Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/nvidia/nemo-relay/agents-mdgit clone --depth 1 https://github.com/NVIDIA/NeMo-RelayWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02587 | $0.02587 |
| Opus 5 | $0.01293 | $0.01293 |
| Sonnet 5 | $0.00517 | $0.00517 |
| Haiku 4.5 | $0.00259 | $0.00259 |
Grade A, and why
NeMo-Relay AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to agents, including Claude Code and OpenAI Codex, when working in this repository.
Project Overview
NeMo Relay is a multi-language agent runtime framework for execution scopes, lifecycle events, middleware, plugins, and observability around tool and LLM calls. The core runtime is Rust. Primary supported bindings are Rust, Python, and Node.js. Go and the raw C FFI are experimental and source-first.
The shared runtime model is:
- Scope stacks decide where work belongs and which scope-local behavior is visible.
- Middleware registries decide what guardrails and intercepts run around managed calls.
- Plugins install reusable runtime behavior from configuration.
- Events record runtime behavior in ATOF form.
- Subscribers and exporters consume events in-process or export them to ATIF, OpenTelemetry, OpenInference, or other backends.
Repository Structure
The repository layout separates the Rust runtime, language bindings, documentation, integrations, and agent-facing skills.
crates/
core/ # Rust core runtime crate, published as nemo-relay
adaptive/ # Adaptive runtime primitives and plugin components
python/ # PyO3 native extension for the Python package
ffi/ # Raw C ABI layer used by downstream bindings such as Go
node/ # NAPI Node.js binding and JavaScript/TypeScript entry points
python/
nemo_relay/ # Python wrapper package: scopes, tools, LLM, middleware, typed helpers, plugins, adaptive helpers
tests/ # Python tests
go/
nemo_relay/ # Experimental Go CGo binding and tests
fern/ # Fern documentation site
scripts/ # Stable wrappers and helper scripts; build/test/docs entry points live in justfile
skills/ # Published Codex/agent skills for NeMo Relay usage patterns
Prerequisites
Install the tools needed for the surfaces you touch. For a full repository validation environment, install all of these:
| Tool | Version / Notes | Required For |
|---|---|---|
| Rust | Docs minimum is 1.86 or newer; the repo pins the active toolchain in rust-toolchain.toml |
Rust core, native bindings, FFI |
| Python | 3.11 or newer | Python package, PyO3 builds, docs tooling |
| Node.js | 24 or newer, with npm | Node.js binding, generated API docs |
| Go | 1.21 or newer | Experimental Go binding |
uv |
Current project workflow tool | Python environments, docs dependencies, pre-commit |
just |
1.40 or newer | Canonical build, test, docs, package task runner |
cargo-deny |
Current stable | Rust dependency auditing |
cargo-about |
0.9.1 | Rust dependency attribution generation |
cargo-nextest |
0.9.111 or newer | CI-style Rust test runs |
cargo-llvm-cov |
0.8.5 or newer | CI-style coverage reports |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 223 lines · 2,587 tokens per session scan A aee4f1195b6b
NeMo-Relay AGENTS.md is an instructions file published in the GitHub repository NVIDIA/NeMo-Relay (132 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,587 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.