Qloo Agentic Hackathon

Overview

The Qloo Agentic Hackathon, hosted by Qloo, focuses on enhancing agentic tools with cultural intelligence. The event aims to address the current limitation of AI agents, which can reason and plan but often lack an understanding of human taste and preferences. Participants are tasked with integrating Qloo's API and extensive taste graph, which includes over 250 million entities across various cultural domains like music, film, dining, and fashion, into their projects. This integration is intended to provide agents with a real cultural grounding, moving beyond generic recommendations to truly understand what people love. The hackathon encourages the development of solutions where cultural intelligence is the primary differentiator. Submissions should demonstrate how Qloo's API and taste graph enable an agent to outperform generic LLM-only approaches by providing reliable insights into human preferences. The challenge is not merely to showcase existing LLM capabilities but to build applications that function uniquely and effectively because they leverage Qloo's cultural data. Participants can develop agentic tools, agent-powered applications, or integrate Qloo into pre-existing agent frameworks. The goal is to create use cases where access to cultural data transforms a "technically functional" solution into one that is "actually good" and deeply relevant to user tastes. Examples include agents that help customers choose lighting styles based on mood and personal taste, recommend age-specific dining options with health considerations, or support individuals with rare diseases by finding tailored information and community resources. The hackathon offers a total of $25,000 in cash prizes across three places, with $15,000 for first, $6,000 for second, and $4,000 for third. The deadline for submissions is October 30, 2026, at 11:45 PM EDT. Projects will be judged on technological implementation, design, potential impact, and the quality of the idea, specifically emphasizing creative and non-obvious uses of Qloo.

What to build

Build a working software application that integrates the Qloo API. The application must function as an agentic tool, be built using an agent framework, or wire Qloo into an existing agent. The core purpose is to use Qloo to ground recommendations in real cultural taste across domains like music, film/TV, dining, fashion, and travel. The project should demonstrate that cultural intelligence is the differentiator, enabling the agent to outperform generic LLM-only approaches due to access to Qloo's API and taste graph (250M+ entities). If the submission would work the same without Qloo, it is not meeting the core requirement. Examples provided include an agent assisting electricians' customers with lighting style choices based on mood and personal taste, an agent recommending age-specific meals and dining options for seniors that consider taste and health constraints, and an agent supporting people in rare-disease journeys by finding tailored information and community resources based on emotional and practical needs.

Prizes

Key dates

• Deadline2026-10-30T23:45:00-04:00

Eligibility

Participants must be above the legal age of majority in their country of residence. All countries/territories are eligible, excluding standard exceptions.

Submission requirements

• A link to a functional demo application: A live, working app that participants can try end-to-end, demonstrating the core features of the project.
• A URL to a public code repository (GitHub, GitLab, or Bitbucket): The repository must be public and contain all source code, assets, and instructions necessary for the project to run.
• A text description of what your project does: Explain the key features, functionality, what the agent or workflow can do, and what makes it "Qloo-powered."
• External hosting / fully published requirement: The demo must be hosted and fully published externally, such as a live website, web app, or a hosted APK/TestFlight build. Submissions that only run locally or rely on private access will not qualify.
• An open-source license: The license file must be visible in the 'About' section of your repository.

Judging criteria

• Technological Implementation: How thoroughly and skillfully does the project use Qloo? Does the code reflect genuine effort and a working, non-trivial implementation?
• Design: Does the project deliver a complete, coherent product experience, not just a technical proof of concept?
• Potential Impact: Does the project make a credible, specific case for solving a real problem for a real audience, and does the solution actually address that problem based on what's demonstrated?
• Quality of the Idea: Is this a creative, non-obvious use of Qloo, and does the team demonstrate genuine understanding of the problem space they're working in?

Sponsors & partners

Resources

• Qloo LLM Hackathon Developer Guide - Getting your API key