (garbage in -> garbage out).
Using AI tools often requires context switching (moving to another app, to a different website, etc.).
We’d like agents to be able to suggest and perform actions on behalf of the users.
Direct product integrations with AI are often more satisfying to use than chat interfaces.
At first, we tried to see what’s possible using off-the-shelf services like ChatGPT or Claude.
By using testing prompts such as “optimize the following Dockerfile, following all best practices” and providing the model with a sub-par but common Dockerfile, we could sometimes get decent answers. Often, though, the resulting Dockerfile had subtle bugs, hallucinations, or simply wasn’t optimized or didn’t use many of the best practices we would’ve hoped for. Thus, this approach was not reliable enough.
Data ended up being the main issue. Training data for LLM models is always outdated by some amount of time, and the number of bad Dockerfiles that you can find online vastly outnumbers the amount of up-to-date Dockerfiles using all best practices, etc.
After doing proof-of-concept tests using a RAG approach, including some documents with lots of useful advice for creating good Dockerfiles, we realized that the AI Agent idea was definitely possible. However, setting up all the things required for a good RAG would’ve taken too much bandwidth from our small team.
Because of this, we opted to use kapa.ai for that specific part of our agent. Docker already uses them to provide the AI docs assistant on Docker docs, so most of our high-quality documentation is already available for us to reference as part of our LLM usage through their service. Using kapa.ai allowed us to experiment more, getting high-quality results faster, and allowing us to try different ideas around the AI agent concept.
Enter Gordon
Out of this experimentation came a new product that you can try: Gordon. With Gordon, we’d like to tackle these pain points. By integrating Gordon into Docker Desktop and the Docker CLI (Figure 1), we can:
Access much more context that can be used by the LLMs to best understand the user’s questions and provide better answers or even perform actions on the user’s behalf.
Be where the users are. If you launch a container via Docker Desktop and it fails, you can quickly debug with Gordon. If you’re in the terminal hacking away, Docker AI will be there, too.
Avoid being a purely chat-based agent by providing Gordon-based features directly as part of Docker Desktop UI elements. If Gordon detects certain scenarios, like a container that failed to start, a button will appear in the UI to directly get suggestions, or run actions, etc. (Figure 2).
Figure 1: Gordon icon on Docker Desktop.Figure 2: Ask Gordon (beta).
What Gordon can do
We want to start with Gordon by optimizing for Docker-related tasks — not general-purpose questions — but we are not excluding expanding the scope to more development-related tasks as work on the agent continues.
Work on Gordon is at an early stage and its capabilities are constantly evolving, but it’s already really good at some things (Figure 3). Here are things to definitely try out:
Ask general Docker-related questions. Gordon knows Docker well and has access to all of our documentation.
Get help debugging container build or runtime errors.
Get help optimizing Docker-related files and configurations.
Ask it how to run specific containers (e.g., “How can I run MongoDB?”).
Figure 3: Using Gordon to understand a Dockerfile.
How Gordon works
The Gordon backend lives on Docker servers, while the client is a CLI that lives on the user’s machine and is bundled with Docker Desktop. Docker Desktop uses the CLI to access the local machine’s files, asking the user for the directory each time it needs that context to answer a question. When using the CLI directly, it has access to the working directory it’s executed in. For example, if you are in a directory with a Dockerfile and you run “Docker AI, rate my Dockerfile”, it will find the one that’s present in that directory
Currently, Gordon does not have write access to any files, so it will not edit any of your files. We’re hard at work on future features that will allow the agent to do the work for you, instead of only suggesting solutions.
Figure 4 shows a rough overview of how we are thinking about things behind the scenes.
Figure 4: Overview of Gordon.
The first step of this pipeline, “Understand the user’s input and figure out which action to perform”, is done using “tool calling” (also known as “function calling”) with the OpenAI API.
Although this is a popular approach, we noticed that the documentation online isn’t very good, and general best practices aren’t well defined yet. This led us to experiment a lot with the feature and try to figure out what works for us and what doesn’t.
Things we noticed:
Tool descriptions are important, and we should prefer more in-depth descriptions with examples.
Testing around tool-detection code is also important. Adding new tools to a request could confuse the LLM and cause it to no longer trigger the expected tool.
The LLM model used influences how the whole tool calling functionality should be implemented, as different models might prefer descriptions written in a certain way, behave better/worse under certain scenarios (e.g. when using lots of tools), etc.
Try Gordon for yourself
Gordon is available as an opt-in Beta feature starting with Docker Desktop version 4.37. To participate in the closed beta, all you need to do is fill out the form on the site.
Initially, Gordon will be available for use both in Docker Desktop and the Docker CLI, but our idea is to surface parts of this tech in various other parts of our products as well.
For more on what we’re doing at Docker, subscribe to our newsletter.
We’ve identified the issue affecting Docker Desktop for some macOS users, which caused disruptions for some existing Docker Desktop installations.
Next steps
To minimize the impact on your Docker experience, we recommend one of the following actions:
1. Upgrade to the latest version
We recommend upgrading to Docker Desktop version 4.37.2, which includes a permanent fix. Download the update here or via the Docker Desktop in-app update.
2. Use a patch update (for older versions)
For users unable to upgrade to the latest version, we’ve released patches for versions 4.32 through 4.36. Access the relevant patch updates here.
3. Apply a one-time corrective action
If you are still seeing the malware pop-up or encountering the issue, please also follow the additional steps detailed here.
4. IT administrators
As an IT administrator, you can use this script to take corrective actions on behalf of your users, provided your developers have either upgraded to the latest version or applied a patch.
We know how critical Docker Desktop is to your workflow and are committed to ensuring a smooth resolution. All remediation steps are documented here. Note that Docker Desktop versions 4.28 and earlier are not impacted by this issue. If you encounter any issues or need assistance, please reach out to our Support Team.
Update: January 8, 2025
We want to inform you about a new issue affecting Docker Desktop for some macOS users. This causes Docker Desktop to not start. Some users may also have received malware warnings. Those warnings are inaccurate.
A temporary workaround that will restore functionality is available for any affected users. Detailed instructions for the workaround are available on GitHub.
Our team is prioritizing this issue and working diligently on a permanent fix. If you prefer to wait for the longer-term patch update, please refrain from (re)-starting Docker Desktop.
We know how important Docker Desktop is to your work, and we’re committed to resolving this issue quickly and effectively. For assistance or additional information, please reach out to our Support team or check the Docker Status page for the latest updates.
One of the best ways to make sure your web apps work well in different environments is to containerize them. Containers let you work in a more controlled way, which makes development and deployment easier. This guide will show you how to containerize a Django web app with Docker and explain why it’s a good idea.
We will walk through creating a Docker container for your Django application. Docker gives you a standardized environment, which makes it easier to get up and running and more productive. This tutorial is aimed at those new to Docker who already have some experience with Django. Let’s get started!
Why containerize your Django application?
Django apps can be put into containers to help you work more productively and consistently. Here are the main reasons why you should use Docker for your Django project:
Creates a stable environment: Containers provide a stable environment with all dependencies installed, so you don’t have to worry about “it works on my machine” problems. This ensures that you can reproduce the app and use it on any system or server. Docker makes it simple to set up local environments for development, testing, and production.
Ensures reproducibility and portability: A Dockerized app bundles all the environment variables, dependencies, and configurations, so it always runs the same way. This makes it easier to deploy, especially when you’re moving apps between environments.
Facilitates collaboration between developers: Docker lets your team work in the same environment, so there’s less chance of conflicts from different setups. Shared Docker images make it simple for your team to get started with fewer setup requirements.
Speeds up deployment processes: Docker makes it easier for developers to get started with a new project quickly. It removes the hassle of setting up development environments and ensures everyone is working in the same place, which makes it easier to merge changes from different developers.
Getting started with Django and Docker
Setting up a Django app in Docker is straightforward. You don’t need to do much more than add in the basic Django project files.
If you need help with the installation, you can find detailed instructions on the Docker and Django websites.
How to Dockerize your Django project
The following six steps include code snippets to guide you through the process.
Step 1: Set up your Django project
1. Initialize a Django project.
If you don’t have a Django project set up yet, you can create one with the following commands:
django-admin startproject my_docker_django_app
cd my_docker_django_app
2. Create a requirements.txt file.
In your project, create a requirements.txt file to store dependencies:
pip freeze > requirements.txt
3. Update key environment settings.
You need to change some sections in the settings.py file to enable them to be set using environment variables when the container is started. This allows you to change these settings depending on the environment you are working in.
A Dockerfile is a script that tells Docker how to build your Docker image. Put it in the root directory of your Django project. Here’s a basic Dockerfile setup for Django:
# Use the official Python runtime image
FROM python:3.13
# Create the app directory
RUN mkdir /app
# Set the working directory inside the container
WORKDIR /app
# Set environment variables
# Prevents Python from writing pyc files to disk
ENV PYTHONDONTWRITEBYTECODE=1
#Prevents Python from buffering stdout and stderr
ENV PYTHONUNBUFFERED=1
# Upgrade pip
RUN pip install --upgrade pip
# Copy the Django project and install dependencies
COPY requirements.txt /app/
# run this command to install all dependencies
RUN pip install --no-cache-dir -r requirements.txt
# Copy the Django project to the container
COPY . /app/
# Expose the Django port
EXPOSE 8000
# Run Django’s development server
CMD ["python", "manage.py", "runserver", "0.0.0.0:8000"]
Each line in the Dockerfile serves a specific purpose:
FROM: Selects the image with the Python version you need.
WORKDIR: Sets the working directory of the application within the container.
ENV: Sets the environment variables needed to build the application
RUNand COPY commands: Install dependencies and copy project files.
EXPOSE and CMD: Expose the Django server port and define the startup command.
You can build the Django Docker container with the following command:
docker build -t django-docker .
To see your image, you can run:
docker image list
The result will look something like this:
REPOSITORY TAG IMAGE ID CREATED SIZE
django-docker latest ace73d650ac6 20 seconds ago 1.55GB
Although this is a great start in containerizing the application, you’ll need to make a number of improvements to get it ready for production.
The CMD manage.py is only meant for development purposes and should be changed for a WSGI server.
Reduce the size of the image by using a smaller image.
Optimize the image by using a multistage build process.
Let’s get started with these improvements.
Update requirements.txt
Make sure to add gunicorn to your requirements.txt. It should look like this:
The Dockerfile below has changes that solve the three items on the list. The changes to the file are as follows:
Updated the FROM python:3.13 image to FROM python:3.13-slim. This change reduces the size of the image considerably, as the image now only contains what is needed to run the application.
Added a multi-stage build process to the Dockerfile. When you build applications, there are usually many files left on the file system that are only needed during build time and are not needed once the application is built and running. By adding a build stage, you use one image to build the application and then move the built files to the second image, leaving only the built code. Read more about multi-stage builds in the documentation.
Add the Gunicorn WSGI server to the server to enable a production-ready deployment of the application.
# Stage 1: Base build stage
FROM python:3.13-slim AS builder
# Create the app directory
RUN mkdir /app
# Set the working directory
WORKDIR /app
# Set environment variables to optimize Python
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
# Upgrade pip and install dependencies
RUN pip install --upgrade pip
# Copy the requirements file first (better caching)
COPY requirements.txt /app/
# Install Python dependencies
RUN pip install --no-cache-dir -r requirements.txt
# Stage 2: Production stage
FROM python:3.13-slim
RUN useradd -m -r appuser && \
mkdir /app && \
chown -R appuser /app
# Copy the Python dependencies from the builder stage
COPY --from=builder /usr/local/lib/python3.13/site-packages/ /usr/local/lib/python3.13/site-packages/
COPY --from=builder /usr/local/bin/ /usr/local/bin/
# Set the working directory
WORKDIR /app
# Copy application code
COPY --chown=appuser:appuser . .
# Set environment variables to optimize Python
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
# Switch to non-root user
USER appuser
# Expose the application port
EXPOSE 8000
# Start the application using Gunicorn
CMD ["gunicorn", "--bind", "0.0.0.0:8000", "--workers", "3", "my_docker_django_app.wsgi:application"]
Build the Docker container image again.
docker build -t django-docker .
After making these changes, we can run a docker image list again:
REPOSITORY TAG IMAGE ID CREATED SIZE
django-docker latest 3c62f2376c2c 6 seconds ago 299MB
You can see a significant improvement in the size of the container.
The size was reduced from 1.6 GB to 299MB, which leads to faster a deployment process when images are downloaded and cheaper storage costs when storing images.
You could use docker init as a command to generate the Dockerfile and compose.yml file for your application to get you started.
Step 3: Configure the Docker Compose file
A compose.yml file allows you to manage multi-container applications. Here, we’ll define both a Django container and a PostgreSQL database container.
The compose file makes use of an environment file called .env, which will make it easy to keep the settings separate from the application code. The environment variables listed here are standard for most applications:
2. Set ALLOWED_HOSTS to read from environment files.
In settings.py, set ALLOWED_HOSTS to:
# 'DJANGO_ALLOWED_HOSTS' should be a single string of hosts with a , between each.
# For example: 'DJANGO_ALLOWED_HOSTS=localhost 127.0.0.1,[::1]'
ALLOWED_HOSTS = os.environ.get("DJANGO_ALLOWED_HOSTS","127.0.0.1").split(",")
3. Set the SECRET_KEY to read from environment files.
In settings.py, set SECRET_KEY to:
# SECURITY WARNING: keep the secret key used in production secret!
SECRET_KEY = os.environ.get("DJANGO_SECRET_KEY")
4. Set DEBUG to read from environment files.
In settings.py, set DEBUG to:
# SECURITY WARNING: don't run with debug turned on in production!
DEBUG = bool(os.environ.get("DEBUG", default=0))
Step 5: Build and run your new Django project
To build and start your containers, run:
docker compose up --build
This command will download any necessary Docker images, build the project, and start the containers. Once complete, your Django application should be accessible at http://localhost:8000.
Step 6: Test and access your application
Once the app is running, you can test it by navigating to http://localhost:8000. You should see Django’s welcome page, indicating that your app is up and running. To verify the database connection, try running a migration:
docker compose run django-web python manage.py migrate
Troubleshooting common issues with Docker and Django
Here are some common issues you might encounter and how to solve them:
Database connection errors: If Django can’t connect to PostgreSQL, verify that your database service name matches in compose.yml and settings.py.
File synchronization issues: Use the volumes directive in compose.yml to sync changes from your local files to the container.
Container restart loops or crashes: Use docker compose logs to inspect container errors and determine the cause of the crash.
Optimizing your Django web application
To improve your Django Docker setup, consider these optimization tips:
Automate and secure builds: Use Docker’s multi-stage builds to create leaner images, removing unnecessary files and packages for a more secure and efficient build.
Optimize database access: Configure database pooling and caching to reduce connection time and boost performance.
Efficient dependency management: Regularly update and audit dependencies listed in requirements.txt to ensure efficiency and security.
Take the next step with Docker and Django
Containerizing your Django application with Docker is an effective way to simplify development, ensure consistency across environments, and streamline deployments. By following the steps outlined in this guide, you’ve learned how to set up a Dockerized Django app, optimize your Dockerfile for production, and configure Docker Compose for multi-container setups.
Docker not only helps reduce “it works on my machine” issues but also fosters better collaboration within development teams by standardizing environments. Whether you’re deploying a small project or scaling up for enterprise use, Docker equips you with the tools to build, test, and deploy reliably.
Ready to take the next step? Explore Docker’s powerful tools, like Docker Hub and Docker Scout, to enhance your containerized applications with scalable storage, governance, and continuous security insights.
The need for secure and high quality software becomes more critical every day as the impact of vulnerabilities increases and related costs continue to rise. For example, flawed software cost the U.S. economy $2.08 trillion in 2020 alone, according to the Consortium for Information and Software Quality (CISQ). And, a software defect that might cost $100 to fix if found early in the development process can grow exponentially to $10,000 if discovered later in production.
Docker helps you deliver secure, efficient applications by providing consistent environments and fast, reliable container management, building on best practices that let you discover and resolve issues earlier in the software development life cycle (SDLC).
Shifting left to ensure fewer defects
In a previous blog post, we talked about using the right tools, including Docker’s suite of products to boost developer productivity. Besides having the right tools, you also need to implement the right processes to optimize your software development and improve team productivity.
The software development process is typically broken into two distinct loops, the inner and the outer loops. At Docker, we believe that investing in the inner loop is crucial. This means shifting security left and identifying problems as soon as you can. This approach improves efficiency and reduces costs by helping teams find and fix software issues earlier.
Using Docker tools to adopt best practices
Docker’s products help you adopt these best practices — we are focused on enhancing the software development lifecycle, especially around refining the inner loop. Products like Docker Desktop allow your dev team in the inner loop to run, test, code, and build everything fast and consistently. This consistency eliminates the “it works on my machine” issue, meaning applications behave the same in both development and production.
Shifting left lets your dev team identify problems earlier in your software project lifecycle. When you detect issues sooner, you increase efficiency and help ensure secure builds and compliance. By shifting security left with Docker Scout, your dev teams can identify vulnerabilities sooner and help avoid issues down the road.
Another example of shifting left involves testing — doing testing earlier in the process leads to more robust software and faster release cycles. This is when Testcontainers Cloud comes in handy because it enables developers to run reliable integration tests, with real dependencies defined in code.
Accelerate development within the hybrid inner loop
We see more and more companies adopting the so-called hybrid inner loop, which combines the best of two worlds — local and cloud. The results provide greater flexibility for your dev teams and encourage better collaboration. For example, Docker Build Cloud uses the power of the cloud to speed up build time without sacrificing the local development experience that developers love.
By using these Docker products across the software development life cycle, teams get quick feedback loops and faster issue resolution, ensuring a smooth development flow from inception to deployment.
Simplifying AI application development
When you’re using the right tools and processes to accelerate your application delivery and maximize efficiency throughout your SDLC, processes that were once cumbersome become your new baseline, freeing up time for true innovation.
Docker also helps accelerate innovation by simplifying AI/ML development. We are continually investing in AI to help your developers deliver AI-backed applications that differentiate your business and enhance competitiveness.
Docker AI tools
Docker’s GenAI Stack accelerates the incorporation of large language models (LLMs) and AI/ML into your code, enabling the delivery of AI-backed applications. All containers work harmoniously and are managed directly from Docker Desktop, allowing your team to monitor and adjust components without leaving their development environment. Deploying the GenAI Stack is quick and easy, and leveraging Docker’s containerization technology helps speed setup and simplify scaling as applications grow.
Earlier this year, we announced the preview of Docker Extension for GitHub Copilot. By standardizing best practices and enabling integrations with tools like GitHub Copilot, Docker empowers developers to focus on innovation, closing the gap from the first line of code to production.
And, more recently, we launched the Docker AI Catalog in Docker Hub. This new feature simplifies the process of integrating AI into applications by providing trusted and ready-to-use content supported by comprehensive documentation. Your dev team will benefit from shorter development cycles, improved productivity, and a more streamlined path to integrating AI into both new and existing applications.
Wrapping up
Docker products help you establish sound processes and practices related to shifting left and discovering issues earlier to avoid headaches down the road. This approach ultimately unlocks developer productivity, giving your dev team more time to code and innovate. Docker also allows you to quickly use AI to close knowledge gaps and offers trusted tools to build AI/ML applications and accelerate time to market.
To see how Docker continues to empower developers with the latest innovations and tools, check out our Docker 2024 Highlights.
Learn about Docker’s updated subscriptions and find the ideal plan for your team’s needs.
Kubernetes is an open source platform for automating the deployment, scaling, and management of containerized applications across clusters of machines. It’s become the go-to solution for orchestrating containers in production environments. But if you’re developing or testing locally, setting up a full Kubernetes cluster can be complex. That’s where Docker Desktop comes in — it lets you run Kubernetes directly on your local machine, making it easy to test microservices, CI/CD pipelines, and containerized apps without needing a remote cluster.
Getting Kubernetes up and running can feel like a daunting task, especially for developers working in local environments. But with Docker Desktop, spinning up a fully functional Kubernetes cluster is simpler than ever. Whether you’re new to Kubernetes or just want an easy way to test containerized applications locally, Docker Desktop provides a streamlined solution. In this guide, we’ll walk through the steps to start a Kubernetes cluster on Docker Desktop and offer troubleshooting tips to ensure a smooth experience.
Note: Docker Desktop’s Kubernetes cluster is designed specially for local development and testing; it is not for production use.
Benefits of running Kubernetes in Docker Desktop
The benefits of this setup include:
Easy local Kubernetes cluster: A fully functional Kubernetes cluster runs on your local machine with minimal setup, handling network access between the host and Kubernetes as well as storage management.
Easier learning path and developer convenience: For developers familiar with Docker but new to Kubernetes, having Kubernetes built into Docker Desktop offers a low-friction learning path.
Testing Kubernetes-based applications locally: Docker Desktop gives developers a local environment to test Kubernetes-based microservices applications that require Kubernetes features like services, pods, ConfigMaps, and secrets without needing access to a remote cluster. It also helps developers to test CI/CD pipelines locally.
How to start Kubernetes cluster on Docker Desktop in three steps
Install Docker Desktop on the operating system of your choice. Currently, the supported operating systems are macOS, Linux, and Windows.
In the Settings menu, select Kubernetes > Enable Kubernetes and then Apply & restart to start a one-node Kubernetes cluster (Figure 1). Typically, the time it takes to set up the Kubernetes cluster depends on your internet speed to pull the needed images.
Figure 1: Starting Kubernetes.
Once the Kubernetes cluster is started successfully, you can see the status from the Docker Desktop dashboard or the command line.
From the dashboard (Figure 2):
Figure 2: Status from the dashboard.
The command-line status:
$ kubectl get node
NAME STATUS ROLES AGE VERSION
docker-desktop Ready control-plane 5d v1.30.2
Getting Kubernetes support
Docker bundles Kubernetes but does not provide official Kubernetes support. If you are experiencing issues with Kubernetes, however, you can get support in several ways, including from the Docker community, Docker guides, and GitHub documentation:
The command will show you where the diagnostics file is saved:
Gathering diagnostics for ID into /var/folders/50/<Random Character>/<Random Character>/<Machine unique ID>/<YYYYMMDDTTTT>.zip.
In this case, the file is saved at /var/folders/50/<Random Characters>/<Random Characters>/<YYYMMDDTTTT>.zip. Unzip the file (<YYYYMMDDTTTT>.zip) where you can find the logs file for Docker Desktop.
Check for logs
Checking for logs instead of guessing the issue is good practice. Understanding what Kubernetes components are available and what their functions are is essential before you start troubleshooting. You can narrow down the process by looking at the specific component logs. Look for the keyword error or fatal in the logs.
Depending on which platform you are using, one method is to use the grep command and search for the keyword in the macOS terminal, a Linux distro for WSL2, or the Linux terminal for the file you unzipped:
$ grep -Hrni "<keyword>" <The path of the unzipped file>
## For example, one of the error found related to Kubernetes in the "com.docker.backend.exe" logs:
$ grep -Hrni "error" *
[com.docker.backend.exe.log:[2022-12-05T05:24:39.377530700Z][com.docker.backend.exe][W] starting kubernetes: 1 error occurred:
com.docker.backend.exe.log: * starting kubernetes: pulling kubernetes images: pulling registry.k8s.io/coredns:v1.9.3: Error response from daemon: received unexpected HTTP status: 500 Internal Server Error
Troubleshooting example
Let’s say you notice there is an issue starting up the cluster. This issue could be related to the Kubelet process, which works as a node-level agent to help with container management and orchestration within a Kubernetes cluster. So, you should check the Kubelet logs.
But, where is the Kubelet log located? It’s at log/vm/kubelet.log in the diagnostics file.
An example of a possible related issue can be found in the kubelet.log. The images needed to set up Kubernetes are not able to be pulled due to network/internet restrictions. You might find errors related to failing to pull the necessary Kubernetes images to set up the Kubernetes cluster.
For example:
starting kubernetes: pulling kubernetes images: pulling registry.k8s.io/coredns:v1.9.3: Error response from daemon: received unexpected HTTP status: 500 Internal Server Error
Normally, 10 images are needed to set up the cluster. The following output is from a macOS running Docker Desktop version 4.33:
$ docker image ls
REPOSITORY TAG IMAGE ID CREATED SIZE
docker/desktop-kubernetes kubernetes-v1.30.2-cni-v1.4.0-critools-v1.29.0-cri-dockerd-v0.3.11-1-debian 5ef3082e902d 4 weeks ago 419MB
registry.k8s.io/kube-apiserver v1.30.2 84c601f3f72c 7 weeks ago 112MB
registry.k8s.io/kube-scheduler v1.30.2 c7dd04b1bafe 7 weeks ago 60.5MB
registry.k8s.io/kube-controller-manager v1.30.2 e1dcc3400d3e 7 weeks ago 107MB
registry.k8s.io/kube-proxy v1.30.2 66dbb96a9149 7 weeks ago 87.9MB
registry.k8s.io/etcd 3.5.12-0 014faa467e29 6 months ago 139MB
registry.k8s.io/coredns/coredns v1.11.1 2437cf762177 11 months ago 57.4MB
docker/desktop-vpnkit-controller dc331cb22850be0cdd97c84a9cfecaf44a1afb6e 3750dfec169f 14 months ago 35MB
registry.k8s.io/pause 3.9 829e9de338bd 22 months ago 514kB
docker/desktop-storage-provisioner v2.0 c027a58fa0bb 3 years ago 39.8MB
You can check whether you successfully pulled the 10 images by running docker image ls. If images are missing, a workaround is to save the missing image using docker image save from a machine that successfully starts the Kubernetes cluster (provided both run the same Docker Desktop version). Then, you can transfer the image to your machine, use docker image load to load the image into your machine, and tag it.
For example, if the registry.k8s.io/coredns:v<VERSION> image is not available, you can follow these steps:
Use docker image save from a machine that successfully starts the Kubernetes cluster to save it as a tar file: docker save registry.k8s.io/coredns:v<VERSION> > <Name of the file>.tar.
Manually transfer the <Name of the file>.tar to your machine.
Use docker image load to load the image on your machine: docker image load <<Name of the file>.tar.
Tag the image: docker image tag registry.k8s.io/coredns:v<VERSION> <Name of the file>.tar.
Re-enable the Kubernetes from your Docker Desktop’s settings.
Check other logs in the diagnostics log.
What to look for in the diagnostics log
In the diagnostics log, look for the folder starting named kube/. (Note that the <kube> below, for macOS and Linux is kubectl and for Windows is kubectl.exe.)
kube/get-namespaces.txt: List down all the namespaces, equal to <kube> --context docker-desktop get namespaces.
kube/describe-nodes.txt: Describe the docker-desktop node, equal to <kube> --context docker-desktop describe nodes.
kube/describe-pods.txt: Description of all pods running in the Kubernetes cluster.
kube/describe-services.txt: Description of the services running, equal to <kube> --context docker-desktop describe services --all-namespaces.
You also can find other useful Kubernetes logs in the mentioned folder.
Search for known issues
For any error message found in the steps above, you can search for known Kubernetes issues on GitHub to see if a workaround or any future permanent fix is planned.
Reset or reboot
If the previous steps weren’t helpful, try a reboot. And, if the previous steps weren’t helpful, try a reboot. And, if a reboot is not helpful, the last alternative is to reset your Kubernetes cluster, which often helps resolve issues:
Reboot: To reboot, restart your machine. Rebooting a machine in a Kubernetes cluster can help resolve issues by clearing transient states and restoring the system to a clean state.
Reset: For a reset, navigate to Settings > Kubernetes > Reset the Kubernetes Cluster. Resetting a Kubernetes cluster can help resolve issues by essentially reverting the cluster to a clean state, and clearing out misconfigurations, corrupted data, or stuck resources that may be causing problems.
Bringing Kubernetes to your local development environment
This guide offers a straightforward way to start a Kubernetes cluster on Docker Desktop, making it easier for developers to test Kubernetes-based applications locally. It covers key benefits like simple setup, a more accessible learning path for beginners, and the ability to run tests without relying on a remote cluster. We also provide some troubleshooting tips and resources for resolving common issues.
Whether you’re just getting started or looking to improve your local Kubernetes workflow, give it a try and see what you can achieve with Docker Desktop’s Kubernetes integration.
In modern software development, businesses are searching for smarter ways to streamline workflows and deliver value faster. For developers, this means tackling challenges like collaboration and security head-on, while driving efficiency that contributes directly to business performance. But how do you address potential roadblocks before they become costly issues in production? The answer lies in optimizing the development inner loop — a core focus for the future of app development.
By identifying and resolving inefficiencies early in the development lifecycle, software development teams can overcome common engineering challenges such as slow dev cycles, spiraling infrastructure costs, and scaling challenges. With Docker’s integrated suite of development tools, developers can achieve new levels of engineering efficiency, creating high-quality software while delivering real business impact.
Let’s explore how Docker is transforming the development process, reducing operational overhead, and empowering teams to innovate faster.
Speed up software development lifecycles: Faster gains with less effort
A fast software development lifecycle is a crucial aspect for delivering value to users, maintaining a competitive edge, and staying ahead of industry trends. To enable this, software developers need workflows that minimize friction and allow them to iterate quickly without sacrificing quality. That’s where Docker makes a difference. By streamlining workflows, eliminating bottlenecks, and automating repetitive tasks, Docker empowers developers to focus on high-impact work that drives results.
Consistency across development environments is critical for improving speed. That’s why Docker helps developers create consistent environments across local, test, and production systems. In fact, a recent study reported developers experiencing a 6% increase in productivity when leveraging Docker Business. This consistency eliminates guesswork, ensuring developers can concentrate on writing code and improving features rather than troubleshooting issues. With Docker, applications behave predictably across every stage of the development lifecycle.
Docker also accelerates development by significantly reducing time spent on iteration and setup. More specifically, organizations leveraging Docker Business achieved a three-month faster time-to-market for revenue-generating applications. Engineering teams can move swiftly through development stages, delivering new features and bug fixes faster. By improving efficiency and adapting to evolving needs, Docker enables development teams to stay agile and respond effectively to business priorities.
Improve scaling agility: Flexibility for every scenario
Scalability is another essential for businesses to meet fluctuating demands and seize opportunities. Whether handling a surge in user traffic or optimizing resources during quieter periods, the ability to scale applications and infrastructure efficiently is a critical advantage. Docker makes this possible by enabling teams to adapt with speed and flexibility.
Docker’s cloud-native approach allows software engineering teams to scale up or down with ease to meet changing requirements. This flexibility supports experimentation with cutting-edge technologies like AI, machine learning, and microservices without disrupting existing workflows. With this added agility, developers can explore new possibilities while maintaining focus on delivering value.
Whether responding to market changes or exploring the potential of emerging tools, Docker equips companies to stay agile and keep evolving, ensuring their development processes are always ready to meet the moment.
Optimize resource efficiency: Get the most out of what you’ve got
Maximizing resource efficiency is crucial for reducing costs and maintaining agility. By making the most of existing infrastructure, businesses can avoid unnecessary expenses and minimize cloud scaling costs, meaning more resources for innovation and growth. Docker empowers teams to achieve this level of efficiency through its lightweight, containerized approach.
Docker containers are designed to be resource-efficient, enabling multiple applications to run in isolated environments on the same system. Unlike traditional virtual machines, containers minimize overhead while maintaining performance, consolidating workloads, and lowering the operational costs of maintaining separate environments. For example, a leading beauty company reduced infrastructure costs by 25% using Docker’s enhanced CPU and memory efficiency. This streamlined approach ensures businesses can scale intelligently while keeping infrastructure lean and effective.
By containerizing applications, businesses can optimize their infrastructure, avoiding costly upgrades while getting more value from their current systems. It’s a smarter, more efficient way to ensure your resources are working at their peak, leaving no capacity underutilized.
Establish cost-effective scaling: Growth without growing pains
Similarly, scaling efficiently is essential for businesses to keep up with growing demands, introduce new features, or adopt emerging technologies. However, traditional scaling methods often come with high upfront costs and complex infrastructure changes. Docker offers a smarter alternative, enabling development teams to scale environments quickly and cost-effectively.
With a containerized model, infrastructure can be dynamically adjusted to match changing needs. Containers are lightweight and portable, making it easy to scale up for spikes in demand or add new capabilities without overhauling existing systems. This flexibility reduces financial strain, allowing businesses to grow sustainably while maximizing the use of cloud resources.
Docker ensures that scaling is responsive and budget-friendly, empowering teams to focus on innovation and delivery rather than infrastructure costs. It’s a practical solution to achieve growth without unnecessary complexity or expense.
Software engineering efficiency at your fingertips
The developer community consistently ranks Docker highly, including choosing it as the most-used and most-admired developer tool in Stack Overflow’s Developer Survey. With Docker’s suite of products, teams can reach a new level of efficient software development by streamlining the dev lifecycle, optimizing resources, and providing agile, cost-effective scaling solutions. By simplifying complex processes in the development inner loop, Docker enables businesses to deliver high-quality software faster while keeping operational costs in check. This allows developers to focus on what they do best: building innovative, impactful applications.
By removing complexity, accelerating development cycles, and maximizing resource usage, Docker helps businesses stay competitive and efficient. And ultimately, their teams can achieve more in less time — meeting market demands with efficiency and quality.
Ready to supercharge your development team’s performance? Download our white paper to see how Docker can help streamline your workflow, improve productivity, and deliver software that stands out in the market.
“You don’t want to think about security — until you have to.”
That’s what I’d tell you if I were being honest about the state of development at most organizations I have spoken to. Every business out there is chasing one thing: speed. Move faster. Innovate faster. Ship faster. To them, speed is survival. There’s something these companies are not seeing — a shadow. An unseen risk hiding behind every shortcut, every unchecked tool, and every corner cut in the name of “progress.”
Businesses are caught in a relentless sprint, chasing speed and progress at all costs. However, as Cal Newport reminds us in Slow Productivity, the race to do more — faster — often leads to chaos, inefficiency, and burnout. Newport’s philosophy calls for deliberate, focused work on fewer tasks with greater impact. This philosophy isn’t just about how individuals work — it’s about how businesses innovate. Development teams rushing to ship software often cut corners, creating vulnerabilities that ripple through the entire supply chain.
The strategic risk: An unsecured development pipeline
Development environments are the foundation of your business. You may think they’re inherently secure because they’re internal. Foundations crumble when you don’t take care of them, and that crack doesn’t just swallow your software — it swallows established customer trust and reputation. That’s how it starts: a rogue tool here, an unpatched dependency there, a developer bypassing IT to do things “their way.” They’re not trying to ruin your business. They’re trying to get their jobs done. But sometimes you can’t stop a fire after it’s started. Shadow IT isn’t just inconvenient — it’s dangerous. It’s invisible, unmonitored, and unregulated. It’s the guy leaving the back door open in a neighborhood full of burglars.
You need control, isolation, and automation — not because they’re nice to have, but because you’re standing on a fault line without them. Docker gives you that control. Fine-grained, role-based access ensures that the only people touching your most critical resources are the ones you trust. Isolation through containerization keeps every piece of your pipeline sealed tight so vulnerabilities don’t spread. Automation takes care of the updates, the patch management, and the vulnerabilities before they become a problem. In other words, you don’t have to hope your foundation is solid — you’ll know it is.
Shadow IT: A growing concern
While securing official development environments is critical, shadow IT remains an insidious and hidden threat. Shadow IT refers to tools, systems, or environments implemented without explicit IT approval or oversight. In the pursuit of speed, developers may bypass formal processes to adopt tools they find convenient. However, this creates unseen vulnerabilities with far-reaching consequences.
In the pursuit of performative busywork, developers often take shortcuts, grabbing tools and spinning up environments outside the watchful eyes of IT. The intent may not be malicious; it’s just human nature. Here’s the catch: What you don’t see, you can’t protect. Shadow IT is like a crack in the dam: silent, invisible, and spreading. It lets unvetted tools and insecure code slip into your supply chain, infecting everything from development to production. Before you know it, that “quick fix” has turned into a legal nightmare, a compliance disaster, and a stain on your reputation. In industries like finance or healthcare, that stain doesn’t wash out quickly.
A solution rooted in integration
The solution lies in a unified, secure approach to development environments that removes the need for shadow IT while fortifying the software supply chain. Docker addresses these vulnerabilities by embedding security directly into the development lifecycle. Our solution is built on three foundational principles: control, isolation, and automation.
Control through role-based access management: Docker Hub establishes clear boundaries within development environments by enabling fine-grained, role-based access. You want to ensure that only authorized personnel can interact with sensitive resources, which will ideally minimize the risk of unintended or malicious actions. Docker also enables publishers to enforce role-based access controls, ensuring only authorized users can interact with development resources. It streamlines patch management through verified, up-to-date images. Docker Official Images and Docker Verified Publisher content are scanned with our in-house image analysis tool, Docker Scout. This helps find vulnerabilities before they can be exploited.
Isolation through containerization: Docker’s value proposition centers on its containerization technology. By creating isolated development spaces, Docker prevents cross-environment contamination and ensures that applications and their dependencies remain secure throughout the development lifecycle.
Automation for seamless security:Recognizing the need for speed in modern development cycles, Docker integrates recommendations with Scout through recommendations for software updates and patch management for CVEs. This ensures that environments remain secure against emerging threats without interrupting the flow of innovation.
Delivering tangible business outcomes
Businesses are always going to face this tension between speed and security, but the truth is you don’t have to choose. Docker gives you both. It’s not just a platform; it’s peace of mind. Because when your foundation is solid, you stop worrying about what could go wrong. You focus on what comes next.
Consider the example of a development team working on a high-stakes application feature. Without secure environments, a single oversight — such as an unregulated access point — can result in vulnerabilities that disrupt production and erode customer trust. By leveraging Docker’s integrated security solutions, the team mitigates these risks, enabling them to focus on value creation rather than crisis management.
Aligning innovation with security
As a previous post covers, securing the development pipeline is not simply deploying technical solutions but establishing trust across the entire software supply chain. With Docker Content Trust and image signing, organizations can ensure the integrity of software components at every stage, reducing the risk of third-party code introducing unseen vulnerabilities. By eliminating the chaos of shadow IT and creating a transparent, secure development process, businesses can mitigate risk without slowing the pace of innovation.
The tension between speed and security has long been a barrier to progress, but businesses can confidently pursue both with Docker. A secure development environment doesn’t just protect against breaches — it strengthens operational resilience, ensures regulatory compliance, and safeguards brand reputation. Docker empowers organizations to innovate on a solid foundation as unseen risks lurk within an organization’s fragmented tools and processes.
Security isn’t a luxury. It’s the cost of doing business. If you care about growth, if you care about trust, if you care about what your brand stands for, then securing your development environments isn’t optional — it’s survival. Docker Business doesn’t just protect your pipeline; it turns it into a strategic advantage that lets you innovate boldly while keeping your foundation unshakable. Integrity isn’t something you hope for — it’s something you build.
Start today
Securing your software supply chain is a critical step in building resilience and driving sustained innovation. Docker offers the tools to create fortified development environments where your teams can operate at their best.
The question is not whether to secure your development pipeline — it’s how soon you can start. Explore Docker Hub and Scout today to transform your approach to innovation and security. In doing so, you position your organization to navigate the complexities of the modern development landscape with confidence and agility.
Anthropic recently unveiled the Model Context Protocol (MCP), a new standard for connecting AI assistants and models to reliable data and tools. However, packaging and distributing MCP servers is very challenging due to complex environment setups across multiple architectures and operating systems. Docker is the perfect solution for this — it allows developers to encapsulate their development environment into containers, ensuring consistency across all team members’ machines and deployments consistent and predictable. In this blog post, we provide a few examples of using Docker to containerize Model Context Protocol (MCP) to simplify building AI applications.
What is Model Context Protocol (MCP)?
MCP (Model Context Protocol), a new protocol open-sourced by Anthropic, provides standardized interfaces for LLM applications to integrate with external data sources and tools. With MCP, your AI-powered applications can retrieve data from external sources, perform operations with third-party services, or even interact with local filesystems.
Among the use cases enabled by this protocol is the ability to expose custom tools to AI models. This provides key capabilities such as:
Tool discovery: Helping LLMs identify tools available for execution
Tool invocation: Enabling precise execution with the right context and arguments
Since its release, the developer community has been particularly energized. We asked David Soria Parra, Member of Technical Staff from Anthropic, why he felt MCP was having such an impact: “Our initial developer focus means that we’re no longer bound to one specific tool set. We are giving developers the power to build for their particular workflow.”
How does MCP work? What challenges exist?
MCP works by introducing the concept of MCP clients and MCP Servers — clients request resources and the servers handle the request and perform the requested action. MCP Clients are often embedded into LLM-based applications, such as the Claude Desktop App. The MCP Servers are launched by the client to then perform the desired work using any additional tools, languages, or processes needed to perform the work.
Examples of tools include filesystem access, GitHub and GitLab repo management, integrations with Slack, or retrieving or modifying state in Kubernetes clusters.
Figure 1: A high-level architecture diagram of MCP client and server interactions
The goal of MCP servers is to provide reusable toolsets and reuse them across clients, like Claude Desktop – write one set of tools and reuse them across many LLM-based applications. But, packaging and distributing these servers is currently a challenge. Specifically:
Environment conflicts: Installing MCP servers often requires specific versions of Node.js, Python, and other dependencies, which may conflict with existing installations on a user’s machine
Lack of host isolation: MCP servers currently run on the host, granting access to all host files and resources
Complex setup: MCP servers currently require users to download and configure all of the code and configure the environment, making adoption difficult
Cross-platform challenges: Running the servers consistently across different architectures (e.g., x86 vs. ARM, Windows vs Mac) or operating systems introduces additional complexity
Dependencies: Ensuring that server-specific runtime dependencies are encapsulated and distributed safely.
How does Docker help?
Docker solves these challenges by providing a standardized method and tooling to develop, package, and distribute applications, including MCP servers. By packaging these MCP servers as containers, the challenges of isolation or environment differences disappear. Users can simply run a container, rather than spend time installing dependencies and configuring the runtime.
Docker Desktop provides a development platform to build, test, and run these MCP servers. Docker Hub is the world’s largest repository of container images, making it the ideal choice to distribute containerized MCP servers. Docker Scout helps ensure images are kept secure and free of vulnerabilities. Docker Build Cloud helps you build images more quickly and reliably, especially when cross-platform builds are required.
The Docker suite of products brings benefits to both publishers and consumers — publishers can easily package and distribute their servers and consumers can easily download and run them with little to no configuration.
Again quoting David Soria Parra,
“Building an MCP server for ffmpeg would be a tremendously difficult undertaking without Docker. Docker is one of the most widely used packaging solutions for developers. The same way it solved the packaging problem for the cloud, it now has the potential to solve the packaging problem for rich AI agents”.
Figure 2: Architecture diagram demonstrating MCP servers running in a Docker container
As we continue to explore how MCP allows us to connect to existing ecosystems of tools, we also envision MCP bridges to existing containerized tools.
Figure 3: Architecture diagram that shows a single MCP server calling multiple tools in their own containers
Try it yourself with containerized Reference Servers
As part of publishing the specification, Anthropic published an initial set of reference servers. We have worked with the Anthropic team to create Docker images for these servers and make them available from the new Docker Hub mcp namespace.
Developers can try this out today using Claude Desktop as the MCP client and Docker Desktop to run any of the reference servers by updating your claude_desktop_config.json file.
The list of current servers documents how to update the claude_desktop_config.json to activate these MCP server docker containers on your local host.
Using Puppeteer to take and modify screenshots using Docker
This demo will use the Puppeteer MCP server to take a screenshot of a website and invert the colors using Claude Desktop and Docker Desktop. Doing this without a containerized environment requires quite a bit of setup, but is fairly trivial using containers.
Update your claude_desktop_config.json file to include the following configuration:
For example, extending Claude Desktop to use puppeteer for browser automation and web scraping requires the following entry (which is fully documented here):
Restart Claude Desktop to apply the changed config file.
Submit the following prompt using the Sonnet 3.5 model:
“Take a screenshot of docs.docker.com and then invert the colors“
Claude will run through several consent screens ensuring that you’re okay running these new tools.
After a brief moment, you’ll have your requested screenshot
What happened? Claude planned out a series of tool calls, starting the puppeteer MCP server in a container, and then used the headless browser in that container to navigate to a site, grab a screenshot, invert the colors on the page, and then finally grab a screenshot of the altered page.
Figure 4: Running Dockerized Puppeteer in Claude Desktop to invert colors on https://docs.docker.com/
Next steps
There’s already a lot that developers can try with this first set of servers. For an educational glimpse into what’s possible with database containers, we recommend that you connect the sqlite server container, and run the sample prompt that it provides. It’s an eye-opening display of what’s already possible today. Plus, the demo is containerized!
We’re busy adding more content to enable you to easily build and distribute your own MCP docker images. We are also encouraging and working closely with the community to package more Docker containers. Please reach out with questions in the discussion group.
This demo will use the Puppeteer MCP server to take a screenshot of a website and invert the colors using Claude Desktop and Docker Desktop. Doing this witho...
Collaboration and security are essential for delivering high-quality applications in modern software development, especially in cloud-native environments. Developers navigate intricate workflows, connect diverse systems, and safeguard applications against emerging threats — all while maintaining velocity and efficiency.
Think of development as preparing a multi-course meal in a high-pressure, professional kitchen, where precision, timing, and communication are critical. Each developer is a chef working on different parts of the dish, passing ingredients (code) along the way. When one part of the system encounters delays, it can ripple across the process, impacting the final result. Similarly, poor collaboration or security gaps can derail a project, causing delays and inefficiencies.
Docker serves as the kitchen manager, ensuring everything flows smoothly, ingredients are passed securely, and security is integrated from start to finish.
Seamless collaboration with Docker Hub and Testcontainers Cloud
Success in a professional kitchen depends on clear communication and coordination. In development, it’s no different. Docker’s collaboration tools, like Docker Hub and Testcontainers Cloud, simplify how teams work together, share resources, and test efficiently.
Docker Hub can be thought of as a kitchen’s “prepped ingredients station.” It’s where some of the most essential ingredients are always ready to go. With a vast selection of curated, trusted images, developers can quickly access high-quality, pre-configured containers, ensuring consistency and reducing the chance for mistakes.
Testcontainers Cloud is like the kitchen’s test station, providing on-demand, production-like environments for testing. Developers can spin up these environments quickly, reducing setup time and ensuring code performs in a real-world setting.
Effective coordination is critical whether you’re in a kitchen or on a development team, especially when projects involve distributed or hybrid teams. Clear communication ensures everyone is aligned and productive. The Docker suite of products provides the tools that make it possible for companies to more easily break down silos, share resources seamlessly, and ensure alignment — no matter how large your team is or where they work!
By streamlining collaboration, Docker reduces complexity and allows teams to move forward with confidence. With Docker Hub, Testcontainers Cloud, and integrated security features, teams can share resources, track progress, and catch issues early, enabling them to deliver high-quality results on time.
These tools improve efficiency, reduce errors, and help teams move faster through the development inner loop by making collaboration seamless and resource sharing simple.
Integrated security from code to production
Embedding security into every development step is essential to maintaining speed and delivering high-quality software. With Docker, security is embedded into every step of the development process so teams can identify and fix issues earlier than ever.
Docker Scout monitors container images in real-time, identifying vulnerabilities early to ensure your software is production-ready. By identifying and resolving risks early, developers can maintain high-quality standards and accelerate time to market.
Docker also integrates additional security features that work behind the scenes:
Hardened Docker Desktop (HDD) strengthens container isolation, protecting against software supply chain risks like malware.
Trusted Content offers developers secure, reliable base images, reducing vulnerabilities in the app’s foundation.
By building security into the workflow, Docker helps teams identify risks earlier, improve code quality, and maintain momentum without compromising safety.
Efficiency in action with Docker
Speed, collaboration, and security are paramount in today’s development landscape. Docker simplifies and secures the development process, helping teams collaborate efficiently and deliver secure, high-quality software faster.
Just as a well-managed kitchen runs smoothly, Docker helps development teams stay coordinated, ensuring security and productivity work together in perfect harmony. Docker removes complexity, accelerates delivery, and embeds security, enabling teams to create efficient, secure applications on time.
Ready to boost efficiency and collaboration in your development process? Explore the Docker suite of productsto see how they can streamline your workflow and improve your team’s productivity today.
Within software development, security and compliance are more than simple boxes to check. Each attestation and compliance check is backed by a well-considered risk assessment that aims to avoid ever-changing vulnerabilities and attack vectors. Software development teams don’t want to worry about vulnerabilities when they are focused on building something remarkable.
In this article, we explain how Docker Hub and Docker Scout can help development teams ensure a more secure and compliant software supply chain.
Security starts with trusted foundations
Every structure needs a strong foundation. A weak base is where cracks begin to show. Using untrusted or outdated software is like building a skyscraper on sand, and security issues can derail progress, leading to costly fixes and delayed releases. By “shifting security left” — addressing vulnerabilities early in the development process — teams can avoid these setbacks down the road.
Modern development demands a secure and compliant software supply chain. Unverified software or vulnerabilities buried deep within base images can become costly compliance issues, disrupting development timelines and eroding customer trust. One weak link in the supply chain can snowball into more significant issues, affecting product delivery and customer satisfaction. Without security and compliance checks, organizations will lack the credibility their customers rely on.
How Docker Hub and Scout help teams shift left
Software developers are like a construction crew building a skyscraper. The process requires specialized components — windows, elevators, wiring, concrete, and so on — which are found at a single supply depot and which work in harmony with each other. This idea is similar to microservices, which are pieced together to create modern applications. In this analogy, Docker Hub acts as the supply depot for a customer’s software supply chain, stocked with trusted container images that help developer teams streamline development.
Docker Hub is more than a container registry. It is the most widely trusted content distribution platform built on secure, verified, and dependable container images. Docker Official Images (DOI) and Docker Verified Publisher (DVP) programs provide a rock-solid base to help minimize risks and let development teams focus on creating their projects.
Docker Hub simplifies supply chain security by ensuring developers start with trusted components. Its library of official and verified publisher images offers secure, up-to-date resources vetted for compliance and reliability, eliminating the risk of untrusted or outdated components.
Proactive risk management is critical to software development
To avoid breaking production environments, organizations need to plan ahead by catching and tracking common vulnerabilities and exposures (CVEs) early in the development process. Docker Scout enables proactive risk management by integrating security checks early in the development lifecycle. Scout reduces the likelihood of security incidents and streamlines the development process.
Additionally, Docker Scout Health Scores provide a straightforward framework for evaluating the security posture of container images used daily by development teams. Using an easy-to-understand alphabetical grading system (A to F), these scores assess CVEs in software components within Docker Hub. This feature lets developers quickly evaluate and select trusted content, ensuring a secure software supply chain.
Avoid shadow changes with IAM and RBAC for secure collaboration
Compliance is not glamorous, but it is essential to running a business. Development teams don’t want to have to worry about whether they are meeting industry standards — they want to know they are. Docker Hub makes compliance simple with pre-certified images and many features that take the guesswork out of governance. That means you can stay compliant while your teams keep growing and innovating.
The biggest challenge to scaling a team or growing your development operations is not about adding people — it’s about maintaining control without losing momentum. Tracking, reducing, and managing shadow changes means that your team does not lose the flow state in development velocity.
Docker Hub’s Image Access Management (IAM) enforces precise permissions to ensure that only authorized people have access to modify sensitive information in repositories. Additionally, with role-based access control (RBAC), you’re not just delegating; you’re empowering your team with predefined roles that streamline onboarding, reduce mistakes, and keep everyone moving in harmony.
Docker Hub’s activity logs provide another layer of confidence as they let you track changes, enforce compliance, and build trust. These capabilities enhance security and boost collaboration by creating an environment where team members can focus on delivering high-quality applications.
Built-in trust
Without verified components, development teams can end up playing whack-a-mole with vulnerabilities. Time is lost. Money is spent. Trust is damaged. Now, picture a team working with trusted content and images that integrate security measures from the start. They deliver on time, on budget, and with confidence.
Building security into your applications doesn’t slow you down; it’s your superpower. Docker weaves trust and security into every part of your development process. Your applications are safeguarded, your delivery is accelerated, and your team is free to focus on what matters most — creating value.
Start your journey today. With Docker, you’re not just developing applications but building trust. Learn how trusted components help simplify compliance, enhance security, and empower your team to innovate fearlessly.
The Docker Desktop 4.37 release brings incremental improvements that make developers’ lives easier by addressing common challenges in modern software development. With a focus on integrating AI resources and streamlining operational workflows, this update ensures developers can work faster, smarter, and more effectively.
Unlocking AI-driven development with Docker AI Catalog integration
AI/ML development is exploding, but many developers face hurdles accessing prebuilt AI models and tools. They often need to search across multiple platforms, wasting valuable time piecing together resources and overcoming compatibility issues. This fragmentation slows down innovation and makes it harder for teams to bring AI-driven features into their applications.
With Docker Desktop 4.37, the AI Catalog in Docker Hub is now accessible directly through Docker Desktop. This seamless integration enables developers to discover, pull, and integrate AI models into their workflows effortlessly. Whether you’re incorporating pretrained machine learning models or exploring generative AI tools, Docker Desktop ensures these resources are just a click away.
Figure 1: AI Catalog in Docker Hub is now accessible directly through Docker Desktop.
Key benefits:
Streamlined discovery: You don’t need to leave your development environment to find AI tools. The AI Catalog is built into Docker Hub and can be immediately accessed from Docker Desktop.
Faster prototyping: By eliminating friction in accessing AI resources, teams can focus on building and iterating faster.
Enhanced compatibility: Docker’s containerized approach ensures AI models run consistently across environments, reducing setup headaches.
Whether you’re developing cutting-edge AI/ML applications or just beginning to experiment with AI tools, this integration empowers developers to innovate without distraction.
Command-line operations: Control Docker Desktop your way
For developers who automate workflows or work heavily in terminal environments, relying solely on graphical user interfaces (GUIs) can be limiting. Starting, stopping, or troubleshooting Docker Desktop often requires GUI navigation, which can disrupt automation pipelines and slow down power users.
Docker Desktop 4.37 introduces robust command-line capabilities for managing Docker Desktop itself. Developers can now perform essential tasks such as starting, stopping, restarting, and checking the status of Docker Desktop directly from the command line.
Faster troubleshooting: Check the status and restart Docker Desktop without leaving the terminal, streamlining issue resolution.
Developer flexibility: A smoother, distraction-free experience for developers who prefer terminal-based workflows.
This new feature bridges the gap between GUI and command-line preferences, allowing developers to tailor their workflows to their needs.
Upgraded components: Keeping developers ahead
Docker Desktop 4.37 includes significant upgrades to its underlying components, bringing enhanced performance, security, and feature sets such as GPU- accelerated workflows.
Here’s what’s new:
Docker Buildx v0.19.2: Optimized multiplatform builds for faster, more efficient pipelines.
At Docker, we aim to provide a stable and dependable development platform so developer teams can focus on creating, not troubleshooting. Docker Desktop 4.37 also addresses several key bugs and usability concerns:
Default disk usage limit: New installations now default to a 1TB disk limit, offering additional flexibility for developers with large containerized applications.
Loopback AF_VSOCK connections: Fixed to ensure container communication reliability.
Dashboard synchronization: Ensures consistent behavior between the Docker Desktop Dashboard and the Docker daemon after engine restarts.
Resource Saver mode stability: Resolves issues with mode reengagement, improving power efficiency for resource-conscious users.
Wrapping up
Docker Desktop 4.37 offers a step forward in enabling developers to innovate. With a focus on AI-driven development and automation-friendly operations, this release aligns with the evolving needs of modern software teams.
Learn more
Authenticate and update to receive your subscription level’s newest Docker Desktop features.
Containerized application development has revolutionized modern software delivery, but slow image builds in CI/CD pipelines can bring developer productivity to a halt. Even with AWS CodeBuild automating application testing and building, teams face challenges like resource constraints, inefficient caching, and complex multi-architecture builds that lead to delays, lower release frequency, and prolonged recovery times.
Enter Docker Build Cloud, a high-performance cloud service designed to streamline image builds, integrate seamlessly with AWS CodeBuild, and reduce build times dramatically. With Docker Build Cloud, you gain powerful cloud-based builders, shared caching, and native multi-architecture support — all while keeping your CI/CD pipelines efficient and your developers focused on delivering value faster.
In this post, we’ll explore how AWS CodeBuild combined with Docker Build Cloud tackles common bottlenecks, boosts build performance, and simplifies workflows, enabling teams to ship more quickly and reliably.
By using AWS CodeBuild, you can automate the build and testing of container applications, enabling the construction of efficient CI/CD workflows. AWS CodeBuild is also integrated with AWS Identity and Access Management (IAM), allowing detailed configuration of access permissions for build processes and control over AWS resources.
Container images built with AWS CodeBuild can be stored in Amazon Elastic Container Registry (Amazon ECR) and deployed to various AWS services, such as Amazon Elastic Container Service (Amazon ECS), Amazon Elastic Kubernetes Service (Amazon EKS), AWS Fargate, or AWS Lambda (Figure 1). Additionally, these services can leverage AWS Graviton, which adopts Arm-based architectures, to improve price performance for compute workloads.
Figure 1: CI/CD pipeline for AWS ECS using AWS CodeBuild (ECS Workshop).
Challenges of container image builds with AWS CodeBuild
Regardless of the tool used, building container images in a CI pipeline often takes a significant amount of time. This can lead to the following issues:
Reduced development productivity
Lower release frequency
Longer recovery time in case of failures
The main reasons why build times can be extended include:
1. Machines for building
Building container images requires substantial resources (CPU, RAM). If the machine specifications used in the CI pipeline are inadequate, build times can increase.
For simple container image builds, the impact may be minimal, but in cases of multi-stage builds or builds with many dependencies, the effect can be significant.
AWS CodeBuild allows changing instance types to improve these situations. However, such changes can apply to parts of the pipeline beyond container image builds, and they also increase costs.
Developers need to balance cost and build speed to optimize the pipeline.
2. Container image cache
In local development environments, Docker’s build cache can shorten rebuild times significantly by reusing previously built layers, avoiding redundant processing for unchanged parts of the Dockerfile. However, in cloud-based CI services, clean environments are used by default, so cache cannot be utilized, resulting in longer build times.
Although there are ways to use storage or container registries to leverage caching, these often are not employed because they introduce complexity in configuration and overhead from uploading and downloading cache data.
3. Multi-architecture builds (AMD64, Arm64)
To use Arm-based architectures like AWS Graviton in Amazon EKS or Amazon ECS, Arm64-compatible container image builds are required.
With changes in local environments, such as Apple Silicon, cases requiring multi-architecture support for AMD64 and Arm64 have increased. However, building images for different architectures (for example, building x86 on Arm, or vice versa) often requires emulation, which can further increase build times (Figure 2).
Although AWS CodeBuild provides both AMD64 and Arm64 instances, running them as separate pipelines is necessary, leading to more complex configurations and operations.
Figure 2: Creating multi-architecture Docker images using AWS CodeBuild.
Accelerating container image builds with Docker Build Cloud
The Docker Build Cloud service executes the Docker image build process in the cloud, significantly reducing build time and improving developer productivity (Figure 3).
Figure 3: How Docker Build Cloud works.
