Documentation

Overview

UrNammu is an open-source AI governance and compliance platform for enterprise teams. It provides centralized oversight of AI systems, autonomous agents, and API usage across your organization.

What is UrNammu?

Named after the ancient Sumerian code of law, UrNammu brings structure and accountability to AI usage in your organization. It answers critical questions:

  • What AI systems are we running? — Complete registry of systems and agents
  • What risks do they pose? — Multi-dimensional risk scoring and heat maps
  • Are we compliant? — Policy tracking, framework mapping, and audit trails
  • What shadow AI exists? — Automated discovery via Workspace scans and DNS logs
  • What does it cost? — API usage telemetry and cost governance

Key capabilities

  • AI System & Agent Registry — Inventory every AI system and autonomous agent with ownership, approval workflows, and lifecycle tracking
  • Risk Center — Score systems across six dimensions (bias, security, privacy, fairness, performance, transparency) with interactive heat maps
  • Shadow AI Discovery — Detect unregistered tools via Google Workspace OAuth scans, DNS/proxy log imports, and manual reporting
  • Compliance & Policy — Define governance policies, map to frameworks (EU AI Act, NIST, ISO 42001), and track compliance per system
  • AI Oversight — Monitor API usage, model drift, and costs across providers with anomaly detection
  • Executive Dashboard — Board-ready governance posture summaries with 12-month trends
  • Vendor Governance — Track vendor risk, contracts, and data residency requirements

Quick start

The fastest way to get running:

git clone https://github.com/your-org/urnammu.git
cd urnammu
npm install
cp .env.example .env     # Configure your environment
npx prisma migrate dev   # Set up database
npm run db:seed           # Load demo data
npm run dev               # Start on http://localhost:3000

For the full installation guide including production deployment, see the Installation page.

Prerequisites

  • Node.js 20+
  • PostgreSQL 16+ (Homebrew on macOS, or any managed Postgres)
  • Google OAuth credentials (for production authentication)
  • Optional: Azure Functions CLI (for the API proxy)