You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
## From Vibe-Coding to Production… Without a DevOps Team
12
+
13
+
Building apps has never been easier. Tools like Cursor, Windsurf, Lovable, V0, and Bolt have ushered in a new era of coding called **vibe coding**, rapid, AI-assisted app development where developers can go from idea to prototype in hours, bringing ideas to life faster than ever before.
14
+
15
+
And with the recently released AWS Kiro, we have now entered a new phase of AI-assisted development called "spec-driven development" where the AI breaks down the app development task even further. You can think of a "PM agent" that goes from prompt to a requirements document, and then an "Architect agent" that goes from the requirements document to a design document, which is then used by "Dev", "Test" and "Docs" agents to generate app code, tests, and documentation respectively. This approach is much more aligned with enterprise use cases and produces higher quality output.
16
+
17
+
## The Hard Part Isn’t Building. It’s Shipping.
18
+
19
+
However, cloud app deployment remains a major challenge! As Andrej Karpathy shared during his [recent YC talk](https://www.youtube.com/watch?v=LCEmiRjPEtQ):
20
+
21
+
> "_I vibe-coded the app in four hours… and spent the rest of the week deploying it._"
22
+
23
+
While AI-powered tools make building apps a breeze, deploying them to the cloud is still frustratingly complex. Kubernetes, Terraform, IAM policies, load balancers, DNS, CI/CD all add layers of difficulty. This complexity continues to be a significant bottleneck that AI tools have yet to fully address, making deployment a critical challenge for developers.
24
+
25
+
The bottleneck is no longer the code. It's the infrastructure.
26
+
27
+
## Enter Defang: Your AI DevOps Agent
28
+
29
+
**Defang** is an AI-enabled agent that takes care of your entire deployment workflow, going from app code to a production-ready deployment on your favorite cloud in a single step.
30
+
31
+
By understanding your app stack (using Docker Compose), **Defang** provisions the right infrastructure and securely deploys to AWS, GCP, or DigitalOcean, following each cloud's best practices.
32
+
33
+
Whether you're launching a side project or scaling a multi-agent app, **Defang** ensures secure, smooth, scalable cloud-native deployments.
34
+
35
+
## Defang Deployment Features at a Glance
36
+
37
+
-**One Command Deployment:** Run `defang compose up` and you're live
38
+
-**Secure and Scalable:** Built-in TLS, secrets, autoscaling, IAM, and HTTPS
39
+
-**Multi-Cloud Ready:** Deploy to your cloud (AWS, GCP, DO) using your own credentials
-**Managed LLM:** Add `x-defang-llm: true` and **Defang** auto-configures cloud-native LLMs like Bedrock, Vertex AI, and the Defang Playground
42
+
-**Configures managed services** (e.g. managed Postgres, MongoDB, Redis) using the target cloud's native services (e.g. RDS for Postgres on AWS, Cloud SQL on GCP).
43
+
-**Tailored deployment modes** (e.g. affordable, balance, high-availability) optimized for different environments (dev, staging, production)
44
+
-**AI Debugging:** Get context-aware assistance to quickly identify and fix deployment issues
45
+
46
+
## Native Integration with AI-Assisted Coding Tools
47
+
48
+
**Defang** can be accessed directly from within your favorite IDE - Cursor, Windsurf, VS Code, Claude, or Kiro - via [Defang's MCP Server](https://docs.defang.io/docs/concepts/mcp). You can now deploy to the cloud with a natural language command like "deploy my app with Defang".
49
+
50
+
## For Developers and CTOs Who Want to Move Fast
51
+
52
+
If you're a developer shipping fast or a CTO scaling lean, **Defang** acts as your drop-in DevOps engineer without needing to build a team around it.
53
+
54
+
You focus on building great software.
55
+
**Defang** gets it live.
56
+
57
+
## Try Defang Now
58
+
59
+
- Deploy your full-stack app with a single command
60
+
- Explore [samples and templates](https://docs.defang.io/docs/samples)
July was all about making cloud deployments even smoother and smarter. We focused on removing friction from deployments and giving you better visibility into costs. Railpack now builds production-ready images automatically when no Dockerfile is present, and our real-time cost estimation feature now supports Google Cloud alongside AWS. We also added managed MongoDB on GCP, introduced an Agentic LangGraph sample, and connected with builders at Bière & Code & Beer MTL. Here’s what’s new.
24
+
25
+
## Railpack Integration
26
+
27
+
We’ve integrated [Railpack](https://docs.defang.io/docs/concepts/railpack) into Defang to make deployments even smoother. Railpack automatically builds OCI-compliant images from your source code with minimal configuration. This helps eliminate one of the most common issues our users face: missing or invalid Dockerfiles, especially when they’re generated by LLMs or created by users with limited Docker experience. Now, if no Dockerfile is provided, Defang will seamlessly use Railpack to build a working image for you, so you can focus on your code, not your container setup.
28
+
29
+
## GCP Cost Estimation
30
+
31
+
In June, Defang announced real-time cost estimation for AWS. In July, we took our [live cloud cost estimation](https://docs.defang.io/docs/concepts/estimation) to the next level by extending support to GCP. Defang now makes it easy to compare real-time pricing for both cloud providers. All you need is your project's compose.yaml file. Whether you’re optimizing for cost, performance, or flexibility, Defang makes it easy to get the information you need to deploy with confidence.
32
+
33
+
## Managed MongoDB on GCP
34
+
35
+
Defang now supports [managed MongoDB](https://docs.defang.io/docs/concepts/managed-storage/managed-mongodb) on GCP through MongoDB-compatible APIs provided by Google Cloud. This integration allows you to spin up a fully managed Firestore datastore and interact with it just like a standard MongoDB instance without any manual setup or configuration.
36
+
37
+
## Agentic LangGraph Sample
38
+
39
+
We have published a new [Agentic LangGraph sample](https://github.com/DefangSamples/sample-agentic-langgraph-template/tree/main) project that demonstrates LangGraph agent deployment with Defang. As AI agent development grows, Defang makes it simple to deploy and scale agents, including those built with LangChain or LangGraph. You can explore the example to see how it works in practice.
40
+
41
+
## Events and Community
42
+
43
+
In July, we hosted the [Bière & Code & Beer MTL](https://www.linkedin.com/feed/update/urn:li:activity:7350573195004952578) during Startupfest in Montreal. It was an incredible evening with great energy, tech conversations, and the chance to connect with so many talented builders over drinks.
44
+
45
+
We are excited to see what you will deploy with Defang next. Join our [Discord](https://s.defang.io/discord) to ask questions, get support, and share your builds with the community.
## Deploying Agentic Apps to the Cloud Shouldn’t Be This Hard…
13
+
14
+
Agentic apps are redefining how software is built: multi-agent workflows, persistent memory, tool-using LLMs, and orchestrated autonomy. But deploying them to the cloud is still painful - for example, your agentic app typically needs to provision:
15
+
16
+
- Managed databases like Postgres or MongoDB
17
+
- Fast, scalable caching (hello Redis)
18
+
- Containerized compute that scales
19
+
- Secure networking and service discovery
20
+
- Managed LLMs like AWS Bedrock or GCP Vertex AI
21
+
22
+
And for many teams, these apps must run inside the customer’s cloud, where sensitive data lives and compliance rules apply. That means you cannot just spin up your own environment and call it a day. Instead, you are deploying across AWS, GCP, DigitalOcean, or whichever stack your customers demand, each with its own APIs, quirks, and limitations.
23
+
24
+
Now you are not just building agents; you are picking the right infrastructure, rewriting IaC templates for every provider, and untangling the edge cases of each cloud.
25
+
26
+
The result: weeks of DevOps headaches, lost momentum, and engineers stuck wiring infrastructure instead of shipping agents.
27
+
28
+
## We Made it Simple with Cloud Native Support for Agentic Apps
29
+
30
+
That’s where Defang comes in. We make it easy to deploy full-stack agentic apps to your cloud of choice: native, secure, and scalable.
31
+
Defang understands the common ingredients of agentic apps and makes them first-class citizens:
32
+
33
+
- Compute: Your Dockerized services deploy as cloud-native workloads (e.g. AWS ECS, or GCP Cloud Run)
34
+
- Databases: Provision managed Postgres or MongoDB with one config line
35
+
- Caching: Add Redis and Defang spins up a managed Redis instance in your cloud
36
+
- LLMs: Integrate directly with Bedrock or Vertex AI - even provision an OpenAI gateway for compatibility with OpenAI APIs.
37
+
- Secure Defaults: : TLS, secrets, IAM, and service accounts handled out of the box
38
+
39
+
## Built for All your Favorite Agentic Frameworks
40
+
41
+
Defang works seamlessly with leading agentic frameworks. Try them out with our ready-to-deploy samples:
42
+
43
+
-[Autogen](https://github.com/DefangLabs/samples/tree/main/samples/agentic-autogen) - demo featuring Mistral AI + FastAPI, deployable with Defang’s OpenAI Access Gateway.
44
+
-[CrewAI](https://docs.defang.io/blog/2025/06/16/crew-ai-sample) - sample app showing multi-agent orchestration in action.
45
+
-[LangGraph](https://github.com/DefangLabs/samples/tree/main/samples/agentic-langgraph) - workflow sample that defines and controls multi-step agentic graphs with LangChain.
46
+
47
+
More framework templates coming soon.
48
+
49
+
## Why It Matters
50
+
51
+
Agentic apps need to be fast, secure, and ready to scale. Defang delivers cloud-native deployments in your environment (AWS, GCP, DO), so you can move from idea to production quickly with consistent behavior across dev, test, and prod.
52
+
53
+
## The Developer Journey, Simplified
54
+
55
+
1. Build your agentic app locally using Docker Compose
56
+
2. Test in Defang's free playground with `defang compose up`
57
+
3. Deploy to your cloud:
58
+
59
+
```bash
60
+
defang compose up --provider=aws # or gcp, do
61
+
```
62
+
63
+
It just works. No Terraform. No YAML explosion. No vendor lock-in.
64
+
65
+
## The Future of AI Apps Is Agentic and Cloud-Native
66
+
67
+
Agility and scalability should not be a trade-off. With Defang, you get both. Developers focus on agents, tools, and outcomes. Defang takes care of the cloud infrastructure.
68
+
69
+
## Try it out
70
+
71
+
Explore more samples at [docs.defang.io](https://docs.defang.io)
72
+
Join our community on [Discord](https://s.defang.io/discord)
Copy file name to clipboardExpand all lines: docs/concepts/authentication.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,7 +12,7 @@ To do pretty much anything with Defang, you'll need to authenticate with the sys
12
12
defang login
13
13
```
14
14
15
-
This will prompt you to open a browser and log in to your [Defang account](/docs/concepts/accounts). For now, the only way to log in is with GitHub, though we will offer other providers to authenticate in the future. Once you've logged in, you can close the browser and return to the terminal. You should see a message that you've successfully logged in.
15
+
This will prompt you to open a browser and log in to your [Defang account](/docs/concepts/accounts). You can log in using [GitHub](https://github.com/) or [GitLab](https://gitlab.com/). We will offer other authentication providers in the future. Once you've logged in, you can close the browser and return to the terminal. You will see a message that you've successfully logged in.
16
16
17
17
:::tip
18
18
Keep in mind that your Defang account is separate from your [cloud provider account](/docs/concepts/defang-byoc). You will need to authenticate with your cloud provider account separately to deploy services to your own cloud account.
Copy file name to clipboardExpand all lines: docs/concepts/mcp.md
+74-10Lines changed: 74 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -20,31 +20,39 @@ This page is a guide to the Defang MCP Server detailing its installation, tools,
20
20
21
21
## Installation
22
22
23
-
Ensure that you have the [npm package manager](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) installed, as `npx` commands are required for setup.
23
+
Ensure that you have the [Defang CLI](/docs/getting-started.mdx#install-the-defang-cli) installed.
24
24
25
-
:::warning
26
-
At this time, the Defang MCP Server can only be installed using `npx`. Other methods are not yet supported.
27
-
:::
28
25
Run the setup command in your terminal for your IDE of choice from the [Supported IDEs](#supported-ides) section. This will connect the Defang MCP Server to your IDE. The general format of the command is as follows:
29
26
27
+
:::tip[Recommended Installation]
28
+
Install the [Defang CLI](/docs/getting-started.mdx#install-the-defang-cli) using [Curl](https://curl.se/) or [Homebrew](https://brew.sh/)
Once the command completes, you may need to restart your IDE for the changes to take effect.
35
37
36
38
Once the MCP Server is running, you can access the Defang MCP tools directly through the AI agent chat in your IDE.
37
39
38
40
That's it! Feel free to explore our [Example Prompts](#example-prompts) to get ideas on how to interact with the AI agent and make the most of the Defang MCP Server.
39
41
42
+
Note that `npx` installation is supported, but not recommended.
Once setup is complete, you can interact with the AI coding agent using Defang-related actions like `check defang services` or [other prompts](#example-prompts). Here's an example of what it could look like:
@@ -56,7 +64,7 @@ Once setup is complete, you can interact with the AI coding agent using Defang-r
56
64
Setup command:
57
65
58
66
```bash
59
-
npx -y defang@latest mcp setup --client=windsurf
67
+
defang mcp setup --client=windsurf
60
68
```
61
69
62
70
Once setup is complete, you can interact with the AI coding agent using Defang-related actions like `check defang services` or [other prompts](#example-prompts). Here's an example of what it could look like:
@@ -68,7 +76,7 @@ Once setup is complete, you can interact with the AI coding agent using Defang-r
68
76
Setup command:
69
77
70
78
```bash
71
-
npx -y defang@latest mcp setup --client=vscode
79
+
defang mcp setup --client=vscode
72
80
```
73
81
74
82
Once setup is complete, you can interact with the AI coding agent using Defang-related actions like `check defang services` or [other prompts](#example-prompts). Here's an example of what it could look like:
@@ -80,21 +88,33 @@ Once setup is complete, you can interact with the AI coding agent using Defang-r
Once setup is complete, you can interact with the AI coding agent using Defang-related actions like `check defang services` or [other prompts](#example-prompts). Here's an example of what it could look like:
87
95
88
96
89
97
98
+
### Kiro
99
+
100
+
Setup command:
101
+
102
+
```bash
103
+
defang mcp setup --client=kiro
104
+
```
105
+
106
+
Once setup is complete, you can interact with the AI coding agent using Defang-related actions like `check defang services` or [other prompts](#example-prompts). Here's an example of what it could look like:
107
+
108
+
109
+
90
110
### Claude Desktop
91
111
92
112
While this is not an IDE in the traditional sense, it can support MCP servers. For a smoother experience, consider specifying a project name or directory when making chat prompts to this platform.
93
113
94
114
Setup command:
95
115
96
116
```bash
97
-
npx -y defang@latest mcp setup --client=claude
117
+
defang mcp setup --client=claude
98
118
```
99
119
100
120
Once setup is complete, you can interact with the AI coding agent using Defang-related actions like `check defang services` or [other prompts](#example-prompts). Here's an example of what it could look like:
@@ -121,6 +141,22 @@ The `services` tool displays the details of all your services that are currently
121
141
122
142
Given a project name or directory, the `destroy` tool identifies any services deployed with Defang and terminates them. If no services are found, it will display an appropriate message.
123
143
144
+
### `estimate`
145
+
146
+
The `estimate` tool scan your project directory and considers your [deployment mode](/docs/concepts/deployment-modes.md) (which defaults to `AFFORDABLE`) to provide a [cost estimation](/docs/concepts/estimation.md) for your project. Currently, the tool supports two providers: `AWS` or `GCP`.
147
+
148
+
### `list_configs`
149
+
150
+
The `list_configs` tool will [list](/docs/cli/defang_config) all the Defang configs set for your project.
151
+
152
+
### `set_config`
153
+
154
+
The `set_config` tool will [set](/docs/tutorials/configure-environment-variables#step-2---set-the-actual-value-in-the-defang-cli) a specific Defang config for your project.
155
+
156
+
### `remove_config`
157
+
158
+
The `remove_config` tool will [remove](/docs/tutorials/configure-environment-variables#removing-a-config-value) a specific Defang config for your project.
159
+
124
160
## Example Prompts
125
161
126
162
After connecting the Defang MCP Server to your IDE using an installation method, you can type in prompts in your chat to invoke the AI agent to use any MCP tool(s).
@@ -149,4 +185,32 @@ deploy this with defang /Users/yourname/Documents/project1
149
185
do I have a service called project1
150
186
```
151
187
188
+
You can estimate the cost of a deployment to a supported cloud provider:
189
+
190
+
```
191
+
can you estimate balance mode on aws for this project?
192
+
```
193
+
194
+
```
195
+
can you estimate how much this project will cost on gcp?
196
+
```
197
+
198
+
You can list, set and remove Defang configs for a project:
199
+
200
+
```
201
+
what defang configs do I have set for this project?
202
+
```
203
+
204
+
```
205
+
list all the defang configs I have set for this project
206
+
```
207
+
208
+
```
209
+
set the defang config DATABASE_URL to example.com
210
+
```
211
+
212
+
```
213
+
remove the defang config DATABASE_URL
214
+
```
215
+
152
216
Feel free to try any of these prompts or create your own!
0 commit comments