This repo is an experiment in vibe codign with no human intervention. Please do not take it as reflective of my general code quality practices
An intelligent email classification and management system designed for professionals with ADHD who need focused, actionable email summaries.
npm startThis will start both the React frontend and API backend automatically!
For developers working on the web application (React frontend + FastAPI backend):
- Windows 10/11 with Microsoft Outlook installed and configured
- Python 3.12+ and pip (download)
- Node.js 18+ and npm (download)
# 1. Clone and navigate to the repository
git clone https://github.com/AmeliaRose802/email_helper.git
cd email_helper
# 2. Set up backend
pip install -r requirements.txt
cp .env.localhost.example .env
# 3. Set up frontend
cd frontend
npm install
cp .env.local.example .env.local
cd ..
# 4. Start backend (in one terminal)
python run_backend.py
# 5. Start frontend (in another terminal)
cd frontend
npm run devThen open your browser to http://localhost:3000 or http://localhost:5173
π Detailed Instructions: See Localhost Setup Guide for comprehensive setup instructions, configuration options, and troubleshooting.
For the original desktop application with Tkinter GUI:
pip install -r requirements.txtChoose your preferred authentication method:
Option A: Azure CLI (Recommended - Most Secure)
az loginOption B: Environment Variables (Fallback)
# Copy template and configure
cp .env.template .env
# Edit .env with your Azure OpenAI details# Create user-specific data directory (if not exists)
mkdir user_specific_data
# Copy templates and customize
cp job_summery.md.template user_specific_data/job_summery.md
cp job_skill_summery.md.template user_specific_data/job_skill_summery.md
# Edit the files with your job context and skillspython email_manager_main.pyemail_helper/
βββ email_manager_main.py # Main entry point (GUI)
βββ src/ # Application code
β βββ unified_gui.py # Unified GUI interface
β βββ ai_processor.py # AI/prompty integration
β βββ azure_config.py # Secure Azure authentication
β βββ ...
βββ prompts/ # AI prompt templates
β βββ email_classifier_system.prompty
β βββ email_one_line_summary.prompty
β βββ ...
βββ user_specific_data/ # Your personal data (NOT COMMITTED)
β βββ job_summery.md # Your job context
β βββ job_skill_summery.md # Your skills profile
βββ .env # Environment variables (NOT COMMITTED)
βββ .env.template # Template for environment setup
βββ requirements.txt # Python dependencies
user_specific_data/- Your job context, skills, and personal information.env- Environment variables and API keys*summary*.html- Generated email summaries (may contain sensitive content)- Azure credentials - All authentication tokens and keys
- Azure DefaultCredential (
az login) - Most secure, no stored credentials - Environment Variables (
.envfile) - Secure fallback
The AI system needs to understand your job context and skills to classify emails accurately. These files contain your personal information and are kept private.
Describe your role, responsibilities, and work focus areas:
I am a Software Engineer working on Azure Compute Node Services, specifically:
- Your job role here
[Add your specific job context...]List your technical skills and learning interests:
## Core Technical Skills
- Programming Languages: C#, Python, Go
- Cloud Platforms: Azure (Expert), AWS (Basic)
[Add your skills and interests...]Your username/email alias for personalized email classification:
your_username
Note: This is used to identify emails sent directly to you vs. mass distribution.
- Smart Email Classification: Automatically categorizes emails into actionable categories
- ADHD-Friendly Summaries: Focused, concise summaries without distractions
- Secure Authentication: Multiple authentication options with security best practices
- Learning System: Improves classification accuracy based on your feedback - TODO: Currently stores this but does not learn from it yet
- Customizable Categories: Tailored to professional workflows and priorities
- Localhost Setup Guide - Complete localhost development setup
- Backend README - Backend API documentation and setup
- Frontend README - React frontend documentation and setup
SECURITY_SETUP.md- Detailed security configuration guidescripts/README.md- Technical implementation details
- Complete Documentation Index - Start here for all documentation
- Quick Start Guide - Get up and running quickly
- User Setup - Detailed setup instructions
- Feature Guides - Learn about specific features
- Technical Documentation - Architecture and design details
- Test Documentation - Testing guide and organization
- Troubleshooting Guide - Common issues and solutions
Backend won't start:
# Check if port 8000 is already in use
netstat -ano | findstr :8000
# Verify Python dependencies are installed
pip install -r requirements.txt
# Check Outlook is installed and configuredFrontend can't connect to backend:
# Verify backend is running
curl http://localhost:8000/health
# Check .env.local has correct API URL
cat frontend/.env.local | grep VITE_API_BASE_URL
# Ensure CORS is configured in backend .envOutlook COM errors:
- Ensure Microsoft Outlook is installed (2016 or later)
- Open Outlook manually to verify it works
- Run the application with administrator privileges
- Check Windows COM settings
π More Help: See the Troubleshooting Guide for comprehensive troubleshooting steps.
This is a personal productivity tool, but improvements are welcome! Please ensure:
- No personal data in commits
- Security best practices maintained
- Documentation updated for changes
- Tests written and passing (see
test/TEST_ORGANIZATION.md) - Follow guidelines in
.github/copilot-instructions.md
- Never commit personal data - The
.gitignoreprotects you, but double-check - Review summaries before sharing - Generated content may contain sensitive information
- Keep authentication secure - Use
az loginwhen possible, rotate API keys regularly