Anthropic unveils new framework allowing AI agents to operate physical devices

Anthropic introduced a new framework on Thursday called the Model Hardware Standard (MHS), designed to enable AI agents to operate physical devices in scientific research and advanced manufacturing settings. This framework allows AI agents to interact with lab and manufacturing instruments, such as microscopes and robotic arms, to carry out complex tasks ranging from drug discovery experiments to laser calibration on a quantum computer.

By merging agentic AI capabilities with lab and manufacturing hardware, Anthropic aims to enable researchers and engineers to execute autonomous, round-the-clock workflows with minimal human intervention, thereby speeding up processes. The MHS framework is compatible with any device that has a programmable interface, allowing devices and AI agents to communicate across networks.

Anthropic has shared an early version of the MHS with partners to facilitate the development of safety evaluations before making it open source.