An intelligent task assignment system powered by AI that analyzes GitHub issues and developer profiles to make optimal task assignments. Features multi-provider AI support, Google SSO authentication, and automatic notification generation.

• User Authentication: Secure login/signup with password hashing
• Google SSO: One-click sign-in with Google OAuth
• API Key Management: Store and auto-load your AI provider keys

• OpenAI (GPT-4, GPT-3.5)
• Google Gemini (Gemini 1.5 Pro, Gemini 2.0 Flash)
• Local AI (Ollama - run models locally)

• GitHub Integration: Fetch issues and contributors directly from repositories
• AI Analysis: Intelligent matching of tasks to developers based on skills, workload, and preferences
• Manual Upload: JSON file upload for offline use

• Auto-generate Jira tickets with professional descriptions
• Create Slack messages for developer notifications
• Draft Messenger updates for quick status sharing

• SQLite database for persistent storage
• Assignment history tracking
• User profile management

• Python 3.8+
• Git
• Google Cloud Console account (for Google SSO)

1. Clone the repository

git clone https://github.com/yordanos-habtamu/AI-Task-Assigner.git
cd AI-Task-Assigner

2. Create virtual environment

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies

pip install -r requirements.txt

4. Configure environment variables

cp .env.example .env

Edit .env and add your API keys:

# AI Provider (choose one)
OPENAI_API_KEY=your_openai_key
# OR
GOOGLE_API_KEY=your_gemini_key

# Google OAuth (optional, for SSO)
GOOGLE_CLIENT_ID=your_google_client_id
GOOGLE_CLIENT_SECRET=your_google_client_secret

# GitHub (optional, for higher rate limits)
GITHUB_TOKEN=your_github_token

Terminal 1 - Start OAuth Server:

./run_oauth.sh

Terminal 2 - Start Streamlit App:

./run.sh

Access at:

• Streamlit App: http://localhost:8501
• OAuth Server: http://localhost:8502

./run.sh

Then create an account using username/password.

1. Go to Google Cloud Console
2. Create a new project or select existing
3. Go to APIs & Services → Credentials
4. Click Create Credentials → OAuth 2.0 Client ID
5. Configure OAuth consent screen
6. Add redirect URI: http://localhost:8502/auth/google/callback
7. Copy Client ID and Client Secret to .env

See GOOGLE_SSO_SETUP.md for detailed instructions.

1. Get API key from OpenAI Platform
2. Add to .env: OPENAI_API_KEY=sk-...

1. Get API key from Google AI Studio
2. Add to .env: GOOGLE_API_KEY=...

1. Install Ollama: https://ollama.ai
2. Pull a model: ollama pull llama3.1
3. Start Ollama: ollama serve

• Google: Click "Continue with Google"
• Username/Password: Create an account or login

• Select provider (OpenAI, Gemini, or Ollama)
• Enter API key if needed
• Choose model
• Click "💾 Save API Keys to Profile" (optional)

Option A: GitHub Repository

• Enter repository URL (e.g., owner/repo)
• Add GitHub token for private repos
• Click "Fetch Data"

Option B: Manual JSON Upload

• Upload issues.json and developers.json
• See backend/data/ for example formats

• Click "🚀 Run AI Assignment"
• View results in the table
• Check "📝 Review & Send" tab for notifications

• Edit Jira ticket descriptions
• Customize Slack messages
• Click "🚀 Send All (Simulate)" or individual send buttons

TaskAssignAi/
├── backend/
│   ├── ai/                      # AI agents
│   │   ├── llm_provider.py     # Multi-provider abstraction
│   │   ├── issue_agent.py      # Issue analysis
│   │   ├── dev_agent.py        # Developer analysis
│   │   ├── assign_agent.py     # Task assignment
│   │   └── notification_agent.py # Notification generation
│   ├── oauth_server.py         # Flask OAuth server
│   ├── database.py             # SQLAlchemy models
│   ├── crud.py                 # Database operations
│   ├── auth_utils.py           # Password hashing
│   └── data/                   # Sample JSON files
├── frontend/
│   ├── app.py                  # Main Streamlit UI
│   └── auth.py                 # Login/Signup pages
├── run.sh                      # Start Streamlit
├── run_oauth.sh               # Start OAuth server
└── requirements.txt           # Python dependencies

pytest

python backend/main.py

# View database
sqlite3 task_assignments.db

# Reset database
rm task_assignments.db

• API keys are stored in plain text in the database (encrypt in production)
• Use HTTPS in production
• Rotate OAuth secrets regularly
• Don't commit .env file to version control

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Submit a pull request

MIT License - see LICENSE file for details

• Built with Streamlit
• AI powered by OpenAI, Google Gemini, and Ollama
• OAuth integration with Authlib

For issues and questions:

• GitHub Issues: https://github.com/yordanos-habtamu/AI-Task-Assigner/issues
• Documentation: See QUICKSTART.md and DEMO.md

Made with ❤️ by the TaskAssignAI Team