> 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/platform/platform.md).

# Platform overview

Katara is governed AI infrastructure for regulated teams. It sits between the AI tools people already use and the enterprise systems that need oversight.

The platform is organized around four components:

* [AI Knowledge Base](/about/platform/ai-knowledge-base.md): approved knowledge and policy-aware retrieval.
* [AI Gateway](/about/platform/ai-gateway.md): governed model traffic, access checks, routing, and traces.
* [MCP Registry](/about/platform/mcp-registry.md): approved MCP servers and tools with ownership and policy attached.
* [Shared Memory Layer](/about/platform/shared-memory-layer.md): governed context persistence across approved sessions and workflows.

Together, these components help teams answer governance questions such as:

* Which sources were available to the AI workflow?
* Which users, applications, or organizations were in scope?
* Which policies, access rules, or boundaries applied?
* What evidence remains after the interaction?

These docs intentionally avoid detailed configuration instructions unless the behavior is already documented and supported by repo evidence.