1 basic n8n setupmax 1000x1000 1
n8n is a powerful yet easy-to-use workflow and automation tool for multi-step AI agents, and many teams want a simple, scalable, and cost-effective way to self-host it. With just a few commands, you can deploy n8n to Cloud Run and have it up and running, ready to supercharge your business with AI workflows that can manage spreadsheets, read and draft emails, and more. The n8n docs now tell you how to deploy the official n8n Docker image to our serverless platform, connect it to Cloud SQL for persistent data storage, call Gemini as the agents’ LLM, and (optionally) connect your workflows directly to Google Workspace.
You can deploy the official n8n image directly to Cloud Run. This gives you a managed, serverless environment that automatically scales from zero to handle any workload, so you only pay for what you use. That means whenever you’re not actively using n8n, you’re not paying for any compute and your n8n data is persisted in Cloud SQL.
To first try out n8n quickly on Cloud Run, deploy it with this one command:
This gives you a running instance of n8n that you can use to try out n8n and all its awesome features for workflow automation with the power of AI. Connect your first n8n agent to Gemini (provide your Gemini API key for the “Google Gemini Chat Model” credentials) and see it in action.
Then when you’re ready to use n8n for actual workflows, you can follow the steps in the n8n docs for a more durable, secure setup (using Cloud SQL, Secrets Manager, etc.). You can either use a Terraform script or follow along step-by-step through each gcloud command in the instructions.
A key benefit of hosting on Google Cloud is the ability to easily connect n8n to your Google Workspace tools. The n8n docs walk you through the steps to configure OAuth for Google Cloud, allowing your n8n workflows to securely access and automate tasks using Google tools like Gmail, Google Calendar, and Google Drive.
Here’s a demo showing an n8n instance on Cloud Run that uses Gmail and Google Calendar to schedule appointments on your behalf whenever an email hits your inbox with a request to meet:
The two AI agents in this n8n workflow call Gemini to do the following:
The Text Classifier reads your incoming emails to see which ones are asking for time to meet
The Agent checks your calendar for your availability, and sends a response with a suggested time
Cloud Run is a versatile, easy-to-use runtime for all your AI application needs. Whether your agentic app was made with n8n, LangChain, ADK, or no framework at all, you can deploy it to Cloud Run. This collaboration on Cloud Run and n8n is another example of how we aim to simplify the process for developers to build and deploy intelligent applications.
Read more about Cloud Run (or just try it out in the web console!)
Explore n8n
Embeddings — vector-based numerical representations of typically unstructured data like text — have been primarily…
Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. However, they…
This post is co-written with Sunaina Kavi, AI/ML Product Manager at Omada Health. Omada Health,…
Anthropic released Cowork on Monday, a new AI agent capability that extends the power of…
New York governor Kathy Hochul says she will propose a new law allowing limited autonomous…
Artificial intelligence (AI) is increasingly used to analyze medical images, materials data and scientific measurements,…