Skip to main content
Ctrl+K
NVIDIA NeMo Relay - Home NVIDIA NeMo Relay - Home

NVIDIA NeMo Relay

  • GitHub
NVIDIA NeMo Relay - Home NVIDIA NeMo Relay - Home

NVIDIA NeMo Relay
  • GitHub
Version v0.3 beta.2 Prerelease snapshot Prerelease
  • v0.2 Latest stable Stable
  • v0.1 Release snapshot Stable
  • v0.3 beta.2 Prerelease snapshot Prerelease

Table of Contents

About NeMo Relay

  • Overview
  • Architecture
  • Ecosystem
  • Concepts
    • Scopes
    • Middleware
    • Plugins
    • Events
    • Subscribers
    • Framework Integrations
  • Release Notes
    • Highlights
    • Known Issues
    • Related Topics

Getting Started

  • Agent Runtime Primer
  • Prerequisites
  • Installation
  • Configuration / Setup
  • Quick Start
    • Python Quick Start
    • Node.js Quick Start
    • Rust Quick Start

NeMo Relay CLI

  • About
  • Basic Usage
  • Claude Code
  • Codex
  • Cursor
  • Hermes Agent

Supported Integrations

  • About
  • OpenClaw Plugin Guide
  • LangChain Integration Guide
  • LangGraph Integration Guide
  • Deep Agents Integration Guide

Instrument Applications

  • About
  • Adding Scopes and Marks
  • Instrument a Tool Call
  • Instrument an LLM Call
  • Add Middleware
  • Code Examples

Observability Plugin

  • About
  • Configuration
  • Agent Trajectory Interchange Format (ATIF)
  • Agent Trajectory Observability Format (ATOF)
  • OpenTelemetry
  • OpenInference

Adaptive Plugin

  • About
  • Configuration
  • Adaptive Cache Governor (ACG)
  • Adaptive Hints

Integrate into Frameworks

  • About
  • Adding Scopes
  • Wrap Tool Calls
  • Wrap LLM Calls
  • Handle Non-Serializable Data
  • Using Codecs
  • Provider Codecs
  • Provider Response Codecs
  • Code Examples

Build Plugins

  • About
  • Define a Plugin
  • Validate Plugin Configuration
  • Plugin Configuration Files
  • Register Plugin Behavior
  • Design Plugin Configuration
  • NeMo Guardrails Example Plugin
  • Code Examples

Contribute

  • About
  • Development Setup
  • Workflow and Reviews
  • Testing and Documentation

Reference

  • APIs
    • Python
      • nemo_relay
        • nemo_relay._native
        • nemo_relay.adaptive
        • nemo_relay.codecs
        • nemo_relay.guardrails
        • nemo_relay.integrations
        • nemo_relay.intercepts
        • nemo_relay.llm
        • nemo_relay.observability
        • nemo_relay.plugin
        • nemo_relay.scope
        • nemo_relay.scope_local
        • nemo_relay.subscribers
        • nemo_relay.tools
        • nemo_relay.typed
        • nemo_relay.utils
    • Node.js
      • runtime
      • typed
      • plugin
      • adaptive
      • observability
    • Rust
      • nemo-relay
        • mod api
        • mod codec
        • mod config_editor
        • mod error
        • mod json
        • mod observability
        • mod plugin
        • mod plugins
        • mod stream
      • nemo-relay-adaptive
        • mod acg
        • mod acg_component
        • mod acg_learner
        • mod acg_profile
        • mod adaptive_hints_intercept
        • mod cache_diagnostics
        • mod config
        • mod context_helpers
        • mod drain
        • mod error
        • mod intercepts
        • mod learner
        • mod plugin_component
        • mod storage
        • mod subscriber
        • mod tool_parallelism_learner
        • mod trie
        • mod types
  • Performance

Troubleshooting

  • Troubleshooting Guide

Resources

  • Support and FAQs
  • Glossary
  • Community
  • Legal
    • Open Source Software (OSS)
    • License Agreement
  • Release Notes
  • Related Topics

Related Topics#

Use these links to continue into adjacent concepts and workflows.

  • Ecosystem

  • Support and FAQs

previous

Known Issues

next

Agent Runtime Primer
NVIDIA NVIDIA
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved..