> This page is for NeMo Relay, version dev.
> For other versions, use one of these documentation indexes:
> - Latest (v0.11.2) (default): https://docs.nvidia.com/nemo/relay/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/relay/dev/llms.txt
> - v0.11.2: https://docs.nvidia.com/nemo/relay/v0.11.2/llms.txt
> - v0.10.4: https://docs.nvidia.com/nemo/relay/v0.10.4/llms.txt
> - v0.9.4: https://docs.nvidia.com/nemo/relay/v0.9.4/llms.txt
> - v0.8.4: https://docs.nvidia.com/nemo/relay/v0.8.4/llms.txt
> - v0.7.3: https://docs.nvidia.com/nemo/relay/v0.7.3/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.

# Frameworks

> Install Relay for Google ADK, LangChain, LangGraph, or Deep Agents.

Add the extra for your framework to an existing Python project. These commands
install the latest stable Relay release and the framework dependencies it needs.
The quick starts include project creation and pin their example versions.

## Google ADK

```bash
uv add "nemo-relay[google-adk]"
```

Continue with the [Google ADK Quick Start](/nemo/relay/dev/getting-started/quick-start/google-adk)
or [Google ADK Integration Guide](/nemo/relay/dev/supported-integrations/google-adk).

## LangChain

```bash
uv add "nemo-relay[langchain]"
```

Continue with the [LangChain Quick Start](/nemo/relay/dev/getting-started/quick-start/langchain).

## LangGraph

```bash
uv add "nemo-relay[langgraph]"
```

Continue with the [LangGraph Quick Start](/nemo/relay/dev/getting-started/quick-start/langgraph).

## Deep Agents

```bash
uv add "nemo-relay[deepagents]"
```

Continue with the [Deep Agents Quick Start](/nemo/relay/dev/getting-started/quick-start/deep-agents).

## Installation Notes

Run `uv add` in a project with a `pyproject.toml`; run `uv init` first for a new
project. If you use an active virtual environment without project metadata, use
`uv pip install` or `pip install` with the same package extra instead.

Model providers can require additional dependencies and credentials. The LangChain
and Deep Agents quick starts include the `langchain-nvidia` extra for their NVIDIA
model examples. For integration coverage and configuration, use
[Supported Integrations](/nemo/relay/dev/supported-integrations/about).