Anthropic has introduced the Model Hardware Standard (MHS), a new framework designed to allow artificial intelligence agents to operate physical devices. This initiative marks Anthropic's entry into the realm of "physical AI," aiming to bridge the gap between advanced large language models (LLMs) and hardware used in scientific research and advanced manufacturing.
The MHS framework is intended to enable AI agents to control laboratory and manufacturing equipment, such as microscopes and robotic arms, facilitating complex tasks and autonomous workflows. Anthropic stated that the MHS can help researchers and engineers execute tasks around the clock with minimal human intervention, thereby accelerating processes. The standard is designed to work with any device that has a programmable interface, allowing for cross-network communication between devices and agents.
Anthropic is currently sharing an early version of the MHS with partners to aid in developing safety evaluations before its planned open-source release. The company highlighted that integrating AI into equipment using MHS can take hours or minutes, a significant reduction compared to the weeks or months typically required for custom builds. The MHS is model-agnostic, meaning it is compatible with various LLMs, including those from other companies and open-source models. It is built upon Anthropic's Model Context Protocol (MCP), an open standard for connecting data sources.
To address potential limitations with existing equipment lacking programming interfaces, Anthropic is collaborating with device manufacturers to integrate MHS into new products and add connections to existing ones. This effort aims to prevent vendor lock-in for scientists and provide a standardized, easily programmable interface. The development of MHS involved partnerships with entities like HHMI Janelia Research Campus, Genentech, Carnegie Mellon University, QuEra, Universal Robots, Amazon Web Services, Doosan Robotics, and Danaher.
Separately, Anthropic has also released an open-source reference project called Claude Desktop Buddy, which allows ESP32-S3-based devices to connect directly to the Claude desktop app via Bluetooth Low Energy (BLE). This feature enables physical desk companions to provide real-time updates on AI agent activity and allows users to respond to permission requests directly from the device, enhancing interaction speed and privacy.
