Self-hosted AI — for whom and why?
Self-hosted AI is for companies where data sensitivity (finance, healthcare, public sector) requires the data to never leave the infrastructure.
Nortinia AI Assistant in self-hosted mode runs on your own servers, in your own VPC or on-premise — optionally air-gapped. Open-source models (Llama, Mistral) supported for full independence.
What does the self-hosted option mean?
Your own environment
On-premise, your own VPC (AWS/GCP/Azure), Kubernetes or Docker.
Air-gapped option
Runs fully offline — for the most sensitive industries.
Open-source models
Llama, Mistral and other open-source models — no cloud API dependency.
Your own keys
Anthropic / OpenAI API keys are yours — or zero cloud dependency.
Self-hosted rollout
Architecture plan
On-premise vs own VPC, model selection, integrations.
Install
Kubernetes Helm chart or Docker Compose. NIP Platform optional.
Knowledge base migration
Document import, indexing in your environment.
Operations
24/7 monitoring, eval dashboard, model update management.
What it builds on and connects to
Nortinia AI Assistant — product home
Embeddable AI assistant for every surface you own.
NIP Platform — self-hosted infrastructure
Private cloud and deploy platform for on-premise AI rollouts.
Nortinia Engine — LLM routing and decision layer
The Nortinia AI engine — model routing, prompt management, eval harness.
Nortinia.com — AI and software engineering background
The engineering studio behind the Nortinia AI Assistant.
Nortinia Sales AI — outbound side
Assistant talks to visitors on your site. Sales AI calls, writes and advertises prospects on your behalf. Inbound + outbound, one stack.
Nortinia AI Chat — text-only, cheaper
Same Nortinia AI Engine, just text-only — no voice calls. Faster to deploy, lower monthly price. If your focus is text channels, this is the one.
Nortinia AI Call Center — 24/7 voice call center
Full voice-based call center: inbound + outbound, parallel call handling, recording and transcripts. Assistant is task-focused; Call Center is call-focused.
Self-hosted AI chatbot — questions
Where can it be deployed?
On-premise, own VPC (AWS/GCP/Azure), Kubernetes or Docker Compose. NIP Platform optional for managed self-hosted.
Which models run in self-hosted mode?
Open-source models: Llama 3, Mistral, Gemma, Qwen. Cloud models (Anthropic, OpenAI) can also be used with your own keys.
Does it work in an air-gapped environment?
Yes — fully offline. Model + knowledge base + LLM in your own environment. Updates ship as signed packages.
Which GDPR/ISO compliance is supported?
Data storage in your environment, AES-256-GCM encryption, audit trail, permission tiers, data export/deletion API.
Self-hosted demo on your own infrastructure.
60-minute workshop, architecture plan, install timeline at the end.