Full-stack platform that scrapes, stores, and analyzes sports betting odds in real time using a LangGraph AI agent powered by DeepSeek V3.1.
# ScrapOddsAPI
Full-stack platform that scrapes, stores, and analyzes sports betting odds in real time using a LangGraph AI agent powered by DeepSeek V3.1.
## Architecture
```
The Odds API --> Python Scraper --> PostgreSQL --> Flask + LangGraph Agent --> React Frontend
|
ChromaDB (RAG) + football-data.org
```
| Layer | Technology |
|-------|-----------|
| Data source | [The Odds API](https://the-odds-api.com/) |
| Scraper | Python 3.11+, httpx, pandas |
| Database | PostgreSQL 15+ (Docker) |
| Backend | Flask, LangGraph, DeepSeek V3.1 (OpenRouter), psycopg2 |
| RAG | ChromaDB, sentence-transformers |
| Live data | [football-data.org](https://www.football-data.org/) (standings, scorers) |
| Frontend | React 18, Vite, TailwindCSS |
## Project Structure
```
ScrapOddsAPI/
├── scrapping/ # Data collection scripts
│ ├── odds_scraper.py
│ └── rag/ # RAG context builder
├── odds-agent/
│ ├── backend/server_py/ # Flask API + LangGraph agent
│ │ ├── app.py # API routes
│ │ ├── graph.py # LangGraph state graph
│ │ ├── budget.py # Cost tracking
│ │ ├── tools/ # Agent tools (odds, RAG, football-data)
│ │ └── services/ # Data services
│ └── frontend/ # React application
├── pyproject.toml # Python dependencies (uv)
├── docker-compose.yml
└── README.md
```
## Supported Leagues
Premier League, La Liga, Serie A, Bundesliga, Ligue 1, Champions League.
## Prerequisites
- Python 3.11+
- [uv](https://docs.astral.sh/uv/) (fast Python package manager)
- Node.js 18+
- Docker Desktop
- API keys: [The Odds API](https://the-odds-api.com/), [OpenRouter](https://openrouter.ai/keys), [football-data.org](https://www.football-data.org/client/register)
## Setup
```bash
git clone <your-repo-url>
cd ScrapOddsAPI
# Environment vaHAL 分层混合模型工作流 — 强模型(Claude)负责理解/拆解/验收,低成本模型(DeepSeek)负责检索/提取/清洗。Hermes Agent skill。
An LLM agent fine-tuned on DeepSeek for spaced repetition, dynamically integrating knowledge points based on the Ebbinghaus forgetting curve.
基于 STM32F103 构建的端到端 AI 智能手表生态。自研“零重定位”原生机器码动态加载引擎与页面栈式 UI 框架;集成生产级 OTA 回滚保护机制与高带宽(921600 baud)串口协议栈。通过 Node.js 中继实现 DeepSeek AI 语义控制及 ASRPRO 语音全双工交互,是一个集成了分布式计算、现代存储管理与 AI Agent 的嵌入式全栈工程。
A Meta-Agent-Driven Self-Evolving Multi-Agent System for UAV Detection and Tracking
One command to run Hermes AI Agent with a browser UI. Zero prerequisites. 一行命令,AI 就位。
网页应用Agent,接入DeepSeek、Mimo等模型