Skip to content

OriLevin55/cryptosentinel

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

CryptoSentinel — AI-Powered Crypto News Sentiment Tracker

A professional-grade web application that analyzes real-time market sentiment for any cryptocurrency by combining global news data with AI-powered natural language processing.

Enter a crypto symbol (BTC, ETH, SOL, DOGE, XRP, etc.) and CryptoSentinel instantly fetches the latest news articles and uses Claude AI to classify each headline as Positive, Negative, or Neutral — complete with confidence scores and interactive visualizations.


Features

  • Real-Time News Ingestion — Fetches the 20 most recent articles for any cryptocurrency via NewsAPI
  • AI Sentiment Analysis — Each headline is analyzed by Claude (Anthropic) for sentiment and confidence scoring
  • Interactive Dashboard — Gauge chart, donut breakdown, timeline visualization, and per-article cards
  • Dark Terminal Aesthetic — Sleek trading-terminal UI with neon accents, animations, and responsive design
  • Instant Symbol Lookup — Quick-pick pills for popular coins or type any symbol

Tech Stack

Layer Technology
Backend Python, Flask
AI Engine Claude API (Anthropic)
News Data NewsAPI
Frontend Vanilla HTML / CSS / JS
Charts Chart.js (CDN)
Fonts Inter (Google Fonts)

Getting Started

Prerequisites

Installation

git clone https://github.com/OriLevin55/CryptoSentinel.git
cd CryptoSentinel
python -m venv venv
source venv/bin/activate   # Windows: venv\Scripts\activate
pip install -r requirements.txt

Configuration

Copy the example env file and fill in your keys:

cp .env.example .env
ANTHROPIC_API_KEY=sk-ant-...
NEWS_API_KEY=your-newsapi-key

Run

python app.py

Open http://localhost:5000 in your browser.

How It Works

  1. User enters a crypto symbol (e.g. BTC)
  2. The backend queries NewsAPI for the latest 20 articles matching that cryptocurrency
  3. All headlines are sent to Claude in a single request for batch sentiment analysis
  4. Claude returns a JSON array with sentiment labels and confidence scores
  5. The frontend renders an interactive dashboard with charts, metrics, and article cards

Real-World Use Cases

  • Traders & Investors — Quickly gauge market sentiment before making buy/sell decisions
  • Research Analysts — Track how news coverage shifts over time for a given asset
  • Content Creators — Identify trending narratives and sentiment swings for crypto content
  • Portfolio Managers — Monitor sentiment across multiple holdings in seconds

Project Structure

CryptoSentinel/
├── app.py               # Flask backend (routes + API integration)
├── templates/
│   └── index.html       # Complete frontend (HTML + CSS + JS inline)
├── requirements.txt     # Python dependencies
├── .env.example         # Environment variable template
└── README.md

License

This project is open source and available under the MIT License.


Built with Claude AI by Ori Levin

About

AI-powered crypto news sentiment tracker — Flask + Claude API + NewsAPI + Chart.js

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages