Your ideal Open-source AI companion
Bordeaux
Joined November 2025
- Tweets69
- Following19
- Followers337
- Likes247
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.
reachymini retweeted
Introducing local Reachy Mini conversations: free chats forever!
So fast that we had to hardcode delays to stop it from interrupting you mid-sentence.
We built an open-source Realtime API powered by llama.cpp:
Parakeet -> Gemma 4 E4B -> Qwen3TTS
Run it anywhere you run local LMs. Video shows DGX Spark and a 36GB M3 Pro MacBook.
Blog: huggingface.co/blog/local-re…
🤩
met @darkseed on Tuesday at @gosimfoundation Paris (Station F)
asked him if I could bring my Reachy Mini over — the one with the eyes I'd modded.
he said yes. and then… 🤖👇
reachymini retweeted
I 3D printed my Reachy mini a custom outfit, then built a live object detection app and deployed it on her camera
Turns out she's not a robot with AI added. She's an LLM with a body. different thing
youtube.com/watch?v=2D_EAcDg…
