Get Started With NeMo Relay
OfficialFreeQuickly evaluate NeMo Relay with minimal setup.
Free · Opens the source repo
What Get Started With NeMo Relay does
The Get Started With NeMo Relay skill is designed to assist first-time users in evaluating the NeMo Relay framework without the complexities of a full production deployment. This skill focuses on guiding users through a streamlined process to achieve observable success with the least complicated trial option available. By emphasizing a single, clear path to value, it helps users quickly understand the capabilities of NeMo Relay in their specific environment.
Users can choose from three distinct try-now paths based on their existing setup and goals. The default option is the CLI try-now, ideal for those who want to experience Relay without altering their application code. Alternatively, if users are working within a framework like LangChain or Deep Agents, the built-in integrations path is recommended. For those who have direct control over their application code in Python, Node.js, or Rust, the manual language path is the best fit. This flexibility ensures that users can find the quickest route to verifying Relay's functionality.
Once a path is selected, the skill guides users through the installation process without unnecessary repetition or confusion. It emphasizes the importance of confirming the environment's configuration and obtaining user approval before making any changes. This structured approach not only simplifies the initial setup but also lays the groundwork for further exploration of NeMo Relay's capabilities, such as plugin integration for enhanced functionality.
The skill is particularly valuable for developers and designers looking to quickly assess the potential of NeMo Relay in their projects. By following the suggested paths and steps, users can gain immediate insights into Relay's performance and how it can fit into their workflows, making it an essential tool for anyone new to the framework.
When to use it
Use this skill when you want to quickly evaluate NeMo Relay without diving into a full production setup.
When not to use it
This skill is not suitable for advanced users who require in-depth configuration or production-level deployment.
What you can build with it
First-Time Evaluation
A developer new to NeMo Relay uses the CLI try-now path to quickly assess its capabilities without modifying existing code.
Integration with Existing Frameworks
A user with a LangChain application opts for the built-in integrations path to evaluate how NeMo Relay can enhance their current setup.
Direct Language Testing
A programmer working in Python chooses the manual language path to directly integrate NeMo Relay into their application code.
How to install Get Started With NeMo Relay
View source1. Install with the skills CLI
npx skills add nvidia/skills/nemo-relay-get-started --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by nvidiaGet Started With NeMo Relay
Guide a new user to visible Relay value with the least complicated applicable trial. Do not begin with production deployment or Relay's full architecture. Keep the first run focused on one observable success path.
Choose A Try-Now Path
Evaluate these paths in order. Use the first one that fits the user's stated goal and existing environment.
- CLI try-now (default): choose this for a generic "try Relay" request or when the user wants value without modifying application code. Run Codex, Claude Code, or Hermes through the local CLI wrapper. Read CLI Try-Now.
- Built-in integrations try-now: choose this when an existing LangChain, LangGraph, Deep Agents, or OpenClaw application owns the execution boundary. Prefer the maintained supported integration over manual wrapping. Read Built-In Integrations Try-Now.
- Language-specific manual try-now: choose this when the user's Python, Node.js, or Rust application directly owns its tool or LLM call sites and no maintained integration is the better boundary. Read Manual Language Try-Now.
Do not ask the user to choose among all three when their request, manifest, or framework already identifies the boundary. For an unspecified request, use the CLI path. When more than one CLI agent is available, ask one concise question to select the agent.
Resolve Installation Without Looping
Select the try-now path before choosing an install package.
- CLI path -> verify
nemo-relay --version; if missing, usenemo-relay-installfor the CLI outcome. - Built-in integration path -> use
nemo-relay-installfor the named framework or harness package. - Manual language path -> use
nemo-relay-installfor the detected language package.
If installation already succeeded, preserve the chosen path and continue from its next step. Do not ask the install-path question again or bounce between the install and get-started skills.
Apply The Common First-Value Contract
Follow the selected reference, then:
- Inspect the target environment and existing Relay configuration before proposing changes.
- Explain the attachment boundary and show the exact minimal change.
- Obtain confirmation before writing configuration, modifying application code, or launching a model-consuming run.
- Use a non-sensitive, read-only trial and exercise one representative tool and LLM path when the selected surface exposes both.
- Verify observable evidence from the selected path rather than treating a successful application result as proof that Relay is active.
- Summarize the captured root, tool, and model relationships without dumping prompts, credentials, or complete event payloads.
Explain only the concepts visible in the result: the chosen attachment boundary, scopes and parentage, captured lifecycle events, and how subscribers or the Observability plugin make those events inspectable. Keep instrumentation and export distinct.
Continue With One Plugin
Stop the initial try-now workflow when the selected path's success checks pass. Then make one additional built-in plugin the primary suggested next step.
Explain Relay's core progression: instrument an execution boundary once, then change or extend behavior through plugin configuration without repeatedly rewriting those call sites. Easy plugin configuration and reconfiguration is the main value to demonstrate after the first observable proof.
If the selected path did not use plugin-managed Observability, add it first to establish the reusable plugin path. If Observability already produced the proof, ask what outcome matters next and recommend exactly one plugin:
- Adaptive -> adaptive runtime behavior and optimization
- NeMo Guardrails -> policy checks around managed execution
- PII Redaction -> sanitization of sensitive observability payloads
- Model Pricing -> cost estimates for managed LLM responses
Use the plugin overview to select the next component. Preview its smallest configuration, obtain confirmation, and verify its behavior before layering in another plugin.
Use another handoff only after the user accepts or declines plugin progression, or when the demonstrated boundary does not yet cover the intended workflow:
- Direct application expansion ->
nemo-relay-instrument-calls - Additional exporters or durable observability configuration ->
nemo-relay-plugin-observability - A different package or supported integration ->
nemo-relay-install - Persistent Claude Code or Codex loading ->
nemo-relay-install; for Codex Desktop, complete its recovery-note safety gate before changing global config - Missing hooks, gateway traffic, or events ->
nemo-relay doctor,nemo-relay doctor --json, ornemo-relay-debug-runtime-integration
Do not configure production OTLP backends, model pricing, guardrails, adaptive tuning, custom plugins, Go or FFI examples during the quick start. Mention optional plugins only after the initial proof and add only the one the user selects.
Public Entry Points
Use these public entry points for current product documentation:
Frequently asked questions about Get Started With NeMo Relay
Similar skills
WinMD API Search
Easily find and explore Windows desktop APIs.
WebMCPify
Transform any web app into an agent-ready platform.
Phoenix Tracing
Instrument LLM applications with OpenInference tracing.
Foundry Hosted Agent CopilotKit
Guidance for developing agentic web apps on Azure.
Power Automate Foundation
Connect AI agents to Power Automate seamlessly.
Power Automate Flow Builder
Efficiently build and deploy Power Automate flows programmatically.