Particularly in CI pipelines, Docker Build Cloud enables faster container image builds without the need for significant changes or migrations to existing pipelines.
Docker Build Cloud includes the following features:
High-performance cloud builders: Cloud builders equipped with 16 vCPUs and 32GB RAM are available. This allows for faster builds compared to local environments or resource-constrained CI services.
Shared cache utilization: Cloud builders come with 200 GiB of shared cache, significantly reducing build times for subsequent builds. This cache is available without additional configuration, and Docker Build Cloud handles the cache maintenance for you.
Multi-architecture support (AMD64, Arm64): Docker Build Cloud supports native builds for multi-architecture with a single command. By specifying --platform linux/amd64,linux/arm64 in the docker buildx build command or using Bake, images for both Arm64 and AMD64 can be built simultaneously. This approach eliminates the need to split the pipeline for different architectures.
Architecture of AWS CodeBuild + Docker Build Cloud
Figure 4 shows an example of how to use Docker Build Cloud to accelerate container image builds in AWS CodeBuild:
Once the builder is successfully created, a guide is displayed for using it in local environments (Docker Desktop, CLI) or CI/CD environments (Figure 5).
Figure 5: Setup instructions of Docker Build Cloud.
Additionally, to use Docker Build Cloud from AWS CodeBuild, a Docker personal access token (PAT) is required. Store this token in AWS Secrets Manager for secure access.
Setting up the AWS CodeBuild pipeline
Next, set up the AWS CodeBuild pipeline. You should prepare an Amazon ECR repository to store the container images beforehand.
The following settings are used to create the AWS CodeBuild pipeline:
AMD64 instance with 3GB memory and 2 vCPUs.
Service role with permissions to push to Amazon ECR and access the Docker personal access token from AWS Secrets Manager.
In the install phase, Buildx, which is necessary for using Docker Build Cloud, is installed.
Although Buildx may already be installed in AWS CodeBuild, it might be an unsupported version for Docker Build Cloud. Therefore, it is recommended to install the latest version.
In the pre_build phase, the following steps are performed:
Log in to Amazon ECR.
Log in to Docker (Build Cloud).
Specify the cloud builder.
In the build phase, the image tag is specified, and the container image is built and pushed to Amazon ECR.
Instead of separating the build and push commands, using --push to directly push the image to Amazon ECR helps avoid unnecessary file transfers, contributing to faster builds.
Results comparison
To make a comparison, an AWS CodeBuild pipeline without Docker Build Cloud is created. The same instance type (AMD64, 3GB memory, 2vCPU) is used, and the build is limited to AMD64 container images.
Additionally, Docker login is used to avoid the pull rate limit imposed by Docker Hub.
Figure 6: The result of the execution without Docker Build Cloud.
Figure 7 shows the execution result of the AWS CodeBuild pipeline using Docker Build Cloud:
Figure 7: The result of the execution with Docker Build Cloud.
The results may vary depending on the container images being built and the state of the cache, but it was possible to build container images much faster and achieve multi-architecture builds (AMD64 and Arm64) within a single pipeline.
Conclusion
Integrating Docker Build Cloud into a CI/CD pipeline using AWS CodeBuild can dramatically reduce build times and improve release frequency. This allows developers to maximize productivity while delivering value to users more quickly.
As mentioned previously, the new Docker subscription already includes a free tier for Docker Build Cloud. Take advantage of this opportunity to test how much faster you can build container images for your current projects.
In 2024, as developers and engineering teams focused on delivering high-quality, secure software faster, Docker continued to evolve with impactful updates and a streamlined user experience. This commitment to empowering developers was recognized in the annual Stack Overflow Developer Survey, where Docker ranked as one of the most loved and widely used tools for yet another year. Here’s a look back at Docker’s 2024 milestones and how we helped teams build, test, and deploy with greater ease, security, and control than ever.
Streamlining the developer experience
Docker focused heavily on streamlining workflows, creating efficiencies, and reducing the complexities often associated with managing multiple tools. One big announcement in 2024 is our upgraded Docker plans. With the launch of updated Docker subscriptions, developers now have access to the entire suite of Docker products under their existing subscription.
The all-in-one subscription model enables seamless integration of Docker Desktop, Docker Hub, Docker Build Cloud, Docker Scout, and Testcontainers Cloud, giving developers everything they need to build efficiently. By providing easy access to the suite of products and flexibility to scale, Docker allows developers to focus on what matters most — building and innovating without unnecessary distractions.
For more details on Docker’s all-in-one subscription approach, check out our Docker plans announcement.
Build up to 39x faster with Docker Build Cloud
Docker Build Cloud, introduced in 2024, brings the best of two worlds — local development and the cloud to developers and engineering teams worldwide. It offloads resource-intensive build processes to the cloud, ensuring faster, more consistent builds while freeing up local machines for other tasks.
A standout feature is shared build caches, which dramatically improve efficiency for engineering teams working on large-scale projects. Shared caches allow teams to avoid redundant rebuilds by reusing intermediate layers of images across builds, accelerating iteration cycles and reducing resource consumption. This approach is especially valuable for collaborative teams working on shared codebases, as it minimizes duplicated effort and enhances productivity.
Docker Build Cloud also offers native support for multi-architecture builds, eliminating the need for setting up and maintaining multiple native builders. This support removes the challenges associated with emulation, further improving build efficiency.
We’ve designed Docker Build Cloud to be easy to set up wherever you run your builds, without requiring a massive lift-and-shift effort. Docker Build Cloud also works well with Docker Compose, GitHub Actions, and other CI solutions. This means you can seamlessly incorporate Docker Build Cloud into your existing development tools and services and immediately start reaping the benefits of enhanced speed and efficiency.
Optimizing development workflows with performance enhancements
In 2024, Docker Desktop introduced a series of enterprise-grade performance enhancements designed to streamline development workflows at scale. These updates cater to the unique needs of development teams operating in diverse, high-performance environments.
One notable feature is the Virtual Machine Manager (VMM) in Docker Desktop for Mac, which provides a robust alternative to the Apple Virtualization Framework. Available since Docker Desktop 4.35, VMM significantly boosts performance for native Arm-based images, delivering faster and more efficient workflows for M1 and M2 Mac users. For development teams relying on Apple’s latest hardware, this enhancement translates into reduced build times and a smoother experience when working with containerized applications.
Additionally, Docker Desktop expanded its platform support to include Red Hat Enterprise Linux (RHEL) and Windows on Arm architectures, enabling organizations to maintain a consistent Docker Desktop experience across a wide array of operating systems. This flexibility ensures that development teams can optimize their workflows regardless of the underlying platform, leveraging platform-specific optimizations while maintaining uniformity in their tooling.
These advancements reflect Docker’s unwavering commitment to speed, reliability, and cross-platform support, ensuring that development teams can scale their operations without bottlenecks. By minimizing downtime and enhancing performance, Docker Desktop empowers developers to focus on innovation, improving productivity across even the most demanding enterprise environments.
More options to improve file operations for large projects
We enhanced Docker Desktop with synchronized file shares (Figure 1), a feature that can significantly improve file operation speeds by 2-10x. This enhancement brings fast and flexible host-to-VM file sharing, offering a performance boost for developers dealing with extensive codebases.
Synchronized file sharing is ideal for developers who:
Develop on projects that consist of a significant number of files (such as PHP or Node projects).
Develop using large repositories or monorepos with more than 100,000 files, totaling significant storage.
Utilize virtual file systems (such as VirtioFS, gRPC FUSE, or osxfs) and face scalability issues with their workflows.
Encounter performance limitations and want a seamless file-sharing solution without worrying about ownership conflicts.
This integration streamlines workflows, allowing developers to focus more on coding and less on managing file synchronization issues and slow file read times.
Figure 1: Synchronized file shares.
Enhancing developer productivity with Docker Debug
Docker Debug enhances the ability of developer teams to debug any container, especially those without a shell (that is, distroless or scratch images). The ability to peek into “secure” images significantly improves the debugging experience for both local and remote containerized applications.
Docker Debug does this by attaching a dedicated debugging toolkit to any image and allows developers to easily install additional tools for quick issue identification and resolution. Docker Debug not only streamlines debugging for both running and stopped containers but also is accessible directly from both the Docker Desktop CLI and GUI (Figure 2).
Figure 2: Docker Debug.
Being able to troubleshoot images without modifying them is crucial for maintaining the security and performance of containerized applications, especially those images that traditionally have been hard to debug. Docker Debug offers:
Streamlined debugging process: Easily debug local and remote containerized applications, even those not running, directly from Docker Desktop.
Cross-device and cloud compatibility: Initiate debugging effortlessly from any device, whether local or in the cloud, enhancing flexibility and productivity.
Docker Debug improves productivity and seamless integration. The docker debug command simplifies attaching a shell to any container or image. This capability reduces the cognitive load on developers, allowing them to focus on solving problems rather than configuring their environment.
Ensuring reliable image builds with Docker Build checks
Docker Desktop 4.33 was a big release because, in addition to including the GA release of Docker Debug, it included the GA release of Docker Build checks, a new feature that ensures smoother and more reliable image builds. Build checks automatically validate common issues in your Dockerfiles before the build process begins, catching errors like invalid syntax, unsupported instructions, or missing dependencies. By surfacing these issues upfront, Docker Build checks help developers save time and avoid costly build failures.
You can access Docker Build checks in the CLI and in the Docker Desktop Builds view. The feature also works seamlessly with Docker Build Cloud, both locally and through CI. Whether you’re optimizing your Dockerfiles or troubleshooting build errors, Docker Build checks let you create efficient, high-quality container images with confidence — streamlining your development workflow from start to finish.
Onboarding and learning resources for developer success
To further reduce friction, Docker revamped its learning resources and integrated new tools to enhance developer onboarding. By adding beginner-friendly tutorials, Docker’s learning center makes it easier for developers to ramp up and quickly learn to use Docker tools, helping them spend more time coding and less time troubleshooting.
As Docker continues to rank as a top developer tool globally, we’re dedicated to empowering our community with continuous learning support.
Built-in container security from code to production
In an era where software supply chain security is essential, Docker has raised the bar on container security. With integrated security measures across every phase of the development lifecycle, Docker helps teams build, test, and deploy confidently.
Proactive security insights with Docker Scout Health Scores
Docker Scout, launched in 2023, has become a cornerstone of Docker’s security ecosystem, empowering developer teams to identify and address vulnerabilities in container images early in the development lifecycle. By integrating with Docker Hub, Docker Desktop, and CI/CD workflows, Scout ensures that security is seamlessly embedded into every build.
Addressing vulnerabilities during the inner loop — the development phase — is estimated to be up to 100 times less costly than fixing them in production. This underscores the critical importance of early risk visibility and remediation for engineering teams striving to deliver secure, production-ready software efficiently.
In 2024, we announced Docker Scout Health Scores (Figure 3), a feature designed to better communicate the security posture of container images development teams use every day. Docker Scout Health Scores provide a clear, alphabetical grading system (A to F) that evaluates common vulnerabilities and exposures (CVEs) for software components within Docker Hub. This feature allows developers to quickly assess and wisely choose trusted content for a secure software supply chain.
Air-gapped containers: Enhanced security for isolated environments
Docker introduced support for air-gapped containers in Docker Desktop 4.31, addressing the unique needs of highly secure, offline environments. Air-gapped containers enable developers to build, run, and test containerized applications without requiring an active internet connection.
This feature is crucial for organizations operating in industries with stringent compliance and security requirements, such as government, healthcare, and finance. By allowing developers to securely transfer container images and dependencies to air-gapped systems, Docker simplifies workflows and ensures that even isolated environments benefit from the power of containerization.
Strengthening trust with SOC 2 Type 2 and ISO 27001 certifications
Docker also achieved two major milestones in its commitment to security and reliability: SOC 2 Type 2 attestation and ISO 27001 certification. These globally recognized standards validate Docker’s dedication to safeguarding customer data, maintaining robust operational controls, and adhering to stringent security practices. SOC 2 Type 2 attestation focuses on the effective implementation of security, availability, and confidentiality controls, while ISO 27001 certification ensures compliance with best practices for managing information security systems.
These certifications provide developers and organizations with increased confidence in Docker’s ability to support secure software supply chains and protect sensitive information. They also demonstrate Docker’s focus on aligning its services with the needs of modern enterprises.
Accelerating success for development teams and organizations
In 2024, Docker introduced a range of features and enhancements designed to empower development teams and streamline operations across organizations. From harnessing the potential of AI to simplifying deployment workflows and improving security, Docker’s advancements are focused on enabling teams to work smarter and build with confidence. By addressing key challenges in development, management, and security, Docker continues to drive meaningful outcomes for developers and businesses alike.
Docker Home: A central hub to access and manage Docker products
Docker introduced Docker Home (Figure 4), a central hub for users to access Docker products, manage subscriptions, adjust settings, and find resources — all in one place. This approach simplifies navigation for developers and admins. Docker Home allows admins to manage organizations, users, and onboarding processes, with access to dashboards for monitoring Docker usage.
Future updates will add personalized features for different roles, and business subscribers will gain access to tools like the Docker Support portal and organization-wide notifications.
Figure 4: Docker Home.
Empowering AI innovation
Docker’s ecosystem supports AI/ML workflows, helping developers work with these cutting-edge technologies while staying cloud-native and agile. Read the Docker Labs GenAI series to see how we’re innovating and experimenting in the open.
Through partnerships like those with NVIDIA and GitHub, Docker ensures seamless integration of AI tools, allowing teams to rapidly experiment, deploy, and iterate. This emphasis on enabling advanced tech aligns Docker with organizations looking to leverage AI and ML in containerized environments.
Optimizing AI application development with Docker Desktop and NVIDIA AI Workbench
Docker and NVIDIA partnered to integrate Docker Desktop with NVIDIA AI Workbench, streamlining AI development workflows. This collaboration simplifies setup by automatically installing Docker Desktop when selected as the container runtime in AI Workbench, allowing developers to focus on creating, testing, and deploying AI models without configuration hassles. By combining Docker’s containerization capabilities with NVIDIA’s advanced AI tools, this integration provides a seamless platform for model training and deployment, enhancing productivity and accelerating innovation in AI application development.
We announced that Docker joined GitHub’s Partner Program and unveiled the Docker extension for GitHub Copilot (@docker). This extension is designed to assist developers in working with Docker directly within their GitHub workflows. This integration extends GitHub Copilot’s technology, enabling developers to generate Docker assets, learn about containerization, and analyze project vulnerabilities using Docker Scout, all from within the GitHub environment.
Accelerating AI development with the Docker AI catalog
Docker launched the AI Catalog, a curated collection of generative AI images and tools designed to simplify and accelerate AI application development. This catalog offers developers access to powerful models like IBM Granite, Llama, Mistral, Phi 2, and SolarLLM, as well as applications such as JupyterHub and H2O.ai. By providing essential tools for machine learning, model deployment, inference optimization, orchestration, ML frameworks, and databases, the AI Catalog enables developers to build and deploy AI solutions more efficiently.
