> For the complete documentation index, see [llms.txt](https://docs.katara.ai/about/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.katara.ai/about/overview/readme.md).

# Welcome to Katara

## What is Katara?

Katara is governed AI infrastructure that lets regulated organizations adopt AI while proving every interaction stays controlled, traceable, and compliant.

Katara sits between the AI tools your team already uses and the systems that need oversight. It applies policy, traceability, and access control so teams can keep working while governance evidence is produced along the way.

## Platform components

Katara is organized around four platform components:

* [**AI Knowledge Base**](/about/platform/ai-knowledge-base.md): keeps AI retrieval tied to approved sources, permissions, and policy.
* [**AI Gateway**](/about/platform/ai-gateway.md): keeps model traffic inside policy with access, routing, budget, and traceability controls.
* [**MCP Registry**](/about/platform/mcp-registry.md): manages approved MCP servers and tools so agents discover only the tools they are allowed to call.
* [**Shared Memory Layer**](/about/platform/shared-memory-layer.md): preserves useful context across sessions while scope, retention, and reuse stay governed.

Start with the [platform overview](/about/platform/platform.md), then open the component that matches the system you are evaluating.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.katara.ai/about/overview/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.