Technology
Nexma is built on a skill-driven architecture where a single AI agent serves any infrastructure domain. Here's how the layers work together.
Platform architecture
Agentic loop powered by Claude — reads, writes, and reasons over spatial data autonomously. Domain knowledge injected through configuration, not hardcoded tools.
Unified data layer that serves as the single source of truth. Agent skills, spatial data, and configuration coexist in a structured representation. Every view renders from it.
The type system that defines a domain. Entities, relationships, constraints, expressions, rendering rules — load a different agent skill, get a different application. Zero code changes.
Mapbox GL JS foundation with satellite imagery, 3D terrain, and live intelligence overlays. Real-time rendering of spatial data from the unified data engine.
Multiple solver families dispatched automatically based on problem structure. Optimized for speed at interactive scale. Self-correcting on constraint violations.
Next.js 15 monorepo with TypeScript, Turborepo, and pnpm workspaces. Clerk auth, Vercel deployment, and strict Biome linting. Mobile app with offline-first architecture.
Every capability ships with every seat. No feature gates, no module add-ons.
Telecom, water, electric, gas, logistics, construction, defense — one platform, any domain through agent skill plugins.
Jax speaks your language. Full natural language support with voice I/O in 70+ languages including RTL support.
Android field app with offline-first sync, dual camera, voice I/O, and GPS tracking. Designed for construction sites.
SSO/SAML, audit logs, data isolation, encryption at rest and in transit. SOC 2 and ISO 27001 compliance path.
100+ real-time data feeds — ADS-B flights, AIS ships, weather, satellites, seismic — unified on a single map.
Import and export GeoJSON, Shapefile, KML, CSV, and more. No vendor lock-in — your data stays portable.
Book a technical demo and see how Nexma's architecture translates to real-world infrastructure design in minutes.