Previewing the Model Hardware Standard

模型硬件标准（MHS）预览

We’re opening a research preview of the Model Hardware Standard (MHS), a shared specification for AI agents to safely operate physical devices, to a first group of scientific research labs and advanced manufacturers. MHS enables AI agents to operate multiple lab and manufacturing instruments, such as microscopes, liquid handlers, and robotic arms, in parallel, and perform intricate tasks ranging from routine drug discovery experiments to laser calibration on a quantum computer. The development of MHS began as a collaboration between Anthropic and HHMI Janelia Research Campus.

我们正在向首批科学研究实验室和先进制造企业开放“模型硬件标准”（Model Hardware Standard，简称 MHS）的研究预览。这是一项旨在让 AI 智能体能够安全操作物理设备的共享规范。MHS 使 AI 智能体能够并行操作多种实验室和制造仪器（如显微镜、液体处理工作站和机械臂），并执行从常规药物发现实验到量子计算机激光校准等各种复杂任务。MHS 的开发始于 Anthropic 与 HHMI Janelia 研究园区的合作。

It typically takes a lab or manufacturing facility weeks, if not months, to set up and integrate their hardware. Most devices don’t communicate with each other, instead requiring specialists to build bespoke integrations. MHS reduces this integration work to hours or minutes. And by incorporating AI into these tools, MHS also helps researchers and engineers more readily orchestrate autonomous, round-the-clock experiments and workflows, with agents able to reason through each step in an experiment, update parameters in real time, and, in some cases, recover from hardware errors without intervention.

通常情况下，实验室或制造工厂需要数周甚至数月的时间来设置和集成其硬件。大多数设备之间无法直接通信，需要专家构建定制化的集成方案。MHS 将这一集成工作缩短至数小时甚至数分钟。通过将 AI 融入这些工具，MHS 还帮助研究人员和工程师更轻松地编排自主的、全天候的实验和工作流程。智能体能够对实验的每一步进行推理、实时更新参数，并在某些情况下无需人工干预即可从硬件错误中恢复。

We’re sharing an early version of MHS with partners across science, robotics, electronics, and manufacturing so we can collaborate to build safety evaluations and develop best practices for AI systems operating physical equipment, ahead of making the standard open source. MHS works with any device that has a programmable interface. It is also model-agnostic, and any agent harness can access it using standard protocols, such as the Model Context Protocol. To apply for access to the research preview, head here.

我们正在与科学、机器人、电子和制造领域的合作伙伴分享 MHS 的早期版本，以便在将该标准开源之前，共同构建安全评估体系并制定 AI 系统操作物理设备的最佳实践。MHS 适用于任何具有可编程接口的设备。它与模型无关，任何智能体框架都可以使用标准协议（如模型上下文协议 MCP）对其进行访问。如需申请研究预览权限，请点击此处。

How MHS works

MHS 的工作原理

Getting multiple devices in a lab or on a factory floor to communicate with one another can be challenging, even setting aside the added difficulty of integrating AI into the setup. Each device tends to have its own programming interface, and so far there has been no standardized way to integrate them. And once the devices are connected, there is no common way for them to share data with an AI agent, nor to let the agent operate them safely. MHS addresses these challenges by introducing a standardized driver: software that translates between a computer’s operating system and a hardware device. The MHS driver uses a simple set of primitives—commands like “read” (for example, “get temperature”) or “write” (for example, “set temperature”)—that any hardware device can understand and act on. And it makes each device discoverable in a standard format, so that devices and agents can find each other and communicate across networks without needing a bespoke “translator” program in between.

在实验室或工厂车间让多台设备相互通信极具挑战性，更不用说将 AI 集成到其中的额外难度了。每台设备往往都有自己的编程接口，目前还没有标准化的集成方式。即使设备连接起来，也没有通用的方法让它们与 AI 智能体共享数据，或让智能体安全地操作它们。MHS 通过引入标准化驱动程序解决了这些挑战：这是一种在计算机操作系统和硬件设备之间进行转换的软件。MHS 驱动程序使用一组简单的原语——例如“读取”（如“获取温度”）或“写入”（如“设置温度”）等指令——任何硬件设备都能理解并执行这些指令。它还以标准格式使每台设备可被发现，从而使设备和智能体能够在无需中间定制“翻译”程序的情况下，跨网络相互发现并进行通信。

The MHS driver also helps an AI agent understand how to use a device it has never seen before, giving it information about machine characteristics that may not be discernable from code alone (for example, the weight of a robot arm, which is important for knowing how to manipulate it safely). To date, much of this information has been stored in paper manuals, on a user’s computer, or as tacit knowledge. But the MHS driver contains tags that let the user write this information directly in natural language (users can either do this themselves, or by chatting to an agent that interviews them about their hardware setup). With the information from these tags, the MHS driver then automatically produces a reference file with information about a device’s general characteristics, such as what it can measure, what can be adjusted, and what safety limits will be enforced. This file gives the agent everything it needs to know to operate the device.

