Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Reachy Mini just got a new Brain! We released a fully open-source backend for talking to Reachy Mini. In the last 48 hours, 3,000+ robots have already hit the version deployed on Hugging Face's infra. Until today, if you wanted a real-time voice agent in your robot, you were... looking at $20+ a day. Realtime APIs are expensive because every second the connection is up, you are being charged! But with our approach, you can run the audio models locally and use your OpenAI or Claude subscription for the LLM, at no extra costs. The audio pipeline is very efficient; in the video, it's running on the cheapest Mac mini, 16GB of RAM (the one that sold out a couple of months back when people were buying them up for openclaws setups). Tutorials coming in the next few weeks: how to run your robot fully locally, or with your favorite agent. Stay tuned!show more

Andi Marafioti

7,397 subscribers

55,683 views • 1 month ago •via X (Twitter)

Education Health & Wellness Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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!

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!

Google Gemma

107,622 views • 10 days ago

This robot assistant from the NVIDIA CES Keynote on Monday is going viral. Nader Khalil🍊 explains all the hottest emerging AI trends in one demo: AI applications in 2026 will be multi-model, multi-modal, hybrid cloud/local, use open source models as well as proprietary models, control robots and embedded devices in the physical world, and have voice interfaces. (And the demo had a cute robot *and* a cute dog. Gold.) The demo was built with Pipecat AI. NVIDIA posted a really nice technical walk-through and complete code. The Reachy Mini robot from Hugging Face is open source hardware. (You can order it now, I have one!). You can run the assistant locally on your own hardware, in the cloud, or both.

This robot assistant from the NVIDIA CES Keynote on Monday is going viral. Nader Khalil🍊 explains all the hottest emerging AI trends in one demo: AI applications in 2026 will be multi-model, multi-modal, hybrid cloud/local, use open source models as well as proprietary models, control robots and embedded devices in the physical world, and have voice interfaces. (And the demo had a cute robot and a cute dog. Gold.) The demo was built with Pipecat AI. NVIDIA posted a really nice technical walk-through and complete code. The Reachy Mini robot from Hugging Face is open source hardware. (You can order it now, I have one!). You can run the assistant locally on your own hardware, in the cloud, or both.

kwindla

48,964 views • 5 months ago

How to have your Openclaw install the new Qwen 3.5-9b Local LLM in 1 minute This came out TODAY and is one of the only local models you can run on a 16GB Mac Mini Will be testing and making some videos this week, look out for that (check below for some tests for now)

How to have your Openclaw install the new Qwen 3.5-9b Local LLM in 1 minute This came out TODAY and is one of the only local models you can run on a 16GB Mac Mini Will be testing and making some videos this week, look out for that (check below for some tests for now)

ashen

63,977 views • 3 months ago

MAC MINI + IPAD + CLAUDE OPUS 4.8 = THE MOST UNDERRATED SETUP OF 2026 > $600 Mac Mini M4 in the closet. no monitor. autonomous agents running 24/7 > reviewing code, managing files, handling workflows while you sleep > you wake up, open the iPad, connect to the full desktop, see what got done coffee shop. lid open. check on the agents. nudge one. close it. your AI keeps working > Mac Mini M4: $600 > Claude: $20/month > iPad you already own this is a remote AI office that fits in a shoebox demo below. Claude skills that run on this setup are in the article above

MAC MINI + IPAD + CLAUDE OPUS 4.8 = THE MOST UNDERRATED SETUP OF 2026 > $600 Mac Mini M4 in the closet. no monitor. autonomous agents running 24/7 > reviewing code, managing files, handling workflows while you sleep > you wake up, open the iPad, connect to the full desktop, see what got done coffee shop. lid open. check on the agents. nudge one. close it. your AI keeps working > Mac Mini M4: $600 > Claude: $20/month > iPad you already own this is a remote AI office that fits in a shoebox demo below. Claude skills that run on this setup are in the article above

Mr. Buzzoni

47,978 views • 21 days ago

Will you be coding with Reachy Mini? 🤖 All the hardware, software, and simulation tools for this adorable robot are open source. Here's how you can become the mad scientist you always wanted to be. 🧪

Will you be coding with Reachy Mini? 🤖 All the hardware, software, and simulation tools for this adorable robot are open source. Here's how you can become the mad scientist you always wanted to be. 🧪

