
Teams running coding agents hit the same wall. Claude Code speaks the Anthropic Messages API, Codex CLI speaks OpenAI, and the model a team actually wants to serve sits behind vLLM, NVIDIA NIM, or Ollama. Rewriting the agent is not an option, so the translation layer has to live somewhere else. Switchyard is NVIDIA’s answer: a Rust proxy and library for LLM traffic that routes requests across providers, translates between OpenAI and Anthropic formats, records operational metrics, and e
Will NVIDIA's Switchyard proxy appear on GitHub within 7 days?
Resolves by Sep 10, 2026
Switchyard is a Rust proxy and library that routes requests across different large language model APIs, translating between OpenAI and Anthropic formats so clients can use their native API regardless of which backend processes the request. Teams using coding agents face the problem that different agents speak different API languages while the actual model they want to use sits behind a different service entirely, and Switchyard solves this by decoding inbound requests into provider-neutral types, selecting a backend through a routing algorithm, and re-encoding the response in the format the client expects. The tool supports four routing strategies: passthrough to a single target, random distribution across targets, LLM-classifier routing based on capability verdicts, and stage-router selection based on agent signals. Switchyard is currently pre-alpha and experimental, released under Apache 2.0 for evaluation only, with NVIDIA explicitly warning it is not suitable for production use.

While restaurant owners might look to generative AI as a shortcut to sprucing up their menu, customers can viscerally sense that something is wrong with the food.
.gif&s=kx7H9a1S3ZIMP7WHNPT2XBlIq6uwDsVvpMZbLf-dnSA)
ChatGPT, Claude, and Grok all suffered outages at nearly the exact same time for reasons that remain murky.

Most teams building a shopping assistant or agent rebuild the same scaffolding: an agent loop, a tool layer over the catalog, an approval gate, and an eval suite. Anthropic has now released that scaffolding as code. This week, they published anthropics/commerce-agents, a reference blueprint containing a shopping agent and a merchant agent, along with four runnable verticals: retail, travel, telecom and entertainment. It ships alongside two write-ups: a product announcement and an engineering de
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven