NVIDIA-NeMo/Switchyard

Switchyard lets LLM applications route traffic across models and providers while preserving native OpenAI and Anthropic API compatibility - enabling flexible model selection, benchmarking, and cost/performance optimization.

Language modelsPython

3.1 Breakout Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

Open on Seismograph Open on GitHub

About the project

An LLM request router that picks the cheapest model capable of handling each call while preserving OpenAI and Anthropic API compatibility. Runs as a NeMo Relay or LiteLLM plugin, an embeddable library, or a standalone proxy.

Useful for

Attach a routes.toml to an existing LiteLLM Router to cut token costs
Run the standalone proxy and point Claude Code or Codex CLI at it without code changes
Embed the routing algorithm into your own gateway via pip install nemo-switchyard

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

50 stars today.
Over the last two days the pace is 2.7× that of the previous week and a half.
Recent forks include notable developers: @zapabob (258 followers).

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 3,032
Stars in a day: 51
Forks: 267
Issues and pull requests: 682
Watchers: 10
Language: Python
License: Apache-2.0
Latest release: v0.2.0 · August 10, 2026
Created: May 19, 2026
Last push: September 13, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

September 13, 2026GitHub Trending this month: #21, +2,319 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/NVIDIA-NeMo/Switchyard.svg?lang=en)](https://gitnova.dev/en/r/NVIDIA-NeMo/Switchyard)

Similar projects

6.1
JustVugg/colibri
A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.

BreakoutLanguage modelsC+1,048 stars in a day
5.7
asgeirtj/system_prompts_leaks
A collection of extracted system prompts from Anthropic, OpenAI, Google, xAI and others — the hidden instructions chatbots receive before a user's first message.

BreakoutLanguage modelsJavaScript+428 stars in a day
5.1
kennethwolters/litelm
A lightweight litellm alternative: routes LLM calls across 19 providers and translates message formats in ~2,900 lines with two dependencies, without proxy, caching, or cost tracking.

Early signalLanguage modelsPython+9 stars in a day
5.0
MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
A local EXL3 2.9 bpw checkpoint of DeepSeek-V4.1-Flash (196 GiB, 39 shards) served via an OpenAI-compatible vLLM API on a 2x NVIDIA GB10 (DGX Spark) kit with tensor-parallel 2. Includes DSpark speculative decoding and…

Early signalLanguage modelsPython+81 stars in a day
4.8
unclecode/crawl4ai
Open-source web crawler and scraper that turns pages into clean, LLM-ready Markdown for RAG, agents and data pipelines. Runs via Python API, CLI and Docker with no API keys.

BreakoutLanguage modelsPython+411 stars in a day
4.5
Edge0-AI/Edge0
An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run…

CoolingLanguage modelsPython+118 stars in a day