Technology stack

Local AI, private by design.

Ollama runs the language models behind Health AI analysis directly on NexDam infrastructure - your scan data is interpreted locally and never leaves for a third-party API.

Where Ollama fits

After every scan, a locally hosted model reads the results and writes a plain-language advisory: what is critical, why it matters and how to fix it. All inference happens on NexDam hardware.

  • Fully local model inference
  • No data sent to external AI providers
  • Plain-language security advisories
  • Runs alongside the engine in Docker
Ollama

AI that respects your data.

See how Health AI explains every scan.

Explore the products →