What is the Model Hardware Standard (MHS)?

MHS is a framework for connecting large language models like Claude to physical objects, such as manufacturing equipment or microscopes. It uses a set of commands like 'read' that any hardware device can understand.

How is MHS different from previous approaches?

MHS allows companies to integrate AI into equipment in hours or minutes, whereas the typical process takes weeks or months and requires specialists for custom builds.

Does MHS work with models other than Claude?

Yes, MHS is model-agnostic, meaning it works with any LLM, including those from other companies like OpenAI or open-source models.

RoboticsAI Business & IndustryFortune AIAug 27, 2026Aug 28, 2026, 04:00 JST

Anthropic launches first physical AI standard, MHS

Send on LINE

3 Key Points

What happened
Anthropic released its Model Hardware Standard (MHS), a framework to connect AI models like Claude to physical equipment, as a research preview on Thursday.
Why it matters
With MHS, companies can integrate AI into equipment in hours or minutes instead of weeks or months, enabling round-the-clock experiments and workflows. It is model-agnostic, working with any LLM, and built on the company's 2024 open standard, MCP.
What to watch
Anthropic is working with device manufacturers to build new products with the necessary interface and add MHS to existing ones. Partners include Genentech, Carnegie Mellon, QuEra, and Universal Robots, with early access given to a handful of labs and manufacturers.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

The release of MHS marks Anthropic's entry into physical AI, a field combining AI with robotics and hardware. The framework builds on the Model Context Protocol (MCP), which Anthropic debuted in 2024 as a universal standard for connecting data sources, described as 'the USB for AI to software connection.' This move positions MHS as a potential industry standard, reducing reliance on proprietary solutions that often hinder scientific equipment. Anthropic's partnerships with device manufacturers and early access for labs suggest a push toward making AI integration as simple as plugging in a device. The timing aligns with growing interest in AI-robotics integration, as seen with Hugging Face's robotic duck debut and Nvidia's acquisitions, though MHS operates independently of these efforts.

FAQ

What is the Model Hardware Standard (MHS)?: MHS is a framework for connecting large language models like Claude to physical objects, such as manufacturing equipment or microscopes. It uses a set of commands like 'read' that any hardware device can understand.
How is MHS different from previous approaches?: MHS allows companies to integrate AI into equipment in hours or minutes, whereas the typical process takes weeks or months and requires specialists for custom builds.
Does MHS work with models other than Claude?: Yes, MHS is model-agnostic, meaning it works with any LLM, including those from other companies like OpenAI or open-source models.

Fortune AIRead Original Article

Send on LINE

Also reported by THE DECODER, Top Companies AI

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.