Anthropic has opened a research preview of the Model Hardware Standard (MHS), a shared specification designed to let AI agents control physical laboratory and manufacturing equipment. The standard enables simultaneous operation of devices such as microscopes, liquid handlers and robotic arms, reducing hardware integration time from weeks or months to hours or minutes.
The MHS uses a standardized driver to translate between a computer's operating system and connected hardware via simple commands, making each device discoverable in a standard format for cross-network communication without custom integration programs. The system is model-agnostic and works with any device featuring a programmable interface, allowing agent harnesses to access it using standard protocols such as the Model Context Protocol.
Anthropic developed MHS in collaboration with the Howard Hughes Medical Institute's Janelia Research Campus. The company has secured support from Amazon Web Services (AWS), which will integrate MHS into its Strands Robots library for connecting AI agents to physical devices. Tecan will add MHS support to its Fluent liquid handling platforms, while Universal Robots plans to integrate the standard into its robotics platform.
Automata will incorporate MHS into its LINQ lab automation platform, and Danaher is exploring how the standard could enable smart instruments and scalable autonomous laboratories for biomedical research. Doosan Robotics is testing MHS with robotic arms for automated quality assurance, and QIAGEN is experimenting with the standard on its QIAsymphony Connect nucleic acid purification platform.
During the research preview period, Anthropic will work with launch partners to build safety evaluations and develop protections for AI use with physical equipment. The company intends to open-source the standard after the preview and publish findings as part of its safe deployment guidance. Stakeholders across industries are invited to join the waitlist for the research preview.
