Anthropic releases MHS standard for AI agents to safely control physical lab hardware
AnthropicAI · x · 2026-08-28
Anthropic has launched the research preview for the Model Hardware Standard (MHS), a shared specification for AI agents to safely operate physical devices.
Key Features & Value:
- Unified Interface: Enables agents to control multiple instruments like microscopes, liquid handlers, and robotic arms in parallel.
- Rapid Integration: Reduces hardware setup from weeks/months to hours or minutes.
- Autonomous Workflows: Supports round-the-clock autonomous experiments where agents reason through steps, update parameters in real-time, and recover from errors.
Technical Details:
- Works with any device having a programmable interface.
- Model-agnostic; accessible via standard protocols like the Model Context Protocol (MCP).
- Currently collaborating with select labs and manufacturers, with plans to open source the standard.
More from Embodied
- Ambi releases CARGO physical AI model with 72.5% stacking density — jfiance · 2026-08-28
- Anthrobotics discusses artificial muscles and product building — IanPritchard · 2026-08-28
- Microduck Open Sources Full RL Stack for Sim2Real Bipedal Robot — carlosdponx · 2026-08-28
- Shield AI aims for 10x performance, Hivemind flies on 30+ platforms — BrettKrieger12 · 2026-08-28
- Avride (ex-Yandex self-driving): 600k deliveries & 100k autonomous rides — demian_ai · 2026-08-28
- Tesla Optimus supply chain scaled for 70k units, silence signals commitment — JOBhakdi · 2026-08-28