> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Integrate into Frameworks

## Docs

- [About](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/about.md): Choose NeMo Relay APIs for tool and LLM calls controlled by a framework.
- [Adding Scopes](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/adding-scopes.md): 
- [Wrap Tool Calls](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/wrap-tool-calls.md): 
- [Wrap LLM Calls](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/wrap-llm-calls.md): 
- [Handle Non-Serializable Data](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/non-serializable-data.md): 
- [Using Codecs](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/using-codecs.md): 
- [Provider Codecs](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/provider-codecs.md): 
- [Provider Response Codecs and Model Pricing](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/provider-response-codecs.md): Normalize LLM response data with provider codecs and configure model pricing estimates.
- [Code Examples](https://docs.nvidia.com/nemo/relay/v0.10.0/integrate-into-frameworks/code-examples.md):