The Docker AI Catalog addresses common challenges in AI development, such as decision overload from the vast array of tools and frameworks, steep learning curves, and complex configurations. By offering a curated list of trusted content and container images, Docker simplifies the decision-making process, allowing developers to focus on innovation rather than setup. This initiative underscores Docker’s commitment to empowering developers and publishers in the AI space, fostering a more streamlined and productive development environment.
Streamlining enterprise administration
Simplified deployment and management with Docker’s MSI and PKG installers
Docker simplifies deploying and managing Docker Desktop with the new MSI Installer for Windows and PKG Installer for macOS. The MSI Installer enables silent installations, automated updates, and login enforcement, streamlining workflows for IT admins. Similarly, the PKG Installer offers macOS users easy deployment and management with standard tools. These installers enhance efficiency, making it easier for organizations to equip teams and maintain secure, compliant environments.
These new installers also align with Docker’s commitment to simplifying the developer experience and improving organizational management. Whether you’re setting up a few machines or deploying Docker Desktop across an entire enterprise, these tools provide a reliable and efficient way to keep teams equipped and ready to build.
New sign-in enforcement options enhance security and help streamline IT administration
Docker simplifies IT administration and strengthens organizational security with new sign-in enforcement options for Docker Desktop. These features allow organizations to ensure users are signed in while using Docker, aligning local software with modern security standards. With flexible deployment options — including macOS Config Profiles, Windows Registry Keys, and the cross-platform registry.json file — IT administrators can easily enforce policies that prevent tampering and enhance security. These tools empower organizations to manage development environments more effectively, providing a secure foundation for teams to build confidently.
Desktop Insights: Unlocking performance and usage analytics
Docker introduced Desktop Insights, a powerful feature that provides developers and teams with actionable analytics to optimize their use of Docker Desktop. Accessible through the Docker Dashboard, Desktop Insights offers a detailed view of resource usage, build times, and performance metrics, helping users identify inefficiencies and fine-tune their workflows (Figure 5).
Whether you’re tracking the speed of container builds or understanding how resources like CPU and memory are being utilized, Desktop Insights empowers developers to make data-driven decisions. By bringing transparency to local development environments, this feature aligns with Docker’s mission to streamline container workflows and ensure developers have the tools to build faster and more effectively.
Figure 5: Desktop Insights dashboard.
New usage dashboards in Docker Hub
Docker introduced Usage dashboards in Docker Hub, giving organizations greater visibility into how they consume resources. These dashboards provide detailed insights into storage and image pull activity, helping teams understand their usage patterns at a granular level (Figure 6).
By breaking down data by repository, tag, and even IP address, the dashboards make it easy to identify high-traffic images or repositories that might require optimization. With this added transparency, teams can better manage their storage, avoid unnecessary pull requests, and optimize workflows to control costs.
Usage dashboards enhance accountability and empower organizations to fine-tune their Docker Hub usage, ensuring resources are used efficiently and effectively across all projects.
Figure 6: Usage dashboard.
Enhancing security with organization access tokens
Docker introduced organization access tokens, which let teams manage access to Docker Hub repositories at an organizational level. Unlike personal access tokens tied to individual users, these tokens are associated with the organization itself, allowing for centralized control and reducing reliance on individual accounts. This approach enhances security by enabling fine-grained permissions and simplifying the management of automated processes and CI/CD pipelines.
Organization access tokens offer several advantages, including the ability to set specific access permissions for each token, such as read or write access to selected repositories. They also support expiration dates, aligning with compliance requirements and bolstering security. By providing visibility into token usage and centralizing management within the Admin Console, these tokens streamline operations and improve governance for organizations of all sizes.
Docker’s vision for 2025
Docker’s journey doesn’t end here. In 2025, Docker remains committed to expanding its support for cloud-native and AI/ML development, reinforcing its position as the go-to container platform. New integrations and expanded multi-cloud capabilities are on the horizon, promising a more connected and versatile Docker ecosystem.
As Docker continues to build for the future, we’re committed to empowering developers, supporting the open source community, and driving efficiency in software development at scale.
2024 was a year of transformation for Docker and the developer community. With major advances in our product suite, continued focus on security, and streamlined experiences that deliver value, Docker is ready to help developer teams and organizations succeed in an evolving tech landscape. As we head into 2025, we invite you to explore Docker’s suite of tools and see how Docker can help your team build, innovate, and secure software faster than ever.
This ongoing Docker Labs GenAI series explores the exciting space of AI developer tools. At Docker, we believe there is a vast scope to explore, openly and without the hype. We will share our explorations and collaborate with the developer community in real time. Although developers have adopted autocomplete tooling like GitHub Copilot and use chat, there is significant potential for AI tools to assist with more specific tasks and interfaces throughout the entire software lifecycle. Therefore, our exploration will be broad. We will be releasing software as open source so you can play, explore, and hack with us, too.
In our past experiments, we started our work from the assumption that we had a project ready to work on. That means someone like a UI tech writer would need to understand Git operations in order to use the tools we built for them. Naturally, because we have been touching on Git so frequently, we wanted to try getting a Git agent started. Then, we want to use this Git agent to understand PR branches for a variety of user personas — without anyone needing to know the ins and outs of Git.
Git as an agent
We are exploring the idea that tools are agents. So, what would a Git agent do?
Let’s tackle our UI use case prompt.
Previously:
You are at $PWD of /project, which is a git repo.
Force checkout {{branch}}
Run a three-dot diff of the files changed in {{branch}} compared to main using --name-only.
A drawback that isn’t shown here, is that there is no authentication. So, if you haven’t fetched that branch or pulled commits already, this prompt at best will be unreliable and more than likely will fail (Figure 1):
Figure 1: No authentication occurs.
Now:
You are a helpful assistant that checks a PR for user-facing changes.
1. Fetch everything and get on latest main.
2. Checkout the PR branch and pull latest.
3. Run a three-dot git diff against main for just files. Write the output to /thread/diff.txt.
This time around, you can see that we are being less explicit about the Git operations, we have the ability to export outputs to the conversation thread and, most importantly, we have authentication with a new prompt!
Preparing GitHub authentication
Note: These prompts should be easily adaptable to other Git providers, but we use GitHub at Docker.
Before we can do anything with GitHub, we have to authenticate. There are several ways to do this, but for this post we’ll focus on SSH-based auth rather than using HTTPS through the CLI. Without getting too deep into the Git world, we will be authenticating with keys on our machine that are associated with our account. These keys and configurations are commonly located at ~/.ssh on Linux/Mac. Furthermore, users commonly maintain Git config at ~/.gitconfig.
The .gitconfig file is particularly useful because it lets us specify carriage return rules — something that can easily cause Git to fail when running in a Linux container. We will also need to modify our SSH config to remove UseKeychain. We found these changes are enough to authenticate using SSH in Alpine/Git. But we, of course, don’t want to modify any host configuration.
We came up with a fairly simple flow that lets us prepare to use Git in a container without messing with any host SSH configs.
Readonly mounts: Git config and SSH keys are stored on specific folders on the host machine. We need to mount those in. a. Mount ~/.ssh into a container as /root/.ssh-base readonly. b. Mount ~/.gitconfig into the same container as /root/.gitconfig.
Copy /root/.ssh-base to /root/.ssh and make the new file readwrite.
Make necessary changes to config.
For the LLM, we also need it to verify the config is in the thread and the changes were made to it. In the event that it fails to make the right changes, the LLM can self-correct.
Copy the .ssh directory and .gitconfig to /thread.
All of this is baked in a prompt you can find and run on GitHub. Simply replace <username> with your system username (Figure 2).
Figure 2: Readonly mounts.
If you’re using the default behavior in our extension for VSCode, then the /thread/ volume is ephemeral, so you would need to make sure your agent runs it before any Git tools. However, if you use the Set prompt thread ID command in VSCode, you can keep the /thread volume around under your own tag (Figure 3).
Tagging the thread persists everything after the prompt completes, so you would only need to run the prompt once before going on to develop your Git tools.
Figure 3: Set the prompt thread ID.
If you opt to persist the thread, then this prompt would only need to be run once and the Git credentials will stick around (Figure 4).
Figure 4: Stored credential data.
Now that we have our credentials ready, we need our Git tool to pick up on them.
Our container definition copies the SSH credentials and .gitconfig files to the correct directory before running Git commands.
Unpacking objects: 90% (9/10)
Unpacking objects: 100% (10/10)
Unpacking objects: 100% (10/10), 4.14 KiB | 141.00 KiB/s, done.
From github.com:docker/repo
abcd123..abcd123 main -> origin/main
* [new tag] branch/v2982.0.0 -> branch/v2982.0.0
# ROLE assistant
I have fetched all origin branches. The latest updates have been applied to your local repository, and any new tags have been downloaded.
```
Now, we can see our Git tool is authenticated as if it were us.
Running the agent now, it can:
## ROLE assistant
I have run the git fetch --all command, which retrieves updates from all remotes. If you need further assistance with your Git repository, feel free to ask!
```
# ROLE assistant
```json
{"request":"checkout main"}
```
## ROLE assistant
```json
{"args":"checkout main"}
```
## ROLE assistant
You are already on the 'main' branch, and it is up to date with 'origin/main'.
```
# ROLE assistant
```json
{"request":"checkout the branch branch and pull latest changes."}
```
...
## ROLE assistant
The branch branch has been successfully checked out, and it's already up to date with the latest changes.
...
# ROLE assistant
```json
{"request":"Run a three-dot git diff against main and write the output for just files to /thread/diff.txt."}
```
...
## ROLE assistant
```json
{"args":"diff main... --name-only","outfile":"/thread/diff.txt"}
```
*entering tool*
## ROLE tool (git)
file1.tsx
file2.tsx
...
## ROLE assistant
The three-dot Git diff against the main branch has been executed, and the output has been saved to /thread/diff.txt. This includes the names of files that have differences.
``
With the new Git agent, we have enabled our assistant to fetch new information from upstream, switch branches, and pull in new code to review. If we provide our agent with credentials that are limited to read-only access, this agent could be used by someone that does not have a local git install.
For more on what we’re doing at Docker, subscribe to our newsletter.
This ongoing Docker Labs GenAI series explores the exciting space of AI developer tools. At Docker, we believe there is a vast scope to explore, openly and without the hype. We will share our explorations and collaborate with the developer community in real time. Although developers have adopted autocomplete tooling like GitHub Copilot and use chat, there is significant potential for AI tools to assist with more specific tasks and interfaces throughout the entire software lifecycle. Therefore, our exploration will be broad. We will be releasing software as open source so you can play, explore, and hack with us, too.
Can an AI-powered assistant understand a GitHub repo enough to answer questions for UI writers?
Across many projects, user-facing content is rendered based on some sort of client-side code. Whether a website, a game, or a mobile app, it’s critical to nail the text copy displayed to the user.
So let’s take a sample question: Do any open PRs in this project need to be reviewed for UI copy? In other words, we want to scan a GitHub repo’s PRs and gain intelligence about the changes included.
Disclaimer: The best practice to accomplish this at a mature organization would be to implement Localization (i18n), which would facilitate centralized user-facing text. However, in a world of AI-powered tools, we believe our assistants will help minimize friction for all projects, not just ones that have adopted i18n.
So, let’s start off by seeing what options we already have.
The first instinct someone might have is to open the new copilot friend in the GitHub nav
Figure 1: Type / to search.
We tried to get it to answer basic questions, first: “How many PR’s are open?”
Figure 2: How many PR’s are there open? The answer doesn’t give a number.
Despite having access to the GitHub repo, the Copilot agent provides less helpful information than we might expect.
Figure 3: Copilot is powered by AI, so mistakes are possible.
We don’t even get a number like we asked, despite GitHub surfacing that information on the repository’s main page. Following up our first query with the main query we want to ask effectively just gives us the same answer
Figure 4: The third PR is filesharing: add some missing contexts.
And, after inspecting the third PR in the list, it doesn’t contain user-facing changes. One great indicator for this web project is the lack of any clientside code being modified. This was a backend change so we didn’t want to see this one.
Figure 5: The PR doesn’t contain user-facing changes.
So let’s try to improve this:
First prompt file
---
functions:
- name: bash
description: Run a bash script in the utilities container.
parameters:
type: object
properties:
command:
type: string
description: The command to send to bash
container:
image: wbitt/network-multitool
command:
- "bash"
- "-c"
- "{{command|safe}}"
- name: git
description: Run a git command.
parameters:
type: object
properties:
command:
type: string
description: The git command to run, excluding the `git` command itself
container:
image: alpine/git
entrypoint:
- "/bin/sh"
command:
- "-c"
- "git --no-pager {{command|safe}}"
---
# prompt system
You are a helpful assistant that helps the user to check if a PR contains any user-facing changes.
You are given a container to run bash in with the following tools:
curl, wget, jq
and default alpine linux tools too.
# prompt user
You are at $PWD of /project, which is a git repo.
Checkout branch `{{branch}}`.
Diff the changes and report any containing user facing changes
This prompt was promising, but it ended up with a few blocking flaws. The reason is that using git to compare files is quite tricky for an LLM.
git diff uses a pager, and therefore needs the --no-pager arg to send stdout to the conversation.
The total number of files affected via git diff can be quite large.
Given each file, the raw diff output can be massive and difficult to parse.
The important files changed in a PR might be buried with many extra files in the diff output.
The container has many more tools than necessary, allowing the LLM to hallucinate.
The agent needs some understanding of the repo to determine the sorts of files that contain user-facing changes, and it needs to be capable of seeing just the important pieces of information.
Our next pass involves a few tweaks:
Switch to alpine git image and a file writer as the only tools necessary.
Use –files-only and –no-pager args.
# ROLE assistant
The following files are likely to contain user-facing changes as they mainly consist of UI components, hooks, and API functionalities.
```
file1.ts
fil2.tsx
file3.tsx
...
```
Remember that this isn't a guarantee of whether there are user-facing changes, but just an indication of where they might be if there are any.
Remember that this isn’t a guarantee of whether there are user-facing changes, but just an indication of where they might be if there are any.
Giving the agent the tool run-javascript-sandbox allowed our agent to write a script to save the output for later.
Figure 6: Folder called user-changes with files.txt.
This is a great start; however, we now need to inspect the files themselves for user-facing changes. When we started this, we realized that user-facing changes could manifest in a diverse set of “diff”s so we needed to include expert knowledge. We synced up with Mark Higson, a staff SWE currently working on the frontend platform here at Docker. Mark was able to help provide some key advice for what “user-facing” changes look like in many repos at Docker, so I baked the tips into the prompt.
Straightforward approaches
Looking for changes in text nodes found in a JSX tree is the easiest example.
JSX node with interpolation
<div>{functionReturningString()}</div>
If the result is a string, the result is probably user-facing, but the components that create the string could be elsewhere, so look for:
Nuanced indicators
Standard user-facing components. Example: notifications. If a notification’s props change, we can likely infer that it is a user-facing change.
Constructors for commonly used components. Example: errors. If an Error() is constructed with a different argument, we know that error could show up differently.
The key for UI reviewers is the overall amount of text is changed, rather than layout.
So, despite not being able to catch everything that could be rendered, we will be able to deliver value by focusing on these areas.
Diffing the files
There are a few approaches to finding changes in the files. To start, we’ll use git again.
Before including expert advice, git diff was hallucinating changes that weren’t actually represented in the output. After the expert advice, we are seeing much more focused outputs from the LLM.
Our second prompt just needs to read the user-facing files that we already saved, and then compare them to main. After a bit of trial and error with git, we found that a combination of --no-color and --minimal was able to give the LLM enough context without consuming too many tokens for each change.
There’s a lot of buzz around generating and reading diffs with LLMs. The teams at Aider and Cursor are both focusing on fine-tuning LLM’s using speculative decoding:
For our use cases, however, we found that the average “big” PR at Docker was not a problem for traditional LLMs when given good advice and the right tools.
So here’s the second prompt:
## User-facing content
The following pieces of code are what we want to focus on for user-facing content:
Text Nodes in any JSX or TSX files.
Text Nodes in any HTML files.
Standard user-facing components. Example: Definitions/Constructors for notifications, toasts, and errors.
# prompt user
Can you tell me if there are any user-facing changes in {{branch}}?
Note: Some full paths, branches, and diffs are trimmed or replaced with placeholders for this article.
# ROLE assistant
```json
{
"args": ["checkout", "branch"]
}
```
# ROLE tool (git)
Already on 'branch'
Your branch is up to date with 'origin/branch'.
# ROLE assistant
```json
{
"path": "/thread/user-changes/files.txt"
}
```
*entering tool*
# ROLE tool (read-file)
path1
path2
path3
...rest of paths
# ROLE assistant
```json
{
"args": ["diff", "main", "--no-color", "--minimal", path1 path2 path3...]
}
```
*entering tool*
# ROLE tool (git)
<Diff output truncated>
# ROLE assistant
The following user-facing changes were detected between the "main" branch and the "branch" branch:
1. In `File1.tsx` file, the text "Sign In" was modified to "Sign in".
2. In `File2.ts` file, titles "Databases & Storage", "Monitoring & Observability", "Developer Tools", "New Extensions", were changed to "Databases & storage", "Monitoring & observability", "Developer tools", "New extensions" respectively.
3. In `File3.rtl.test.tsx.snap` and `ImageHeader/index.tsx files`, the text "Compressed Size " was changed to "Compressed size".
4. In `File4.rtl.test.tsx` and `ImageDetail/index.tsx files`, a test-case previously checking for the existence of "Compressed Size" now looks for "Compressed size".
5. In `File5.tsx file`, the button text "Add Collaborator" has been changed to "Add collaborator".
6. In `route.tsx file`, the collaborators table title "Current Collaborators" was changed to "Current collaborators".
7. In `File6.tsx` file, the description was updated.
8. In `File7.tsx`, `RepositoryOverview.tsx`, `RepositoryReadMe.tsx`, `TagsAndScans.tsx` files, the description when there is no category or description was updated.
9. In `File8.rtl.test.tsx`, `DeleteRepo.tsx`, the text for confirming repo deletion and the delete button text was adjusted.
10. In `route.tsx file`, the filter label "Trusted Content" was changed to "Trusted content".
11. In `File9.tsx`, the text "Your Organizations" has been changed to "Your organizations".
12. In `Component/index.tsx`, the search group label "Trusted Content" has been changed to "Trusted content".
13. In `file10.test.ts` file, a test-case was updated to check for the new text "Sign in".
```
The changes in the `branch` branch compared to `main` include several modifications that affect user-facing content, particularly in JSX and TSX files. Here is a summary of the key changes:
...
These changes primarily involve simplification and refactoring of the existing UI logic, possibly to streamline the user interaction by removing complexities related to feature flags and reducing the use of modals or conditional rendering for specific purchasing flows.
This is already a promising flow. For example, a tech writer could clone the git repo and run this prompt to inspect a branch for user-facing changes. From here, we might extend the functionality:
Allow user input for PR to review without knowing the branch or git needing to use git.
Automatic git clone & pull with auth.
Support for larger >15 files changed PR by allowing agents to automate their tasks.
“Baking” the final flow into CI/CD so that it can automatically assign reviewers to relevant PRs.
If you’re interested in running this prompt on your own repo or just want to follow along with the code, watch our new public repo and reach out. We also appreciate your GitHub Stars.
Everything we’ve discussed in this blog post is available for you to try out on your own projects.
For more on what we’re doing at Docker, subscribe to our newsletter.
Modern application development has evolved dramatically. Gone are the days when a couple of developers, a few machines, and some pizza were enough to launch an app. As the industry grew, DevOps revolutionized collaboration, and Docker popularized containerization, simplifying workflows and accelerating delivery.
Later, DevSecOps brought security into the mix. Fast forward to today, and the demand for software has never been greater, with more than 750 million cloud-native apps expected by 2025.
This explosion in demand has created a new challenge: complexity. Applications now span multiple programming languages, frameworks, and architectures, integrating both legacy and modern systems. Development workflows must navigate hybrid environments — local, cloud, and everything in between. This complexity makes it harder for companies to deliver innovation on time and stay competitive.
To overcome these challenges, you need a development platform that’s as reliable and ubiquitous as electricity or Wi-Fi — a platform that works consistently across diverse applications, development tools, and environments. Whether you’re just starting to move toward microservices or fully embracing cloud-native development, Docker meets your team where they are, integrates seamlessly into existing workflows, and scales to meet the needs of individual developers, teams, and entire enterprises.
Docker: Simplifying the complex
The Docker suite of products provides the tools you need to accelerate development, modernize legacy applications, and empower your team to work efficiently and securely. With Docker, you can:
Modernize legacy applications: Docker makes it easy to containerize existing systems, bringing them closer to modern technology stacks without disrupting operations.
Boost productivity for cloud-native teams: Docker ensures consistent environments, integrates with CI/CD workflows, supports hybrid development environments, and enhances collaboration
Consistent environments: Build once, run anywhere
Docker ensures consistency across development, testing, and production environments, eliminating the dreaded “works on my machine” problem. With Docker, your team can build applications in unified environments — whether on macOS, Windows, or Linux — for reliable code, better collaboration, and faster time to market.
With Docker Desktop, developers have a powerful GUI and CLI for managing containers locally. Integration with popular IDEs like Visual Studio Code allows developers to code, build, and debug within familiar tools. Built-in Kubernetes support enables teams to test and deploy applications on a local Kubernetes cluster, giving developers confidence that their code will perform in production as expected.
Integrated workflows for hybrid environments
Development today spans both local and cloud environments. Docker bridges the gap and provides flexibility with solutions like Docker Build Cloud, which speeds up build pipelines by up to 39x using cloud-based, multi-platform builders. This allows developers to focus more on coding and innovation, rather than waiting on builds.
Docker also integrates seamlessly with CI/CD tools like Jenkins, GitLab CI, and GitHub Actions. This automation reduces manual intervention, enabling consistent and reliable deployments. Whether you’re building in the cloud or locally, Docker ensures flexibility and productivity at every stage.
Team collaboration: Better together
Collaboration is central to Docker. With integrations like Docker Hub and other registries, teams can easily share container images and work together on builds. Docker Desktop features like Docker Debug and the Builds view dashboards empower developers to troubleshoot issues together, speeding up resolution and boosting team efficiency.
Docker Scout provides actionable security insights, helping teams identify and resolve vulnerabilities early in the development process. With these tools, Docker fosters a collaborative environment where teams can innovate faster and more securely.
Why Docker?
In today’s fast-paced development landscape, complexity can slow you down. Docker’s unified platform reduces complexity as it simplifies workflows, standardizes environments, and empowers teams to deliver software faster and more securely. Whether you’re modernizing legacy applications, bridging local and cloud environments, or building cutting-edge, cloud-native apps, Docker helps you achieve efficiency and scale at every stage of the development lifecycle.
Ready to simplify your development workflows? Start your Docker journey now and equip your team with the tools they need to innovate, collaborate, and deliver with confidence.
Looking for tips and tricks? Subscribe to Docker Navigator for the latest updates and insights delivered straight to your inbox.
Software engineering is a dynamic, high-pressure field where development teams encounter a variety of challenges every day. As software development projects become increasingly complex, engineers must maintain high-quality code, meet time constraints, collaborate effectively, and prevent security vulnerabilities. At the same time, development teams can be held back by inefficiencies that can hinder productivity and speed.
Let’s explore some of the most common software engineering challenges and how Docker’s tools streamline the inner loop of cloud-native workflows. These tools help developers overcome pain points, boost productivity, and deliver better software faster.
Top 4 software engineering challenges developers face
Let’s be real — software development teams face a laundry list of challenges. From managing dependencies across teams to keeping up with the latest threats in an increasingly complex software ecosystem, these obstacles can quickly become roadblocks that stifle progress. Let’s dive into some of the most significant software engineering challenges that developers face today and how Docker can help:
1. Dependency management
One of the most common pain points in software engineering is managing dependencies. In any large development project, multiple teams might work on different parts of the codebase, often relying on various third-party libraries and services. The complexity increases when these dependencies span across different environments and versions.
The result? Version conflicts, broken builds, deployment failures, and hours spent troubleshooting. This process can become even more cumbersome when working with legacy code or when different teams work with conflicting versions.
Containerize your applications with their dependencies
Docker allows developers to package all their apps and dependencies into neat, lightweight containers. Think of these containers as “time capsules” that hold everything your app needs to run smoothly, from libraries and tools to configurations. And because these containers are portable, you get the same app behavior on your laptop, your testing server, or in production — no more hoping that “it worked on my machine” when it’s go-time.
No more version conflict drama. No more hours spent trying to figure out which version of the library your coworker’s been using. Docker ensures that everyone on the team works with the same setup. Consistent environments, happy devs, and no more dependency issues!
2. Testing complexities
Testing presents another significant challenge for developers. In an ideal world, tests would run in an environment that perfectly mirrors production; however, this is rarely the case. Developers often encounter problems when testing code in isolated environments that don’t reflect real-world conditions. As a result, bugs that might have been caught early in development are only discovered later, leading to costly fixes and delays.
Moreover, when multiple developers work in different environments or use different tools, the quality of tests can be inconsistent, and issues might be missed altogether. This leads to inefficiencies and makes it harder to ensure that your software is functional and reliable.
Leverage cloud-native testing environments that match production
One of Docker’s most significant benefits is its ability to create cloud-native testing environments. With Testcontainers Cloud, you can integrate testing within containers to create consistent, reliable testing environments that scale by defining test dependencies as code with confidence that they match production. Testing ensures that bugs and issues are caught earlier in the development cycle, reducing the time spent on troubleshooting and improving the overall quality of the software.
Docker Hub offers a repository of pre-configured images and environments, enabling developers to quickly share and collaborate on testing setups. This eliminates inconsistencies between test environments, ensuring all teams work with the same configurations and tools.
3. Lack of visibility and collaboration
Software development today often involves many developers working on different parts of a project simultaneously. This collaborative approach has obvious benefits, but can also lead to significant challenges. In a multi-developer environment, tracking changes, ensuring consistency, and maintaining smooth collaboration across teams can be hard.
Without proper visibility into the software development process, identifying issues in real-time and keeping everyone aligned becomes difficult. In many cases, teams end up working in silos, each using their own tools and systems. This lack of coherence can lead to misunderstandings, duplication of efforts, and delays in achieving milestones.
Accelerate teamwork with shared images, caches, and insights
Docker fosters collaboration by offering an integrated ecosystem where developers can seamlessly share images, cache, templates, and more. For example, Docker Hub and Hardened Docker Desktop allow teams to push, pull, and share secure images, making it easier to get started quickly using all the right configurations. Meanwhile, teams can also cut down on time-consuming builds and resolve failed builds with the Docker Build Cloud shared cache and Build insights.
Docker’s streamlined workflows provide greater visibility into the development process. With this improved collaboration and integrated workflows, software developers can enjoy faster development cycles and more time to innovate.
4. Security risks
Security is often a major concern in software development, yet it’s a challenge that many teams struggle to address consistently. Developers are constantly working under tight deadlines to release new features and fixes, which can sometimes push security considerations to the sidelines. As a result, vulnerabilities can be unintentionally introduced into the codebase through outdated libraries, insecure configurations, and even simple coding oversights.
The main challenge with security lies in identifying and managing risks across all development stages and environments. Developers must follow security protocols diligently and vulnerabilities need to be patched quickly, especially when building software for organizations with strict security regulations. This becomes increasingly difficult when multiple teams work on separate components, each potentially introducing its own security concerns.
Embed security into every phase of the development lifecycle
Docker solves these challenges by integrating security and compliance from build to production, without sacrificing speed or flexibility. For example, Docker Scout offers continuous vulnerability scanning and actionable insights, enabling teams to identify and address risks early. And with increased visibility into dependencies, images, and remediation recommendations, developers can be set up to prevent outdated libraries and insecure configurations from reaching production.
With tools like Hardened Docker Desktop, IAM, and RAM, Docker reduces the complexity of security oversight while ensuring compliance. These features help organizations avoid costly vulnerabilities, safeguard intellectual property, and maintain customer trust without slowing development speed. This simplified security management allows developers to deliver faster without compromising security.
Adopt Docker to overcome key challenges in software development
From dependency management to security risks, software developers face numerous challenges on their journey to deliver high-quality, secure applications. Docker’s unified development suite streamlines every stage of the inner loop, combining Docker Desktop, Docker Hub, Docker Build Cloud, Docker Scout, and Testcontainers Cloud into one powerful, cloud-native workflow ecosystem.
By streamlining workflows, enhancing collaboration, embedding security into every stage of development, and providing consistent testing environments, Docker empowers teams to build, test, and ship cloud-native applications with unparalleled speed and reliability. Whether you’re tackling legacy code or scaling modern applications, Docker ensures your development process remains efficient, secure, and ready for the demands of today’s fast-paced software landscape.
Docker’s subscription plans offer flexible, scalable access to a unified inner-loop suite, allowing teams of any size to accelerate workflows, ensure consistency, and build better software faster. It’s more than a set of tools — it offers a cohesive platform designed to transform your development lifecycle and keep your team competitive, efficient, and secure.
Did you know that enterprise companies that implemented Docker saw a 126% return on investment (ROI) over three years? In today’s rapidly evolving business landscape, companies face relentless pressure to innovate while managing costs and complexity. Traditional software development methods often struggle to keep pace with technological advancements, leading to inconsistent environments, high operational costs, and slow deployment cycles. That’s where containerization comes in as a smart solution.
Rising technology costs are a concern
Businesses today are navigating a complex environment filled with evolving market demands and economic pressures. A recent survey revealed that 70% of executives expect economic conditions to worsen, driving concerns about inflation and cash flow. Another survey found that 50% of businesses have raised prices to combat rising costs, reflecting broader financial pressures. In this context, traditional software deployment methods often fall short, resulting in rigid, inconsistent environments that impede agility and delay feature releases.
