Google is launching its own version of OpenClaw
Google is launching its own take on OpenClaw, the buzzy AI agent platform that caused a stir in the tech industry earlier this year. Announced during Google I/O 2026, Gemini Spark is an always-on AI agent that can write emails for you, create continually updated study guides, monitor credit card statements for hidden subscription fees, and more.
Gemini Spark is powered by the newly introduced Gemini 3.5 Flash and runs in the background 24/7 using virtual machines on Google Cloud. The AI agent will connect to Workspace apps like Gmail, Docs, Sheets, and Slides, but Google is expanding integrations to third-party apps using the Model Context Protocol (MCP), an open standard that allows AI models to plug into external systems or data. That includes Canva, OpenTable, and Instacart.
This summer, Google will give Spark the ability to interact with your local files through the Gemini app on macOS. “Even when you close your laptop or turn off your phone, Spark can keep working in the background as you go through your day,” Josh Woodward, the vice president of Google Labs, Gemini, and AI Studio, said during a briefing. “When you use it, it almost feels like you’re tossing things over your shoulder, Spark’s catching them, and gets the job done.”
Google also plans to allow users to text and email with Spark directly, a bit like how OpenClaw users can chat with their personal agent using messaging apps. Gemini Spark will eventually be able to connect to Chrome as well and allow users to view live updates on an upcoming UI space called “Android Halo.”
Spark will operate “under your direction,” according to Google, meaning that you can control what it connects to and when to turn it on. The system will also ask you for permission before performing “high-stakes actions,” like making a payment or sending an email. Gemini Spark is rolling out to “trusted testers” this week and will arrive in beta for Google AI Ultra subscribers in the US next week.
Along with Gemini 3.5 Flash, Spark will use Google’s AI-powered coding tool Antigravity, which is also getting a big update. Google is launching a new Antigravity desktop app that will serve as a hub where you can manage AI-powered agents and their tasks. There’s also a new Antigravity command-line interface and a software development kit that developers can use to build their own AI tools.
Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.
- Emma Roth
Related Articles
高德发布首个无长程依赖的万帧级流式3D重建模型ABot-Recon,以12帧重建万帧3D场景
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400"> 2026-08-28 ...
Anthropic was illegally blacklisted by the Trump administration, court rules
On Thursday, a judge ruled that the Pentagon’s blacklisting of Anthropic earlier this year was unconstitutional, delivering the AI lab a win in a monthslong rollercoaster of a battle with the Trump...
34克、全天候AI,1996元起,雷鸟iO热卖加速智能眼镜全民普及
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400"> 2026-08-28 ...
全球首款专为iPhone用户打造的Agent耳机正式发布,有道AI耳机让声音变成生产力
< img id="wx_img" src="https://www.qbitai.com/wp-content/uploads/imgs/qbitai-logo-1.png" width="400" height="400"> 2026-08-28 ...