MHS 驱动程序还帮助 AI 智能体理解如何使用从未见过的设备，为其提供仅凭代码无法识别的机器特性信息（例如机械臂的重量，这对于了解如何安全操作它至关重要）。迄今为止，这些信息大多存储在纸质手册、用户电脑中，或作为隐性知识存在。但 MHS 驱动程序包含标签，允许用户直接用自然语言编写这些信息（用户可以自己编写，也可以通过与智能体聊天，由智能体询问其硬件设置来完成）。利用这些标签中的信息，MHS 驱动程序会自动生成一份参考文件，其中包含有关设备一般特性的信息，例如它可以测量什么、可以调整什么以及将执行哪些安全限制。该文件为智能体提供了操作设备所需的一切信息。

After the devices are connected and the agent knows how to use each one, the agent needs a way to control the hardware. For MHS, there are three such mechanisms: MCP, the command line interface, and code files (APIs). These work together to enable orchestration across multiple devices via a single line of code. Once the agent can control the devices, it’s able to receive operating data from each one and supervise and direct the work at a high level. The agent can sequence steps across instruments, monitor results, and adjust parameters as conditions change in real time. When the agent needs to execute long-running tasks or operate devices faster than its online reasoning would allow, it can chain together driver commands from one or more devices in code files. This allows the devices to carry out operations themselves, without the agent needing to reason at every step.

在设备连接且智能体了解如何使用每台设备后，智能体还需要一种控制硬件的方法。对于 MHS，有三种机制：MCP、命令行界面和代码文件（API）。它们协同工作，通过一行代码即可实现跨多台设备的编排。一旦智能体能够控制设备，它就能从每台设备接收运行数据，并在高层级上监督和指导工作。智能体可以对跨仪器的步骤进行排序、监控结果，并根据实时变化的情况调整参数。当智能体需要执行长时间运行的任务或以超过其在线推理速度的操作设备时，它可以在代码文件中将来自一个或多个设备的驱动程序命令链接在一起。这使得设备能够自行执行操作，而无需智能体在每一步都进行推理。

As we’ve tested MHS, we’ve found that Claude interacts with experiments and hardware in an exploratory manner, much as a scientist would. For example, we observed Claude make an adjustment to a laser, observe the results through a camera to assess how its adjustment moved the laser beam, and repeat the process, seeking to understand the sequence of events. Claude then packaged what it learned into code files, writing a deterministic script that let it align the laser without having to reason at each step, so the whole process could run as a single command.

在测试 MHS 的过程中，我们发现 Claude 以一种探索性的方式与实验和硬件进行交互，就像科学家一样。例如，我们观察到 Claude 对激光器进行调整，通过摄像头观察结果以评估调整如何移动了激光束，并重复这一过程，试图理解事件的顺序。随后，Claude 将其所学内容打包成代码文件，编写了一个确定性脚本，使其无需在每一步都进行推理即可对准激光，从而使整个过程可以作为单个命令运行。

Early examples from MHS

MHS 的早期案例

We are only just beginning to see what people can do with frontier models and MHS, but our hope is that the standard can be of use to researchers, engineers, and other practitioners in speeding up the process of discovery and experimentation in any domain that uses devices with a programmable interface.

我们才刚刚开始看到人们利用前沿模型和 MHS 能做些什么，但我们希望该标准能够帮助研究人员、工程师和其他从业者，在任何使用具有可编程接口设备的领域中，加速发现和实验的过程。

As we developed MHS, we shared it with a handful of labs and hardware manufacturers in biotech, robotics, quantum computing, and other fields. Across these early projects, we saw MHS reduce the time it took to integrate devices, make it possible to iterate faster in a variety of experimental settings, and assist with the live operation of machines and real-time fault detection. Below, our partners share the details of some of their…

在开发 MHS 的过程中，我们将其分享给了生物技术、机器人、量子计算等领域的少数实验室和硬件制造商。在这些早期项目中，我们看到 MHS 缩短了集成设备所需的时间，使在各种实验环境中更快地进行迭代成为可能，并协助了机器的实时操作和故障检测。以下是我们的合作伙伴分享的部分详细信息……