Switchyard is a model-routing library and proxy that chooses which language model should handle each LLM request, based on factors such as cost and task suitability. It is for developers running LLM applications who want to route calls through existing gateways, custom harnesses, or a standalone proxy while retaining OpenAI and Anthropic client compatibility. The catalogue add-ons are workflows for operating or integrating Switchyard with coding agents and gateways.
Borrowing it
Nothing to install: this file belongs to NVIDIA-NeMo/Switchyard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/NVIDIA-NeMo/Switchyard/main/AGENTS.mdgit clone --depth 1 https://github.com/NVIDIA-NeMo/SwitchyardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/nvidia-nemo/switchyard/agents-md)<a href="https://agentmods.dev/instructions/nvidia-nemo/switchyard/agents-md"><img src="https://agentmods.dev/badge/instructions/nvidia-nemo/switchyard/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/nvidia-nemo/switchyard/agents-md"><img src="https://agentmods.dev/badge/instructions/nvidia-nemo/switchyard/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00841 | $0.00841 |
| Opus 5.5 | $0.00336 | $0.00336 |
| Sonnet 5.5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
Switchyard 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switchyard is an LLM router library. It sits between an agent's request (e.g. Claude Code, Codex CLI) and an inference server, selecting the best model for that request.
It is written in Rust with Python bindings.
Core components in crates/. These are layered:
libsy: The core library and routing algorithms. This is the heart of Switchyard. Main entry point isAlgorithm::run_streammethod.libsy-llm-client: HTTP client that makes requests forlibsyalgorithms, and drivesrun_stream. Main entry point isrunfunction inrun.rs.switchyard-runner: Parsing TOML configuration, useslibsy-llm-clientto run until the algorithm resolves to the selected model. The entry point isRunnerstruct.switchyard-server: A thin HTTP demo server wrapped aroundswitchyard-runner. Has a TOML config file.switchyard-py: Python bindings forlibsyandlibsy-llm-client.
Support components (also in crates/):
protocol: Types shared between many components.switchyard-translation: Convert between various JSON inference formats: OpenAI Chat Completions, OpenAI Responses and Anthropic Messages. We convert to/from a vendor neutral independent representation (IR). All the core components with with this IR.
Integrations:
crates/switchyard-nemo-relay-plugin/: Integrate with NeMo Relay.examples/litellm/: Integrate with LiteLLM.
Writing guidance
- Write for a high-school level in short, simple sentences.
- Avoid jargon, analogies and metaphors. Be direct.
- Only say what something is not if it is essential to understanding. Never use negatives or opposites as a rhetorical flourish.
- Be humble. Do not inflate claims.
- Do not say what you would do unless asked.
Official documentation
- Publish documentation about using, integrating, configuring, and understanding Switchyard's product and software.
- Keep repository CI, documentation publishing, release procedures, and maintainer or agent workflows in contributor documentation or excluded internal docs, not in the official product documentation.
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.
- yesterday Changed · +5 lines · +55 tokens per session 5367659479aa
- 20d ago Changed · +6 lines · +51 tokens per session 2c84596407b1
- 1mo ago Changed · -212 lines · -1,901 tokens per session 3511201accb8
- 1mo ago First seen · 269 lines · 2,636 tokens per session scan A be9feb1dc582
Switchyard AGENTS.md is an instructions file published in the GitHub repository NVIDIA-NeMo/Switchyard (3,458 stars, last pushed today), licensed Apache-2.0. It adds 841 tokens to every session, about $0.0034 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.