Skip to main content
Inviolet adds intent-aware access control to every LLM tool call — so your data stays protected even when your agents go rogue. This is the technical documentation; for product overviews and pricing, see inviolet.ai.

​
Start here

Quickstart

Install the gateway and watch your first intent in under five minutes.

Concepts

What Intent Detection and Response (IDR) is, why it matters, and where it sits in your stack.

SDKs

Node, Python, and REST clients for the Inviolet gateway.

Tier comparison

Violet, Deep Violet, and Ultraviolet — what each tier unlocks.

​
What Inviolet is

Inviolet is the access-control layer your AI agents pass through before they touch your data. Every tool call carries a declared intention; every intention is matched against policy; every match writes an audit record; every credential issued has an expiry tied to the active intention. The result: your agents can use the data they need for the work you authorized, and nothing else. When something unexpected happens, you see it as a denial in the live decision feed before it becomes a breach in the news.

​
What this documentation covers

  • Getting Started — concepts and installation paths
  • Guides — step-by-step recipes for the most common workflows
  • SDKs — language-specific reference (Node, Python, REST)
For commercial questions, talk to the Inviolet sales agent on the marketing site — it has full context on tiers, pricing, and your specific compliance requirements.