Reachy Mini's conversation app is the easiest way to get started with the robot.
Plug in, talk, done. Powered by @huggingface.
Long-term memory across sessions. Multi-language support. Full personality control.
Best weekend yet for Reachy Mini’s conversation app🔥
> 3,293 sessions
> 31 peak concurrent robots
> 58 days of conversation
> 1.4s P95 latency, 0.8s median
$390 in infra costs vs. an estimated $4K+ using gpt-realtime-2.1
But the best part is the feedback from happy users :)
One year ago today, we introduced Reachy Mini to the world.
Despite the bumps along the way, you welcomed it, built with it, and kept pushing us forward.
Thank you. Let's keep going.
If you don't want to wait to experience the magic of HF open-source robots, you should get a Reachy mini, ships much faster than microduck and as much fun!
10,000+ microducks were pre-ordered in just five days!
We weren't expecting that many (it's more than the total number of reachy mini in a year) and it will generate delays so from now on, it will be first-ordered, first shipped to make it fair for everyone!
One robot. One API. Run your AI app on the robot, your laptop, or a Hugging Face Space locally or remotely, in Python or the browser.
Full breakdown of Reachy Mini's media stack →
Real-time social robotics, from the cloud to your local device.
Watch Ian from our DevX team use Gemini Live for a seamless voice chat with Reachy Mini.
Then, stick around until the end to see the robot running locally on Gemma 4!