Google Home is set to expand beyond its own Gemini AI, with the company confirming that additional AI agents will soon be able to control smart home devices. Google told customers and developers that any agent supporting Model Context Protocol tools can now interact with all of the devices and event history within the Google Home ecosystem.
The announcement specifically names Anthropic’s Claude, the open-source AI agents OpenClaw and Hermes, and the Google Antigravity coding platform as options that will soon work with Google Home. Previously, Google offered a version of its AI called Gemini for Home to act as a voice assistant and controller for smart devices connected through the Google Home app, including smart lights, heaters, home security cameras and thermostats.
How the New AI Integration Works
Using Model Context Protocol technology, which previously helped users add agents to Google Workspace, Google will begin rolling out support for other AIs in Google Home. This means users could rely on the voice mode within their Claude AI agent to control a thermostat, for example, set up automations, or tap into data that Gemini for Home may not provide on its own.
Google says the AIs will be able to perform more complex Google Home tasks, such as compiling security camera text summaries of what cameras have observed. The platform will also support personalised dashboards for home control, offering an alternative to the standard Google Home interface.
Availability and Access Requirements
The capability has begun rolling out, but for now it is limited to Google Home Premium Advanced users in the US. Access requires a subscription of roughly £16 per month. The feature is offered as early access, meaning it may be prone to bugs or carry limitations at this stage. Google is encouraging users to report feedback to its smart home developers’ help channel.
Opening the platform to third-party agents such as Claude, OpenClaw and Hermes could allow users to configure more advanced automations, for instance tying thermostat actions to specific local weather conditions. The versatility of these agents introduces a broader range of possible home control setups beyond what a single assistant offers.
Gemini for Home has faced criticism for not always understanding complex commands as intended, or failing to operate devices that are connected and ready. The addition of alternative AI agents provides users with options that may address some of these gaps, alongside the possibility of building customised control centres rather than relying solely on the built-in interface.
The expanded AI support is rolling out from Wednesday to Google Home Premium Advanced subscribers in the US.