GitHub

74,339 views • 10 months ago

✨ For the last few months I have been reverse engineering Magnific AI's famous upscaler It uses MultiDiffusion, ControlNet tiles and details LoRas In true AI spirit, I am open sourcing it for everyone to use for free in your apps It's designed to easily control the amount of hallucination, resemblance and creativity. You can use it on Replicate now: Or run it locally with A1111'a web UI (parameters are in the comments) The code is fully open source:

✨ For the last few months I have been reverse engineering Magnific AI's famous upscaler It uses MultiDiffusion, ControlNet tiles and details LoRas In true AI spirit, I am open sourcing it for everyone to use for free in your apps It's designed to easily control the amount of hallucination, resemblance and creativity. You can use it on Replicate now: Or run it locally with A1111'a web UI (parameters are in the comments) The code is fully open source:

philz1337x

565,383 views • 2 years ago

Here's a mini-ChatGPT app that runs locally on your computer. You can chat with it just like you would chat with ChatGPT. We use: - DeepSeek R1 as the LLM - ollama to locally serve R1 - Chainlit for the UI Let's build it!

Here's a mini-ChatGPT app that runs locally on your computer. You can chat with it just like you would chat with ChatGPT. We use: - DeepSeek R1 as the LLM - ollama to locally serve R1 - Chainlit for the UI Let's build it!

Avi Chawla

40,265 views • 1 year ago

As a Twitch streamer, do you struggle with keeping your viewership up when on a BRB or Starting Soon screen? Clip reels are a perfect, fun way to keep attention. And they showcase your content. But they're a LOT of work to maintain. Well.. at least they were😎 What if you could have a simple browser source that automatically played an always-fresh clip reel? What if you could have a simple browser source that would show the clip reel of your last stream, like a "Previously On..." TV show intro? Now you can!! When you use the Highlight Hunter by FrostyTools, you find the best moments from your VOD, automatically. You can already easily turn them into Twitch clips, or download the snippets to edit for a perfect short-form video, or download entire montages of VODs to share with your community. BUT NOW, you can just grab one of two simple browser source links, to pop into your OBS or Meld Studio One of them will roll all your favorited snippets in random order, like a shuffling playlist of your best highlights. Great for BRB screens, or any time you want to entertain with your best moments. The other will play the linear montage of your latest VOD, for a "Previously On..." experience that helps catch viewers up if they missed it or forgot. Great for Starting Soon screens to seamlessly tie the streams together (and pairs great with our Showstarter chatbot feature 😉). The best part? As you continue to use the Highlight Hunter, these update automatically! New favorite snippets since last stream? They're in the reel already! Ran the Highlight Hunter on your latest VOD? Its montage will automatically play on your 'Previously On..' browser source when you start stream up next time. This is a SUPER powerful update; check it out ASAP!

As a Twitch streamer, do you struggle with keeping your viewership up when on a BRB or Starting Soon screen? Clip reels are a perfect, fun way to keep attention. And they showcase your content. But they're a LOT of work to maintain. Well.. at least they were😎 What if you could have a simple browser source that automatically played an always-fresh clip reel? What if you could have a simple browser source that would show the clip reel of your last stream, like a "Previously On..." TV show intro? Now you can!! When you use the Highlight Hunter by FrostyTools, you find the best moments from your VOD, automatically. You can already easily turn them into Twitch clips, or download the snippets to edit for a perfect short-form video, or download entire montages of VODs to share with your community. BUT NOW, you can just grab one of two simple browser source links, to pop into your OBS or Meld Studio One of them will roll all your favorited snippets in random order, like a shuffling playlist of your best highlights. Great for BRB screens, or any time you want to entertain with your best moments. The other will play the linear montage of your latest VOD, for a "Previously On..." experience that helps catch viewers up if they missed it or forgot. Great for Starting Soon screens to seamlessly tie the streams together (and pairs great with our Showstarter chatbot feature 😉). The best part? As you continue to use the Highlight Hunter, these update automatically! New favorite snippets since last stream? They're in the reel already! Ran the Highlight Hunter on your latest VOD? Its montage will automatically play on your 'Previously On..' browser source when you start stream up next time. This is a SUPER powerful update; check it out ASAP!

