Welcome

K-AI is a Document Knowledge Platform (DKP) — a platform that turns a dispersed, ungoverned document estate into a reliable, observable, AI-consumable knowledge asset. This site is the technical reference for engineers integrating, evaluating, or operating K-AI. For commercial positioning and category overview, see k-ai.ai.

Where to start

• I want to evaluate K-AI → The K-AI Platform. Architecture, security, deployment, compliance.

• I want to integrate K-AI → Choose your auth, then dive into Sources & ingestion, K-AI Audit, or K-AI MCP.

• I want to operate K-AI → Operate. Deployment, monitoring, runbooks.

Map of the documentation

• Get started — quickstarts and auth chooser.

• The K-AI Platform — DKP concepts, 5-layer architecture, roles, security, compliance.

• Authentication — Instance API keys, OAuth 2.1, cookies.

• Sources & ingestion — connectors and the Instance API for indexation control.

• K-AI Audit — conflict-first audit workflow (K-AI Audit web app + Audit API + MCP).

• K-AI MCP — Model Context Protocol surface for AI agents.

• Operate — deployment, monitoring, scaling, runbooks.

• Reference — OpenAPI specs, glossary, errors, changelog.