12 posts tagged with "Defang Compose Update"

April flew by with big momentum at Defang. From deeper investments in the Model Context Protocol (MCP), to deploying LLM-based inferencing apps, to live demos of Vibe Deploying, we're making it easier than ever to go from idea to cloud.

MCP + Vibe Deploying​

This month we focused on making cloud deployments as easy as writing a prompt. Our latest Vibe Deploying blog shows how you can launch full-stack apps right from your IDE just by chatting.

Whether you're working in Cursor, Windsurf, VS Code, or Claude, Defang's MCP integration lets you deploy to the cloud just as easily as conversing with the AI to generate your app. For more details, check out the docs for the Defang Model Context Protocol Server – it explains how it works, how to use it, and why it's a game changer for deploying to the cloud. You can also watch our tutorials for Cursor, Windsurf, and VS Code.

Managed LLMs​

Last month we shipped the x-defang-llm compose service extension to easily deploy inferencing apps that use managed LLM services such as AWS Bedrock. This month, we're excited to announce the same support for GCP Vertex AI – give it a try and let us know your feedback!

Events and Programs​

On April 28, we kicked things off with an epic night of demos, dev energy, and cloud magic at RAG & AI in Action. Our own Kevin Vo showed how fast and easy it is to deploy AI apps from Windsurf to the cloud using just the Defang MCP. The crowd got a front-row look at how Vibe Deploying turns cloud infra into a background detail.

We finished the month with our signature Defang Coffee Chat, a casual hangout with product updates, live Q&A, and great conversations with our community. Our Campus Advocates also hosted workshops around the world, bringing Defang to new students and builders.

We wrapped up the month with our latest Defang Coffee Chat, featuring live demos, product updates, and a solid conversation around vibe deploying. Thanks to everyone who joined.

The next one is on May 21 at 10 AM PST. Save your spot here.

Looking Ahead​

Here's what's coming in May:

• Web Summit Vancouver – Defang will be a startup sponsor, please come see us on the expo floor.
• More MCP tutorials and dev tools

Let's keep building. 🚀

Hey folks! There is a lot going on at Defang and we're excited to share our latest product updates with you. Over the last month, we've been working hard to improve the Defang system and make it even easier for you to deploy your applications. Here's a quick overview of what we've been up to:

npx defang​

We know a lot of you are using Defang for the first time. To make it easier to get started, we've added a new way to install the Defang CLI. Now you can use npx to run the CLI without installing it globally by running:

npx defang@latest

This will download the latest version of the Defang CLI and run it for you. No need to worry about installing or updating the CLI manually!

(coming soon) Bring Your Own Domain with Let's Encrypt​

Previously you could bring your own domain with Defang BYOC... but you had to host the DNS records with AWS Route 53 in the AWS account you were deploying to. Now you can point domains hosted anywhere to your Defang deployment and we'll take care of the rest. We'll help generate a Let's Encrypt certificate for your domain and automatically renew it for you.

Windows Support​

Some of you use Defang from a Windows PC and previously a few features didn't work correctly on Windows. Some stuff we've fixed:

• ansi color codes in logs
• handle ctrl-c when tailing logs

Improved CLI​

We've made a variety of small tweaks and improvements to the CLI which should make things a little bit cleaner and more stable.

• log messages have been made more clear
• adding more progress information during compose up

Stability and Reliability​

Defang is still in Beta and we know we've got to be rock solid by the time we release V1, so we've been working hard to improve the stability and reliability of the Defang architecture. We've been battle-testing different technologies to see how they hold up and have mad a few changes that should make things even better:

• capacity improvements in build queues
• improvements in log availability