Watch our webinar to learn more about the hackathon, rules, ADK, and tips & tricks. 

TOOLS AND TECHNOLOGIES

 

Agent Development Kit

  • ADK docs use the quickstart, checkout tools (function, built-in, GCP, MCP, OpenAPI, etc), use adk web locally and deploy.
  • ADK sample agents reference our agents or edit and use these as part of your multi-agent system.
  • ADK videos watch intros and deep dive videos to understand your options.
  • ADK github review the repo for more details and contribute with a PR.


A more DevOps Approach to ADK

 

Other resources 

Join the Devpost Discord server channels dedicated to this challenge

 

FAQs

How can I get Google Cloud credits for the hackathon? 

 

You can obtain access to Google Cloud developer tools by signing up for a no-cost trial at cloud.google.com/free or by using an existing Google Cloud account and requesting $100 in Google Cloud credits by completing a specific form. Be aware that you are responsible for fees if your usage exceeds the credit amount.

 

Which tools and technologies are required for my project? 

Your project must be built using the Agent Development Kit (ADK) (Python or Java version) to build a multi-agent system. 

 

Where can I find resources and support during the hackathon? 

Comprehensive resources can be found on the Resources tab here. You can also register and watch the webinar hosted by Google Cloud experts. Join the Devpost Discord server channels dedicated to this challenge. 

 

Which tools and technologies are required for my project? 

Your project must be built using the Agent Development Kit (ADK) to build a multi-agent system. 

 

What other technologies and tools can I use? 

While ADK is foundational, you are allowed and encouraged to integrate with other relevant technologies within the Google Cloud ecosystem. We will reward bonus points for the use of Google Cloud technology and AI models, like Gemini, Imagen, and Veo. You can explore and integrate other foundation models available on Google Cloud, such as Anthropic models via the Vertex AI Model Garden. You can also define and use custom tools like Python functions or API calls, and you can port over systems built using Langchain or CrewAI to ADK.

 

How many bonus points can I get?

There are three ways to earn bonus points:

  1. Publishing content (blog post, video, or podcast) covering how the project was built using Agent Development Kit. This content can be published on any public platform such as YouTube, medium.com, substack.com, dev.to, and others. When publishing, participants must include language stating that the content was created for the purposes of entering this hackathon. For any social media posts, the hashtag #adkhackathon should be included. A maximum of 0.4 points can be provided in this category.
  2. Making a contribution to the Agent Development Kit open-source repository. Participants should show their contributions (commits, pull requests, issues opened, and code reviews) by linking to their GitHub profile or the repository's contribution history. A maximum of 0.4 points can be provided in this category.
  3. Using Google Cloud technology (including but not limited to Agent Engine, Cloud Run, and BigQuery) or Google AI models (including but not limited to Gemini, Gemma, Veo). A maximum of 0.2 points can be provided in this category.

Each contribution made towards the first two categories (publishing content and making a contribution to ADK) are worth double the last category (use of Google Cloud technology and models). 

These optional contributions are evaluated in Stage Three of the judging process. If the submission includes complete and requested optional developer contributions, points are added to the Stage Two Score.