Ken aka Frosty

102,630 views • 8 months ago

🕰️ Make time your friend. Be the ancestor of your future happiness Poet David Whyte on 'How I Write' with David Perell: "All of us can remember a moment, a threshold moment in our existence where you picked up the phone or you went out the door or you put yourself out to have a conversation. You asked for a gift or funding for your work as you did, you know, and you were granted it. And if you hadn't have gone out the door, if you hadn't have picked up the phone, if you hadn't have asked, your life would be immeasurably impoverished today. So you could actually, well, you could actually go back to the person you were in that moment and thank yourself in a way as making a pilgrimage back to that moment." We imagine time is our enemy: "Time makes fools of us all" "I ran out of time" "There's not enough time in the day" Relating to time in this other way befriends it. Rather than cling to the moment, you jump into the flow of time and realize that now is the opportunity to be the ancestor of your future happiness. Now is the only time. What will you do today for your future happiness?

🕰️ Make time your friend. Be the ancestor of your future happiness Poet David Whyte on 'How I Write' with David Perell: "All of us can remember a moment, a threshold moment in our existence where you picked up the phone or you went out the door or you put yourself out to have a conversation. You asked for a gift or funding for your work as you did, you know, and you were granted it. And if you hadn't have gone out the door, if you hadn't have picked up the phone, if you hadn't have asked, your life would be immeasurably impoverished today. So you could actually, well, you could actually go back to the person you were in that moment and thank yourself in a way as making a pilgrimage back to that moment." We imagine time is our enemy: "Time makes fools of us all" "I ran out of time" "There's not enough time in the day" Relating to time in this other way befriends it. Rather than cling to the moment, you jump into the flow of time and realize that now is the opportunity to be the ancestor of your future happiness. Now is the only time. What will you do today for your future happiness?

Dan McAteer

13,568 views • 11 months ago

🚨 Founders: free, private, 100% local AI is finally here I downloaded Qwen 3.6 and ran it on my MacBook inside Strawberry browser. I couldn't believe it. We now have 100% free and private AI that is on par with the best models from OpenAI, Anthropic and Google. (see video!) The CTO of Hugging Face called this "the second revolution of AI." He's right. If you are a building an AI product, you HAVE to start thinking about how you can leverage open source models in your product. It's only a matter of time until local models are mainstream and can run on most people's devices. LLMs are commoditizing. The human brain only requires a AAA battery's worth of energy to run. If biology figured out efficient intelligence, software can too. Maybe we won't need artificial super intelligence and thousands of data centres to do most economically valuable work. Maybe there's a future where AI agents just run on your laptop, fine-tuned to you, fully owned by you, costing only what your energy bill costs. In this future, it's all about building the most delightful, intuitive experience. We've been building for exactly this moment. Stay tuned.

🚨 Founders: free, private, 100% local AI is finally here I downloaded Qwen 3.6 and ran it on my MacBook inside Strawberry browser. I couldn't believe it. We now have 100% free and private AI that is on par with the best models from OpenAI, Anthropic and Google. (see video!) The CTO of Hugging Face called this "the second revolution of AI." He's right. If you are a building an AI product, you HAVE to start thinking about how you can leverage open source models in your product. It's only a matter of time until local models are mainstream and can run on most people's devices. LLMs are commoditizing. The human brain only requires a AAA battery's worth of energy to run. If biology figured out efficient intelligence, software can too. Maybe we won't need artificial super intelligence and thousands of data centres to do most economically valuable work. Maybe there's a future where AI agents just run on your laptop, fine-tuned to you, fully owned by you, costing only what your energy bill costs. In this future, it's all about building the most delightful, intuitive experience. We've been building for exactly this moment. Stay tuned.

Charles Maddock

12,633 views • 1 month ago

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,113 views • 10 months ago

A mini-app is a dApp that is reduced to its core functionality and loaded in the context of another app or website. #TheGrid under your profile on is the perfect place for mini-apps, making them easy to discover, connect, clone, and share. Today we released the up-provider library allowing any user to one-click-connect mini-apps. You can now one-click-connect to mini-apps with the release of the new up-provider library, supercharging the new web3 experience! Read more here 👉 📦

Universal Profiles

29,733 views • 1 year ago

You can now run supermemory locally. Introducing the supermemory local - Fully self-contained. Comes with our graph engine, embedding model, etc. - Run on any machine, with your OpenClaw🦞, hermes, claude, etc. - SDKs to add memory to your agent, or build your company brain.

