Open-source, self-hosted AI-powered IT Operations Management

AIOps Platform is a comprehensive, 100% open-source solution for AI-powered IT operations management. It combines advanced AI capabilities with real-time monitoring and automated remediation to help operations teams detect, diagnose, and resolve incidents faster.

• AI-Powered Analysis: Local LLM (Ollama with Qwen 2.5) for anomaly detection, root cause analysis, and remediation suggestions
• Real-time Monitoring: Time-series metrics storage with TimescaleDB and ClickHouse
• Incident Management: Track and manage incidents with automated correlation
• Playbook Automation: Create and execute automated remediation workflows
• Alert Management: Smart alert deduplication and prioritization
• 100% Self-hosted: No data leaves your infrastructure - airgap compatible

┌─────────────────────────────────────────────────────────────────┐
│                        Frontend (React)                          │
│              Dashboard │ Alerts │ Incidents │ Chat               │
└─────────────────────────────┬───────────────────────────────────┘
                              │
┌─────────────────────────────▼───────────────────────────────────┐
│                      Backend (FastAPI)                           │
│         REST API │ WebSocket │ AI Agents │ Task Queue            │
└──────────┬──────────────────┬──────────────────┬────────────────┘
           │                  │                  │
    ┌──────▼──────┐    ┌──────▼──────┐    ┌──────▼──────┐
    │  PostgreSQL │    │ TimescaleDB │    │  ClickHouse │
    │   (Main DB) │    │  (Metrics)  │    │ (Analytics) │
    └─────────────┘    └─────────────┘    └─────────────┘
           │
    ┌──────▼──────┐    ┌─────────────┐    ┌─────────────┐
    │    Redis    │    │    NATS     │    │   Ollama    │
    │   (Cache)   │    │ (Messaging) │    │    (LLM)    │
    └─────────────┘    └─────────────┘    └─────────────┘

• Docker 24+ with Compose V2
• 8GB RAM minimum (16GB recommended)
• 20GB disk space
• NVIDIA GPU (optional, for faster LLM inference)

1. Clone the repository

   git clone https://github.com/your-org/aiops-platform.git
   cd aiops-platform

2. Run the setup script

   ./scripts/setup.sh

3. Start the stack

   docker compose up -d

4. Access the platform

   • Frontend: http://localhost:5173
   • API Docs: http://localhost:8000/docs
   • Grafana: http://localhost:3000

Default credentials:

• Username: admin
• Password: admin123

Create a .env file in the project root:

# Security (CHANGE THESE IN PRODUCTION)
SECRET_KEY=your-super-secret-key-change-in-production
POSTGRES_PASSWORD=aiops_secure_2024
REDIS_PASSWORD=aiops_redis_2024

# Ollama
OLLAMA_MODEL=qwen2.5-coder:1.5b

# Environment
ENVIRONMENT=development
LOG_LEVEL=INFO

For NVIDIA GPU acceleration, ensure you have the NVIDIA Container Toolkit installed:

# Install NVIDIA Container Toolkit
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
  sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
  sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update && sudo apt-get install -y nvidia-container-toolkit
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker

aiops-platform/
├── backend/              # FastAPI backend
│   ├── app/
│   │   ├── api/          # REST API routes
│   │   ├── agents/       # AI agents (LangChain)
│   │   ├── core/         # Config, database, security
│   │   ├── models/       # SQLAlchemy models
│   │   └── services/     # Business logic
│   └── tests/
├── frontend/             # React frontend
│   └── src/
│       ├── components/   # UI components
│       ├── pages/        # Route pages
│       ├── services/     # API clients
│       └── stores/       # State management
├── infrastructure/
│   ├── docker/           # Docker configs
│   └── kubernetes/       # Helm charts
├── docs/                 # Documentation
└── scripts/              # CLI tools

cd backend
python -m venv venv
source venv/bin/activate
pip install -r requirements-dev.txt

# Run with hot reload
uvicorn app.main:app --reload --port 8000

cd frontend
npm install

# Run dev server
npm run dev

# Backend tests
cd backend && pytest --cov=app

# Frontend tests
cd frontend && npm test

When running in development, API documentation is available at:

• Swagger UI: http://localhost:8000/docs
• ReDoc: http://localhost:8000/redoc
• OpenAPI JSON: http://localhost:8000/openapi.json

1. Change default passwords before deploying to production
2. Use HTTPS with proper TLS certificates
3. Enable network policies in Kubernetes
4. Regularly update all dependencies
5. Review audit logs for suspicious activity

AIOps Platform is designed for airgap environments:

• All dependencies are bundled
• No external API calls
• LLM runs locally via Ollama
• No CDN dependencies in frontend

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Make your changes
4. Run tests (pytest && npm test)
5. Commit your changes (git commit -m 'feat: add amazing feature')
6. Push to the branch (git push origin feature/amazing-feature)
7. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• FastAPI - Modern Python web framework
• React - UI library
• Ollama - Local LLM runtime
• LangChain - LLM orchestration
• TimescaleDB - Time-series database
• TailwindCSS - CSS framework

Made with passion by the AIOps community