# NVIDIA Run:ai Documentation

## Instructions for AI Agents

- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/run-ai/_mcp/server

## Products

- [Self-Hosted](https://docs.nvidia.com/run-ai/self-hosted/llms.txt)
  - [Home](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/home.md)
  - [Overview](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/getting-started/overview.md)
  - [Architecture and Components](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/getting-started/architecture.md)
  - [Deploy Infrastructure Quick Start](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/getting-started/quick-starts/deploy-infrastructure-quick-start.md)
  - [Configure the Platform Quick Start](https://docs.nvidia.com/run-ai/self-hosted/v3.0/documentation/getting-started/quick-starts/configure-the-platform-quick-start.md)
- [Multi-Tenant](https://docs.nvidia.com/run-ai/multi-tenant/llms.txt)
  - [Home](https://docs.nvidia.com/run-ai/multi-tenant/v3.0/documentation/home.md)
  - [Overview](https://docs.nvidia.com/run-ai/multi-tenant/v3.0/documentation/getting-started/overview.md)
  - [Architecture and Components](https://docs.nvidia.com/run-ai/multi-tenant/v3.0/documentation/getting-started/architecture.md)
  - [Support, Lifecycle, and Deprecation Policy](https://docs.nvidia.com/run-ai/multi-tenant/v3.0/documentation/getting-started/support-lifecycle-and-deprecation-policy.md)
  - [Overview](https://docs.nvidia.com/run-ai/multi-tenant/v3.0/documentation/installation-and-configuration/overview.md)