You can now run supermemory locally. Introducing the supermemory local - Fully self-contained. Comes with our graph engine, embedding model, etc. - Run on any machine, with your OpenClaw🦞, hermes, claude, etc. - SDKs to add memory to your agent, or build your company brain.

Dhravya Shah

617,992 views • 12 days ago

I got NVIDIA’s PersonaPlex running on Reachy Mini and it’s uncanny. Ultra-low latency changes everything for voice agents. BTW, NVIDIA is offering a ~$7k prize (including a DGX Spark!) for the best Reachy Mini community app in the next 15 days.

I got NVIDIA’s PersonaPlex running on Reachy Mini and it’s uncanny. Ultra-low latency changes everything for voice agents. BTW, NVIDIA is offering a ~$7k prize (including a DGX Spark!) for the best Reachy Mini community app in the next 15 days.

Andi Marafioti

54,126 views • 4 months ago

Mac Mini is super nice because you can use native iMessage for talking with OpenClaw. The only problem is that it's very expensive and you need to always have your Mac Mini on to run this setup. So I made a plugin to allow anyone on any computer (either Linux, Windows, or Mac) to be able to have access to iMessage natively. Even better, it has access to all of the reactions, triple dot indicator, etc. Check it out and let me know what you think.

Mac Mini is super nice because you can use native iMessage for talking with OpenClaw. The only problem is that it's very expensive and you need to always have your Mac Mini on to run this setup. So I made a plugin to allow anyone on any computer (either Linux, Windows, or Mac) to be able to have access to iMessage natively. Even better, it has access to all of the reactions, triple dot indicator, etc. Check it out and let me know what you think.

nick vasilescu

265,509 views • 4 months ago

Don't Buy a Mac Mini for Clawdbot: The Secret $10,000 Architecture That Costs You Nothing clawdbot might be the reason you feel like you need a ten thousand dollar computer right now but i am about to show you why that fomo is going to leave you broke. if you have been watching everyone rush out to buy mac minis and mac studios just to run open claw or some local models you are witnessing a massive transfer of wealth from your pocket to apple for no reason. there is a specific setup i use that costs almost nothing and keeps my main machine safe from whatever these autonomous agents are doing. if you stick with me i will walk you through the exact architecture of a professional trading system that handles the heavy lifting without you needing to drop a single rack on hardware most people are scared of running these bots on their main computer because they don't want an agent messing with their personal files or browser sessions. instead of buying a second mac mini for six hundred dollars you can just go to the top left of your screen and create a brand new user profile. this acts like a completely isolated sandbox where you can install all your trading tools and agents without them ever seeing your main data. it is essentially like getting a free computer for the price of five minutes of clicking around your settings but what if you aren't on a mac or you need to access your system while you are traveling without carrying three laptops in your backpack. this is where the first loop of professional automation starts to close because i use something called chrome remote desktop to bridge the gap. this allows me to leave a dedicated machine running in a safe place while i access the full desktop environment from a tablet or a cheap laptop anywhere in the world. it solves the mobility issue but it still doesn't solve the problem of those massive ten thousand dollar price tags for high end mac pros if you are a pc user or just someone who doesn't want to own physical hardware yet you should look into a windows vps through a provider like contabo. most developers will tell you to use a linux terminal but if you aren't a coder yet you need a visual interface you can actually see. getting a windows server allows you to log in and see a desktop just like your home computer for about fifteen dollars a month. i usually recommend at least twelve gigabytes of ram to keep things from getting janky when you are running multiple browser windows and agents at once now you might be thinking that the whole point of the big hardware was to run local models like kimi or glm to save on api costs. i spent years thinking i had to own the machines myself and i even spent hundreds of thousands on developers before i realized i could just do this myself. the secret to running those massive open source models without the ten thousand dollar investment is renting gpu power by the hour. sites like lambda labs let you spin up a monster machine that can run any model in existence for just a couple dollars an hour this is the ultimate pivot because it allows you to test if your strategy actually prints money before you commit to the hardware. you can turn the server on when you are iterating and turn it off the second you are done which keeps your overhead near zero. if you haven't proven that your bot can pay for itself yet then buying a mac studio is just an expensive hobby rather than a business move. there is a much bigger loophole involving the anthropic subscriptions that most people are completely overlooking right now right now i am using a specific plan with claude code that costs about two hundred dollars a month but it lets me run open claw all day without hitting api limits. if i were paying for those same tokens through the standard api i would probably be spending hundreds of dollars every single day. it is a massive cost savings that allows you to iterate and fail until you find a winning strategy without draining your bank account. even if they eventually close this loophole or snitch on the usage patterns it serves as the perfect training ground for a data dog the goal is to find a system that works with a smaller or cheaper model like haiku before you ever try to scale up to the heavy weights. if you can make a strategy profitable using a less intelligent and cheaper model then you know you have found real alpha. once you have that foundation you can decide if it finally makes sense to build your own custom pc rig which will always be half the price of an apple machine. i am an apple guy so i usually pay the tax anyway but i only do it once the system is already generating enough to cover the cost ten times over i believe that code is the great equalizer because it took me from losing money and getting liquidated to having fully automated systems doing the work for me. i had to learn to live with the iterations and the failures on youtube to get to this point of clarity. the universe tends to get out of your way once you make a non negotiable contract with yourself to see the process through to the end. you don't need the flashy hardware or the most expensive setup to start winning in this game stay focused on the logic and the data rather than the hype and the fomo that everyone else is falling for. if you can master the bridge between renting power and owning your logic you will be ahead of ninety nine percent of the people in this space. the path to a fully automated life isn't paved with expensive gadgets but with the discipline to iterate until the system finally prints

