Nvidia dropped switchyard on sep 2 — apache-2.0 rust proxy that decodes llm requests into…
nvidia dropped switchyard on sep 2 — apache-2.0 rust proxy that decodes llm requests into provider-neutral types, then routes them with passthrough, random, or llm-classifier. stack it next to cursor self-hosted machines and coder agent relay and the routing layer quietly became its own product category this month.
none of the model labs are the ones building it.
Context
The NVIDIA-NeMo/Switchyard repository is Apache 2.0 and was created on 19 May 2026. Its docs say it routes LLM requests through provider-neutral Rust types and exposes the result through OpenAI- and Anthropic-compatible APIs, as a standalone server or a Rust library. MarkTechPost has a 2 September 2026 article on its release, seen as a snippet. Cursor's self-hosted machines post is dated 2 September 2026.
The exact release date of 2 September has no first-party dated page; support is a secondary dated URL only, and the repository existed since 19 May. The names passthrough, random and llm-classifier were not individually confirmed. Coder's Agent Relay is about cloud-hosted agents with self-hosted execution, not LLM-request routing, so grouping it under a routing layer is the author's framing. None of the model labs are building it is unsupported, since Cursor and Coder are tied to model-adjacent companies in the same week. Routing becoming a product category is the author's opinion.
Related work
- Switchyard docs ↗First-party.
- Cursor self-hosted machines (2 Sep 2026) ↗First-party.
- Coder Agent Relay ↗Snippet only.
Watch next
- A first-party NVIDIA dated announcement.
Sources
- NVIDIA-NeMo/Switchyard (GitHub)github.com
- Switchyard core conceptsnvidia-nemo.github.io
- NVIDIA releases Switchyard (MarkTechPost, 2 Sep 2026)marktechpost.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 7 September 2026 at 03:01 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →