Leveraging the Google Agent Development Kit (ADK) and the underlying Gemini LLM to build a multi Agent deployment in the Python programming language deployed securely to Google Cloud Run.
Python Version Management
One of the downsides of the wide deployment of Python has been managing the language versions across platforms and maintaining a supported version.
The pyenv tool enables deploying consistent versions of Python:
GitHub - pyenv/pyenv: Simple Python version management
As of writing — the mainstream python version is 3.13. To validate your current Python:
xbill@penguin:~$ python --version
Python 3.13.12
xbill@penguin:~$ pyenv version
3.13.12 (set by /home/xbill/.pyenv/version)
Gemini CLI
If not pre-installed you can download the Gemini CLI to interact with the source files and provide real-time assistance:
npm install -g @google/gemini-cli
Testing the Gemini CLI Environment
Once you have all the tools and the correct Node.js version in place- you can test the startup of Gemini CLI. You will need to authenticate with a Key or your Google Account:
gemini
Node Version Management
Gemini CLI needs a consistent, up to date version of Node. The nvm command can be used to get a standard Node environment:
Agent Development Kit
The Google Agent Development Kit (ADK) is an open-source, Python-based framework designed to streamline the creation, deployment, and orchestration of sophisticated, multi-agent AI systems. It treats agent development like software engineering, offering modularity, state management, and built-in tools (like Google Search) to build autonomous agents.
The ADK can be installed from here:
Where do I start?
The strategy for starting low code agent development is a incremental step by step approach.
The agents in the demo are based on the original code lab:
First, the basic development environment is setup with the required system variables, and a working Gemini CLI configuration.
Then, a minimal ADK Agent is built with the visual builder. Next — the entire solution is deployed to Google Cloud Run.
Setup the Basic Environment
At this point you should have a working Python environment and a working Gemini CLI installation. The next step is to clone the GitHub samples repository with support scripts:
cd ~
git clone https://github.com/xbill9/adkui
Then run init.sh from the cloned directory.
The script will attempt to determine your shell environment and set the correct variables:
source init.sh
pip install -r requirements.txt
If your session times out or you need to re-authenticate- you can run the set_env.sh script to reset your environment variables:
source set_env.sh
Variables like PROJECT_ID need to be setup for use in the various build scripts- so the set_env script can be used to reset the environment if you time-out.
Running the Agent Code
First- start the ADK interface:
xbill@penguin:~/adkui$ adk web
2026-02-21 14:31:53,810 - INFO - service_factory.py:266 - Using in-memory memory service
2026-02-21 14:31:53,811 - INFO - local_storage.py:84 - Using per-agent session storage rooted at /home/xbill/adkui
2026-02-21 14:31:53,811 - INFO - local_storage.py:110 - Using file artifact service at /home/xbill/adkui/.adk/artifacts
INFO: Started server process [25329]
INFO: Waiting for application startup.
+-----------------------------------------------------------------------------+
| ADK Web Server started |
| |
| For local testing, access at http://127.0.0.1:8000. |
+-----------------------------------------------------------------------------+
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8000 (Press CTRL+C to quit)
Running the Tool Locally
Connect to the local web interface:
Then drill into the second Agent — Agent2:
This Agent uses the IMAGEN model to create an artifcact in the current ADK environment.
Deploying to Cloud Run
After the HTTP version of the Agent has been tested locally — it can be deployed remotely to Google Cloud Run.
First- switch to the directory:
xbill@penguin:~/adkui$ make deploy
When the build is complete- an endpoint will be returned. The service endpoint in this example is :
https://adk-1056842563084.us-central1.run.app
The actual endpoint will vary based on your project settings.
Review Service in Cloud Run
Navigate to the Google Cloud console and search for Cloud Run -
Validate Cloud Run Deployment
Once you have the Endpoint — you can attempt a connection- navigate to in your browser. To test image generation — use Agent2:
Once image generation and the ADK UI is working — dig deeper. Select the sub-agent “Agent3”:
This will generate the Comic by using a multi-agent pipeline:
Once the multi Agent system is complete:
Visual Edit Agent Pipeline
The version of the ADK Deployed includes a visual builder:
Run the Online Viewer Agent
Once Agent3 has completed — go to the ADK agent selector and select “Agent4”. This agent will allow you to browse your online comic:
View the Final Artifacts
You can use Agent4 to visualize the results of the agent pipeline:
and the assembled panels:
Summary
The Agent Development Kit was used to visually define a multi Agent pipeline to generate comic book style HTML. This Agent was tested locally with the CLI and then with the ADK web tool. Then, several sample ADK agents were run directly from the Cloud Run deployment in Google Cloud.
Top comments (0)