Moon Dev

17,382 views • 4 months ago

Reachy Mini x Spectacles won first place in the Open Source category at the Spectacles Community Challenge from Lenslist! Thank you Spectacles for the awesome glasses and SensAI Hackademy for the awesome robot (by Hugging Face & Pollen Robotics)

Reachy Mini x Spectacles won first place in the Open Source category at the Spectacles Community Challenge from Lenslist! Thank you Spectacles for the awesome glasses and SensAI Hackademy for the awesome robot (by Hugging Face & Pollen Robotics)

Johannes Tscharn

16,390 views • 2 months ago

I’m giving an agent control over Reachy Mini from Hugging Face and letting it understand and share spatial data via SPECS for Devs AR is the human interface for robotics and physical AI imo. It feels like absolute magic to interact with this, both in voice/agent and “puppeteering” mode. I’ll probably work on AR for either an arm (manipulation tasks) or some sort of drone (locomotion in 3D space) next… Project is fully open source btw: Thank you SensAI Hackademy for sending me the robot!

I’m giving an agent control over Reachy Mini from Hugging Face and letting it understand and share spatial data via SPECS for Devs AR is the human interface for robotics and physical AI imo. It feels like absolute magic to interact with this, both in voice/agent and “puppeteering” mode. I’ll probably work on AR for either an arm (manipulation tasks) or some sort of drone (locomotion in 3D space) next… Project is fully open source btw: Thank you SensAI Hackademy for sending me the robot!

Johannes Tscharn

35,341 views • 3 months ago

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 views • 1 year ago

This is what open robotics actually looks like! 🔓 I was in Bordeaux, sitting inside Pollen Robotics, and had a chance to play around with their humanoid robot Reachy 2. It’s expressive, modular, and can even bring you coffee, and of course runs Python or Rust. I was talking with Reachy in 3 different languages, tele-operating it and manipulating kitchen stuff, and make it even mimic my gestures. The best part is that there are no locked APIs, or hidden stuff, just an open platform that you can build upon. The connection with Hugging Face makes it super easy to start, as the open source approach allows everyone to contribute, experiment and add their own things. I already ordered his little brother Reachy Mini, let's see what a robotics rookie can do with that robot! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

This is what open robotics actually looks like! 🔓 I was in Bordeaux, sitting inside Pollen Robotics, and had a chance to play around with their humanoid robot Reachy 2. It’s expressive, modular, and can even bring you coffee, and of course runs Python or Rust. I was talking with Reachy in 3 different languages, tele-operating it and manipulating kitchen stuff, and make it even mimic my gestures. The best part is that there are no locked APIs, or hidden stuff, just an open platform that you can build upon. The connection with Hugging Face makes it super easy to start, as the open source approach allows everyone to contribute, experiment and add their own things. I already ordered his little brother Reachy Mini, let's see what a robotics rookie can do with that robot! 👀 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

19,433 views • 5 months ago