About NVIDIA NeMo Relay

Release Notes

View as Markdown

This page summarizes the current documentation-visible release state. GitHub Releases remain the source of truth for complete release history and tag-specific notes.

Current Release

NeMo Relay 0.4 focuses on host plugin installation, first-party PII redaction, local NeMo Guardrails execution, pricing-aware LLM response annotations, streaming raw ATOF export, remote ATIF storage, and stronger coding-agent trace fidelity.

The most important compatibility notes are:

  • The Python-only NeMo Guardrails example plugin has been removed. Use the built-in nemo_guardrails component for supported Guardrails integration.
  • Pricing estimates require configured pricing sources. NeMo Relay does not ship provider price data by default.
  • Local NeMo Guardrails mode depends on Python 3.11 or newer and an available nemoguardrails runtime.
  • Node.js 24 or newer remains the minimum supported Node.js version.
  • Native subscriber delivery remains asynchronous. Code that depends on subscriber callback side effects, exporter output, or deterministic test assertions must call the subscriber flush API.

Use the child pages for release highlights and support notes. For the complete PR-by-PR changelog, release artifacts, and tag-specific history, use GitHub Releases.

Release Scope

This release includes:

  • Built-in NeMo Guardrails plugin support, including remote and local Python-backed backends.
  • CLI installation, uninstallation, and doctor flows for Claude Code and Codex host plugins.
  • Code-driven plugin configuration layered over materialized global, project, and user plugin files.
  • First-party PII redaction plugin helpers across Rust, Python, Node.js, and WebAssembly surfaces.
  • Model-pricing catalogs and LLM cost annotations that propagate into ATIF, OpenInference, and OpenTelemetry output.
  • ATOF streaming endpoints for HTTP POST, WebSocket, and NDJSON collectors.
  • ATIF remote storage support for HTTP endpoints in addition to S3-compatible storage.
  • Trace fidelity fixes for Hermes, OpenClaw, LangChain, LangGraph, and Deep Agents integrations.

Feature Documentation

For the major 0.4 additions, start with: