georgedouzas/sports-betting

Collection of sports betting AI tools.

What it solves

sports-betting provides a comprehensive toolkit for creating, testing, and deploying sports betting models. It simplifies the process of gathering sports statistics and betting odds, backtesting strategies against historical data, and identifying "value bets" (where the model's predicted probability is higher than the bookmaker's implied probability).

How it works

The library is divided into two primary components:

  1. Dataloaders: These handle the extraction and shaping of data from specified statistics and odds sources, ensuring the user knows exactly where the data originates.
  2. Bettors: These wrap scikit-learn estimators to backtest betting strategies and predict value bets for upcoming events.

Beyond modeling, the project includes an execution layer that can place bets via bookmaker APIs or by automating a web browser (using Playwright) to interact with bookmaker websites.

Who it’s for

  • Data Scientists and ML Engineers: Those who want to build and evaluate sports prediction models using the scikit-learn ecosystem.
  • AI Agent Developers: The project includes an MCP server, allowing AI agents (like Claude) to explore data, write models, backtest them, and execute bets.
  • Sports Bettors: Users looking for a programmatic way to find and act on value bets.

Highlights

  • AI Agent Integration: Features a dedicated MCP server that enables AI agents to perform the full workflow from data exploration to bet placement.
  • Scikit-learn Compatibility: Any scikit-learn estimator can be used as the underlying model for the bettor.
  • End-to-End Workflow: Covers the entire pipeline: data extraction, model training, backtesting, and automated bet execution.
  • Multi-Interface Access: Available via a Python API, a command-line interface (CLI), and as an MCP server for AI agents.

Related

  • Project
    JerBouma/FinanceToolkit

    An open-source financial toolkit providing over 500 transparent calculation methods for financial metrics, eliminating reliance on inconsistent proprietary data sources.

  • Project
    aws/agent-toolkit-for-aws

    A toolkit that provides AI coding agents with the tools, knowledge, and guardrails needed to build, deploy, and manage applications on AWS.

  • Project
    matlab/matlab-agentic-toolkit

    A toolkit that connects AI coding agents to MATLAB via an MCP server and curated skills, preventing hallucinations and enabling agents to write and execute idiomatic MATLAB code.

  • Project
    Unity-Technologies/ml-agents

    A toolkit that turns Unity games and simulations into environments for training intelligent agents using reinforcement and imitation learning.

  • Project
    caiovicentino/polymarket-mcp-server

    Polymarket MCP Server is a Python‑based MCP server that lets Claude (or any LLM) autonomously discover, analyse, trade, and monitor Polymarket prediction‑market positions. It offers 45 tools across market discovery, analysis, trading, portfolio management, and real‑time monitoring, all guarded by configurable safety limits and full‑node authentication. A web dashboard provides visual control, and the project includes real‑API tests, MIT licensing, and detailed docs for both demo (read‑only) and live‑trading setups.