NeMo Relay Integration

NeMo Relay Integration is an AI Engineering skill for Claude Code, published by NVIDIA in NeMo-Relay.

165 stars67 forkson NVIDIA/NeMo-RelayAdded 2026/09/08+23% in starsRepository updated 2026/09/07

agentsaiatifatofclaude-codecodexdeepagentshermes-agentlangchainlanggraphmiddlewarenvidiaobservabilityopenclawopeninferenceoptimizationotelruntimesecurity

Install in seconds

Install NeMo Relay Integration

Copy NeMo Relay Integration into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/NVIDIA/NeMo-Relay/tree/main/skills/nemo-relay-integrate-upstream ~/.claude/skills/nemo-relay-integrate-upstream

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/NVIDIA/NeMo-Relay.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/nemo-relay-integrate-upstream/SKILL.md in NVIDIA/NeMo-Relay
Installs to: ~/.claude/skills/nemo-relay-integrate-upstream
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 3670 skills

What NeMo Relay Integration does

NeMo Relay Integration helps assess, implement, or qualify Relay support in an agent harness or framework. It maps host boundaries to Relay attachment methods and verifies coverage for tools, model calls, subagents, and lifecycle events.

NeMo Relay Integration is cataloged under AI Engineering on DirSkills. NeMo Relay Integration comes from a repository tagged agents, ai, atif, atof and claude-code.

Documentation

README

Excerpt

Integrate Relay Into An Agent Harness

Use this skill to determine the right NeMo Relay integration for an agent framework or harness that lacks support or needs deeper coverage. First identify how the host runs tools, model calls, streams, subagents, and lifecycle events and what its extension points can control. Then choose the integration depth and Relay attachment methods that meet the required coverage and fit the host's architecture, support model, and lifecycle, using an extension, separate adapter, core wiring, or hybrid as appropriate.

Choose The Work Mode

Choose one mode from the user's request. Do not silently move from assessment to implementation.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about NeMo Relay Integration

What else does NVIDIA publish alongside NeMo Relay Integration?
NeMo Relay Integration is one of 25 skills that DirSkills catalogs from NVIDIA/NeMo-Relay, the repository it ships in. Its siblings there include Adaptive Tuning, Add Binding Feature and Add Middleware. Each one is a separate skill with its own page in this directory, installs the same way NeMo Relay Integration does, and is maintained by NVIDIA in that same repository. The rest of the collection is listed on the NVIDIA/NeMo-Relay page.
How does NeMo Relay Integration compare to other AI Engineering skills?
NeMo Relay Integration ranks #3368 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of NeMo Relay Integration against them. Open each page to compare what they document and how they install.