8000 GitHub - gamezsal/adk_wc26 · GitHub
[go: up one dir, main page]

Skip to content
gamezsalPublic

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

World Cup 2026 Ticket Acquisition Multi-Agent System (WC26 ADK Agents)

An autonomous multi-agent system built with the uAgents Framework designed to monitor sports standings and secondary ticket markets, executing strategic purchases when tournament upsets trigger panic-selling.

Architecture Overview

The system consists of three specialized agents operating in a cooperative environment (a Bureau):

graph TD
    FA[Fixtures Agent] -- Upset Alerts --> BA[Buyer Agent]
    MA[Market Agent] -- Ticket Price/Velocity Data --> BA
    BA -- Purchases Tickets --> External[Ticket Market API / Log]
    
    subgraph wc26_agents [Agent Bureau]
        FA
        MA
        BA
    end
Loading

1. 📋 Fixtures Agent (fixtures_fetching_agent)

  • API Source: API-Football
  • Interval: 5 minutes (300.0s)
  • Responsibility: Regularly polls the live tournament standings. If a favorite team (e.g., Argentina) drops in the rankings (an "upset"), it triggers an alert indicating that they will no longer play at their expected venue (e.g., MetLife Stadium).

2. 📊 Market Agent (market_ingestion_agent)

  • API Source: TicketsData SDK (StubHub, SeatGeek, TicketMaster)
  • Interval: 10 minutes (600.0s)
  • Responsibility: Scans ticket availability and prices for target matches. It computes listing velocity (the rate at which new tickets are being added or removed from the market) and sends real-time updates to the Buyer Agent.

3. 🛒 Buyer Agent (buyer_execution_agent)

  • Responsibility: Listens to messages from both the Fixtures Agent and Market Agent. It evaluates market conditions, and if it detects a massive surge in active listings (velocity drops drastically, indicating panic-selling) immediately following a fixture upset, it executes a strategic purchase at the best available price.

Repository Structure

  • wc26_buyer_system.py — The main orchestrator defining the messages, initializing the agents, configuring their tasks, and starting the Bureau.
  • market_agent.py — Independent script containing the market ingestion logic.
  • .gitignore — Root Git ignore file excluding cache directories, virtual environments, local keys, and agent run states.

Setup & Configuration

Prerequisites

  • Python 3.10+
  • A configured virtual environment (venv)

1. Install Dependencies

Make sure you are in your virtual environment and install the required packages:

pip install uagents httpx python-dotenv ticketsdata-client

2. Configure Environment Variables

Create a .env file inside the wc26_agents folder (ignored by Git) and fill in your API credentials:

AGENT_SEED="your_super_secret_unique_seed"
TICKETSDATA_USERNAME="your_ticketsdata_username"
TICKETSDATA_PASSWORD="your_ticketsdata_password"
API_FOOTBALL_KEY="your_api_football_key"

Running the Bureau

To start all three agents simultaneously inside the bureau, run:

python wc26_agents/wc26_buyer_system.py

The bureau will spin up local servers for the agents and begin checking standings and ticketing platforms automatically.

About

No description, website, or topics provided.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

0