Your ideal Open-source AI companion
Bordeaux
Joined November 2025
- Tweets74
- Following20
- Followers362
- Likes278
reachymini retweeted
Put a Gemma-based model in a robot body. First thing it does: scan the room, spot the giant TV, and start a movie break.
Awesome to see @NVIDIAAI build on Gemma 4 E4B, fitting live conversation, tool calls, animations, and a vision model onto a single 8GB Jetson!
reachymini retweeted
Today we're releasing the Reachy Mini Level UP update, which mainly contains three things:
• A hoverboard, to give Reachy Mini some much-needed mobility (I'm a big inverted pendulum fan and I absolutely love this one, sometimes I just do sit → stand up → sit → stand up on repeat)
• A smartphone app, available on iOS and Android: no computer needed to interact with the robot anymore
• NFC tags, allowing for new angles of creative personalization (e.g. one hat = one personality)
We hope you'll build great things with these new tools, learn stuff and have fun!
Congrats to everyone involved in the release!
PS: There's been a major software update that has been robust for a while now but hasn't gotten a lot of visibility yet: JavaScript apps. I encourage all our AI builders to have a look at it, because for a bunch of applications, it's so comfortable compared to Python. I think the best example of this is the Telepresence app (link below), which allows you to control your Reachy Mini and stream audio and video from your phone, even when you're not home. Also, you just click on the link and it works in your browser, no installation needed.
reachymini retweeted
Sorry for the wait, the episode is here!
Live action with real robots instead of animation (episode 4): "Anger"
Enjoy!
As always, the software of Microduck and Reachy Mini is open source:
github.com/pollen-robotics/m…
github.com/pollen-robotics/r…
reachymini retweeted
I just made the most expressive real-time motion harness for the Reachy Mini.
It was created by:
> synthesizing a massive motion dataset using Astra (over 10000 samples)
> fine-tuning Qwen 3.5 4B using such dataset
> then training a flow matching transformer head to transform sparse motion plan (<1hz) into dense expressive motion (25Hz)
The average inference time for a full motion is less than 200ms, enabling real-time interaction.
@pollenrobotics and @huggingface only recorded 85 emotions for the reachy mini. With my work, you can now prompt and animate any motion you want.
Everything is open-source; write-up and links attached below. Here is a video of Reachy explaining itself through my harness.
reachymini retweeted
Live action with real robots instead of animation: Divorced.
I was exploring how to make Reachy Mini more expressive and I got lost in the plot again.
One is a Wireless and the other a Lite. Both have the experimental "Prosody Wobbler". What do you think?
reachymini retweeted
I got a @reachymini and I want my kids to talk to it, but maybe not to the full extent of what a ChatGPT can do.
I wanted it to have a “brain” of its own and not be dependent on the internet.
Here is my work in progress. A custom base with a small gpu (jetson orin nx) that can run speech and an LLM, no cloud needed.
Dealing with the heat from the GPU was the big question. Still WIP, but I managed to make the custom thermal management work and it keeps the NX at 25W.
It needs some cable management. Can’t wait to have this finished.
#reachymini #nvidia #jetson
reachymini retweeted
Most people should probably update their priors on the state of open-source speech-to-speech.
It's honestly kind of mind-blowing.
We teamed up with @cerebras to build a fully open-source realtime voice demo (models + code) to show what's possible today.
Demo : huggingface.co/spaces/smolag…
Blog: huggingface.co/blog/cerebras…
Go test it, fork it, tweak it, and impress your friends.
video is raw, no cut, no speed-up, first take
reachymini retweeted
Talk to Gemma 4 31B with our voice app!
It sees and searches the web faster than you blink. Thanks to @cerebras’ ultra fast inference, the LLM is almost instantaneous.
The whole stack is fully open-source, and is a drop-in replacement for OpenAI's realtime API.
Demo: huggingface.co/spaces/smolag…
reachymini retweeted
For a while the story was: real-time voice on open models can't work. Too slow, too dumb, won't scale.
We've been quietly running a fully open-source speech-to-speech engine on 9,000+ Reachy Mini robots. Last month it served 301d 4h 43m of conversation.
Now it's yours.
reachymini retweeted
🤖 Reachy Mini Conversation app 0.8.0 was released!
We have three main changes:
- A new nice, simple, and clear UI
- Reachy can now greet you at startup, instead of waiting silently
- It also adds long-term memory. You can ask Reachy Mini to remember things or to forget them, and either way the change persists across restarts, so it still knows what you asked it to keep the next time you start the app
Give it a try and tell in the comments what you think! What would you like your Reachy Mini to remember? 🤖💛
reachymini retweeted
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!
reachymini retweeted
🤖 We added MCP tools to Reachy Mini!
The Reachy Mini conversation app can now use tools hosted on Hugging Face Spaces. Add web search or weather without touching the app's code, publish your own tool and share with the community!
Links below ⬇️
reachymini retweeted
Reachy Mini prices are increasing on Monday! If you want to get one, order it now to get 100$ off!
reachymini retweeted
Local Reachy Mini conversations wireless looks like magic! You can bring your friend around the house and get WOW effect from anyone! 🔥
Thanks @andimarafioti for the blog post on how to set this up: huggingface.co/blog/local-re…
Open-source Realtime API powered by llama.cpp: Parakeet -> Gemma 4 E4B -> Qwen3TTS. Just perfect on M5!
Pictures, audio and content remain local and private!
Next step adding some tools to search on the web or even better interfacing with my Hermes Agent! 🔥
reachymini retweeted
Your @reachymini just stopped needing the cloud.
With @pollenrobotics and @huggingface, we shipped a guide to run the whole speech-to-speech stack on your laptop, audio never leaves the room.