As cloud services costs surge, expected to surpass $1 trillion in 2024, businesses face heightened financial and operational challenges. Outdated deployment methods struggle with modern applications’ complexity, leading to persistent issues and inefficiencies. This underscores the need for a more agile, cost-effective solution.
As the adoption of cloud and hybrid cloud environments accelerates, businesses need solutions that ensure seamless integration and portability across their entire IT ecosystem. Containers provide a key to achieving this, offering unmatched agility, scalability, and security. By embracing containers, organizations can create more adaptable, resilient, and future-proof software solutions.
The solution is a container-first approach
Containerization simplifies the development and deployment of applications by encapsulating them into self-contained units known as containers. Each container includes everything an application needs to run — its code, libraries, and dependencies — ensuring consistent performance across different environments, from development to production.
Similar to how shipping containers transformed the packaging and transport industry, containerization revolutionized development. Using containers, development teams can reduce errors, optimize resources, accelerate time to market, and more.
Key benefits of containerization
Improved consistency: Containers guarantee that applications perform identically regardless of where they are deployed, eliminating the notorious “it works on my machine” problem.
Cost efficiency: Containers reduce infrastructure costs by optimizing resource utilization. Unlike traditional virtual machines that require separate operating systems, containers share the same operating system (OS) kernel, leading to significant savings and better scalability.
Faster time to market: Containers accelerate development and deployment cycles, allowing businesses to bring products and updates to market more quickly.
Enhanced security: Containers provide isolation between applications, which helps manage vulnerabilities and prevent breaches from spreading, thereby enhancing overall security.
Seeing a true impact
A Forrester Consulting study found that enterprises using Docker experienced a three-month faster time to market for revenue-generating applications, along with notable gains in efficiency and speed. These organizations reduced their data center footprint, enhanced application delivery speeds, and saved on infrastructure costs, showcasing containerization’s tangible benefits.
For instance, Cloudflare, a company operating one of the world’s largest cloud networks, needed to address the complexities of managing a growing infrastructure and supporting over 1,000 developers. By adopting Docker’s containerization technology and leveraging innovations like manifest lists, Cloudflare successfully streamlined its development and deployment processes. Docker’s support for multi-architecture images and continuous improvements, such as IPv6 networking capabilities, allowed Cloudflare to manage complex application stacks more efficiently, ensuring consistency across diverse environments and enhancing overall agility.
Stepping into a brighter future
Containerization offers a powerful solution to modern business challenges, providing consistency, cost savings, and enhanced security. As companies face increasing complexity and market pressures, adopting a container-first approach can streamline development, improve operational efficiency, and maintain a competitive edge.
Are you navigating the ever-evolving world of developer tools and container technology? The Docker Newsletter is your essential resource, curated for Docker users like you. Keep your finger on the pulse of the Docker ecosystem. Subscribe now!
If you’re anything like me, you love crafting sleek and responsive user interfaces with React. But, setting up consistent development environments and ensuring smooth deployments can also get complicated. That’s where Docker can help save the day.
As a Senior DevOps Engineer and Docker Captain, I’ve navigated the seas of containerization and witnessed firsthand how Docker can revolutionize your workflow. In this guide, I’ll share how you can dockerize a React app to streamline your development process, eliminate those pesky “it works on my machine” problems, and impress your colleagues with seamless deployments.
Let’s dive into the world of Docker and React!
Why containerize your React application?
You might be wondering, “Why should I bother containerizing my React app?” Great question! Containerization offers several compelling benefits that can elevate your development and deployment game, such as:
Streamlined CI/CD pipelines: By packaging your React app into a Docker container, you create a consistent environment from development to production. This consistency simplifies continuous integration and continuous deployment (CI/CD) pipelines, reducing the risk of environment-specific issues during builds and deployments.
Simplified dependency management: Docker encapsulates all your app’s dependencies within the container. This means you won’t have to deal with the infamous “works on my machine” dilemma anymore. Every team member and deployment environment uses the same setup, ensuring smooth collaboration.
Better resource management: Containers are lightweight and efficient. Unlike virtual machines, Docker containers share the host system’s kernel, which means you can run more containers on the same hardware. This efficiency is crucial when scaling applications or managing resources in a production environment.
Isolated environment without conflict: Docker provides isolated environments for your applications. This isolation prevents conflicts between different projects’ dependencies or configurations on the same machine. You can run multiple applications, each with its own set of dependencies, without them stepping on each other’s toes.
Getting started with React and Docker
Before we go further, let’s make sure you have everything you need to start containerizing your React app.
React app: Use an existing project or create a new one using create-react-app.
A quick introduction to Docker
Docker offers a comprehensive suite of enterprise-ready tools, cloud services, trusted content, and a collaborative community that helps streamline workflows and maximize development efficiency. The Docker productivity platform allows developers to package applications into containers — standardized units that include everything the software needs to run. Containers ensure that your application runs the same, regardless of where it’s deployed.
How to dockerize your React project
Now let’s get down to business. We’ll go through the process step by step and, by the end, you’ll have your React app running inside a Docker container.
Step 1: Set up the React app
If you already have a React app, you can skip this step. If not, let’s create one:
npx create-react-app my-react-app
cd my-react-app
This command initializes a new React application in a directory called my-react-app.
Step 2: Create a Dockerfile
In the root directory of your project, create a file named Dockerfile (no extension). This file will contain instructions for building your Docker image.
Dockerfile for development
For development purposes, you can create a simple Dockerfile:
# Use the latest LTS version of Node.js
FROM node:18-alpine
# Set the working directory inside the container
WORKDIR /app
# Copy package.json and package-lock.json
COPY package*.json ./
# Install dependencies
RUN npm install
# Copy the rest of your application files
COPY . .
# Expose the port your app runs on
EXPOSE 3000
# Define the command to run your app
CMD ["npm", "start"]
What’s happening here?
FROM node:18-alpine: We’re using the latest LTS version of Node.js based on Alpine Linux.
WORKDIR /app: Sets the working directory inside the container.
*COPY package.json ./**: Copies package.json and package-lock.json to the working directory.
RUN npm install: Installs the dependencies specified in package.json.
COPY . .: Copies all the files from your local directory into the container.
EXPOSE 3000: Exposes port 3000 on the container (React’s default port).
CMD ["npm", "start"]: Tells Docker to run npm start when the container launches.
Production Dockerfile with multi-stage build
For a production-ready image, we’ll use a multi-stage build to optimize the image size and enhance security.
# Build Stage
FROM node:18-alpine AS build
WORKDIR /app
COPY package*.json ./
RUN npm install
COPY . .
RUN npm run build
# Production Stage
FROM nginx:stable-alpine AS production
COPY --from=build /app/build /usr/share/nginx/html
EXPOSE 80
CMD ["nginx", "-g", "daemon off;"]
Explanation
Build stage:
FROM node:18-alpine AS build: Uses Node.js 18 for building the app.
RUN npm run build: Builds the optimized production files.
Production stage:
FROM nginx: Uses Nginx to serve static files.
COPY --from=build /app/build /usr/share/nginx/html: Copies the build output from the previous stage.
EXPOSE 80: Exposes port 80.
CMD ["nginx", "-g", "daemon off;"]: Runs Nginx in the foreground.
Benefits
Smaller image size: The final image contains only the production build and Nginx.
Enhanced security: Excludes development dependencies and Node.js runtime from the production image.
Just like .gitignore helps Git ignore certain files, .dockerignore tells Docker which files or directories to exclude when building the image. Create a .dockerignore file in your project’s root directory:
Excluding unnecessary files reduces the image size and speeds up the build process.
Step 4: Build and run your dockerized React app
Navigate to your project’s root directory and run:
docker build -t my-react-app .
This command tags the image with the name my-react-app and specifies the build context (current directory). By default, this will build the final production stage from your multi-stage Dockerfile, resulting in a smaller, optimized image.
If you have multiple stages in your Dockerfile and need to target a specific build stage (such as the build stage), you can use the --target option. For example:
docker build -t my-react-app-dev --target build .
Note: Building with --target build creates a larger image because it includes the build tools and dependencies needed to compile your React app. The production image (built using –target production) on the other hand, is much smaller because it only contains the final build files.
Running the Docker container
For the development image:
docker run -p 3000:3000 my-react-app-dev
For the production image:
docker run -p 80:80 my-react-app
Accessing your application
Next, open your browser and go to:
http://localhost:3000 (for development)
http://localhost (for production)
You should see your React app running inside a Docker container.
Step 5: Use Docker Compose for multi-container setups
Here’s an example of how a React frontend app can be configured as a service using Docker Compose.
Security note: Ensure your .env file is added to .gitignore and .dockerignore to prevent it from being committed to version control or included in your Docker image.
To start all services defined in a compose.yml in detached mode, the command is:
docker compose up -d
Passing environment variables at runtime
Alternatively, you can pass variables when running the container:
docker run -p 3000:3000 -e REACT_APP_API_URL=https://api.example.com my-react-app-dev
Using Docker Secrets (advanced)
For sensitive data in a production environment, consider using Docker Secrets to manage confidential information securely.
Production Dockerfile with multi-stage builds
When preparing your React app for production, multi-stage builds keep things lean and focused. They let you separate the build process from the final runtime environment, so you only ship what you need to serve your app. This not only reduces image size but also helps prevent unnecessary packages or development dependencies from sneaking into production.
The following is an example that goes one step further: We’ll create a dedicated build stage, a development environment stage, and a production stage. This approach ensures you can develop comfortably while still ending up with a streamlined, production-ready image.
# Stage 1: Build the React app
FROM node:18-alpine AS build
WORKDIR /app
# Leverage caching by installing dependencies first
COPY package.json package-lock.json ./
RUN npm install --frozen-lockfile
# Copy the rest of the application code and build for production
COPY . ./
RUN npm run build
# Stage 2: Development environment
FROM node:18-alpine AS development
WORKDIR /app
# Install dependencies again for development
COPY package.json package-lock.json ./
RUN npm install --frozen-lockfile
# Copy the full source code
COPY . ./
# Expose port for the development server
EXPOSE 3000
CMD ["npm", "start"]
# Stage 3: Production environment
FROM nginx:alpine AS production
# Copy the production build artifacts from the build stage
COPY --from=build /app/build /usr/share/nginx/html
# Expose the default NGINX port
EXPOSE 80
CMD ["nginx", "-g", "daemon off;"]
What’s happening here?
build stage: The first stage uses the official Node.js image to install dependencies, run the build, and produce an optimized, production-ready React build. By copying only your package.json and package-lock.json before running npm install, you leverage Docker’s layer caching, which speeds up rebuilds when your code changes but your dependencies don’t.
development stage: Need a local environment with hot-reloading for rapid iteration? This second stage sets up exactly that. It installs dependencies again (using the same caching trick) and starts the development server on port 3000, giving you the familiar npm start experience inside Docker.
production stage: Finally, the production stage uses a lightweight NGINX image to serve your static build artifacts. This stripped-down image doesn’t include Node.js or unnecessary development tools — just your optimized app and a robust web server. It keeps things clean, secure, and efficient.
This structured approach makes it a breeze to switch between development and production environments. You get fast feedback loops while coding, plus a slim, optimized final image ready for deployment. It’s a best-of-both-worlds solution that will streamline your React development workflow.
Troubleshooting common issues with Docker and React
Even with the best instructions, issues can arise. Here are common problems and how to fix them.
Issue: “Port 3000 is already in use”
Solution: Either stop the service using port 3000 or map your app to a different port when running the container.
docker run -p 4000:3000 my-react-app
Access your app at http://localhost:4000.
Issue: Changes aren’t reflected during development
Solution: Use Docker volumes to enable hot-reloading. In your compose.yml, ensure you have the following under volumes:
This setup allows your local changes to be mirrored inside the container.
Issue: Slow build times
Solution: Optimize your Dockerfile to leverage caching. Copy only package.json and package-lock.json before running npm install. This way, Docker caches the layer unless these files change.
COPY package*.json ./
RUN npm install
COPY . .
Issue: Container exits immediately
Cause: The React development server may not keep the container running by default.
Solution: Ensure you’re running the container interactively:
docker run -it -p 3000:3000 my-react-app
Issue: File permission errors
Solution: Adjust file permissions or specify a user in the Dockerfile using the USER directive.
# Add before CMD
USER node
Issue: Performance problems on macOS and Windows
File-sharing mechanisms between the host system and Docker containers introduce significant overhead on macOS and Windows, especially when working with large repositories or projects containing many files. Traditional methods like osxfs and gRPC FUSE often struggle to scale efficiently in these environments.
Solutions:
Enable synchronized file shares (Docker Desktop 4.27+): Docker Desktop 4.27+ introduces synchronized file shares, which significantly enhance bind mount performance by creating a high-performance, bidirectional cache of host files within the Docker Desktop VM.
Key benefits:
Optimized for large projects: Handles monorepos or repositories with thousands of files efficiently.
Performance improvement: Resolves bottlenecks seen with older file-sharing mechanisms.
Real-time synchronization: Automatically syncs filesystem changes between the host and container in near real-time.
Reduced file ownership conflicts: Minimizes issues with file permissions between host and container.
How to enable:
Open Docker Desktop and go to Settings > Resources > File Sharing.
In the Synchronized File Shares section, select the folder to share and click Initialize File Share.
Use bind mounts in your compose.yml or Docker CLI commands that point to the shared directory.
Optimize with .syncignore: Create a .syncignore file in the root of your shared directory to exclude unnecessary files (e.g., node_modules, .git/) for better performance.
Leverage WSL 2 on Windows: For Windows users, Docker’s WSL 2 backend offers near-native Linux performance by running the Docker engine in a lightweight Linux VM.
How to enable WSL 2 backend:
Ensure Windows 10 version 2004 or higher is installed.
Install the Windows Subsystem for Linux 2.
In Docker Desktop, go to Settings > General and enable Use the WSL 2 based engine.
Use updated caching options in volume mounts: Although legacy options like :cached and :delegated are deprecated, consistency modes still allow optimization:
consistent: Strict consistency (default).
cached: Allows the host to cache contents.
delegated: Allows the container to cache contents.
Let’s enhance our setup with some advanced techniques.
Reducing image size
Every megabyte counts, especially when deploying to cloud environments.
Use smaller base images: Alpine-based images are significantly smaller.
Clean up after installing dependencies:
RUN npm install && npm cache clean --force
Avoid copying unnecessary files: Use .dockerignore effectively.
Leveraging Docker build cache
Ensure that you’re not invalidating the cache unnecessarily. Only copy files that are required for each build step.
Using Docker layers wisely
Each command in your Dockerfile creates a new layer. Combine commands where appropriate to reduce the number of layers.
RUN npm install && npm cache clean --force
Conclusion
Dockerizing your React app is a game-changer. It brings consistency, efficiency, and scalability to your development workflow. By containerizing your application, you eliminate environment discrepancies, streamline deployments, and make collaboration a breeze.
So, the next time you’re setting up a React project, give Docker a shot. It will make your life as a developer significantly easier. Welcome to the world of containerization!
Login
