Skip to main content

Getting Started

Get CALMGuard running locally in under 5 minutes.

Prerequisites​

RequirementMinimum VersionNotes
Node.js22+LTS recommended
pnpm9+npm install -g pnpm
GitAnyFor cloning
Google Gemini API key—Free tier sufficient for demo

Installation​

1. Clone the repository​

git clone https://github.com/finos/dtcch-2026-opsflow-llc.git
cd dtcch-2026-opsflow-llc

2. Install dependencies​

pnpm install

3. Configure environment variables​

Create a .env.local file in the project root:

# Required — Gemini is the default LLM provider
GOOGLE_GENERATIVE_AI_API_KEY=your-gemini-api-key-here

# Optional — additional LLM providers
ANTHROPIC_API_KEY=your-anthropic-key
OPENAI_API_KEY=your-openai-key

Getting a Gemini API key:

  1. Visit Google AI Studio
  2. Create a new API key (free tier includes 15 requests/minute)
  3. Copy the key to your .env.local

4. Start the development server​

pnpm dev

The app will be available at http://localhost:3000.

Quick Start​

Once the server is running:

  1. Navigate to the dashboard — visit http://localhost:3000
  2. Select a demo architecture — choose "Trading Platform" or "Payment Gateway" from the dropdown
  3. Click "Analyze" — watch the four AI agents stream their findings in real-time
  4. Explore the dashboard — compliance scores, architecture graph, risk heat map, and pipeline configs appear as agents complete

The full analysis typically takes 30-60 seconds depending on your LLM provider's response time.

Demo Architectures​

Two demo architectures are bundled in the examples/ directory:

ArchitectureDescriptionNodesComplexity
Trading PlatformEquities trading system with market data feeds, order matching, and regulatory reporting12 nodesHigh
Payment GatewayPayment processing with fraud detection, card networks, and settlement8 nodesMedium

Both include realistic CALM controls referencing PCI-DSS, SEC, and FINRA requirements, making them ideal for demonstrating compliance analysis.

Next Steps​