Content Aviator without Content Cloud

You can run a full AI assistant inside OpenText Content Management without moving to OpenText Content Cloud. tara deploys on the OpenText you already run and does far more than answer questions — it retrieves under your existing ACLs and acts in-chat, entirely inside your network. The only pluggable piece is the language model, which you can self-host for a fully air-gapped deployment.

Request a demo See the architecture

AI inside OpenText, no Content Cloud

tara UIExperience layer · same tara, multiple ways to work

Standalone tara App

Full-page chat workspace

tara Widget

Embedded panel inside the OTCM UI

tara Mobile coming next

tara on the go — in the works

tara Platform on-premise · kubernetes

REST API

Integrates tara into any system across your enterprise landscape

rag engineproprietary

Cascade Retrieval

Hybrid content searchMetadata-awareACL filterGrounded context

Vector & Metadata Store

Full-text index & metadata

external · 3rd party

Chat-LLM

Pluggable model provider — bring your own

Azure AI Foundry
Amazon Bedrock
Google Vertex AI
Self-hosted / custom model

syncReal-time sync keeps the index up to date

Change Observer

Delta Queue

Delta changes from OTCM

Stateless Workers

Queue processors · scale horizontally

integrations3 supported ways to integrate with OTCM

Database Connector

REST API Connector

WebReports Power Pack

source of record

OpenText Content Manager (OTCM)

Everything inside the on-premise boundaryruns on your Kubernetes — the RAG engine, the vector & metadata store, and OpenText Content Manager itself. Your content never leaves your network. The language model is the only pluggable component: point it at your own cloud tenant or a self-hosted model for a fully air-gapped deployment.

A full AI assistant on your own OpenText

No Content Cloud, no migration

tara runs on the OpenText Content Management you already operate. There is no move to OpenText Content Cloud, no re-platforming and no content migration — you point tara at your existing repository and it works.

Answers governed by your OpenText ACLs

Every answer is filtered by existing OpenText access rights. Users only ever see content they are already permitted to open — there is no separate permission model to build or maintain.

Acts, doesn't just answer

tara is a full assistant, not a search box. It retrieves across your content and takes in-chat actions on it — grounded in your documents and running entirely inside your network.

Pluggable, self-hostable LLM

Point the language model at your own Azure, Bedrock or Vertex tenant, or run a self-hosted open model inside the boundary for a fully air-gapped deployment. Only the LLM is ever pluggable.

Want to see how tara works live?

We offer a focused live demo of tara. We show how it works in real time, explain key capabilities, walk through the vision and answer your questions.

hello@teamnine.eu

Hi, I'm tara.

Book your live demo