Robot app store has arrived: Hugging Face launches open source Reachy Mini App Store with 200+ apps
There’s an app for almost every imaginable user and use case these days, but one thing they all have in common is that they focus on one device: the smartphone.
That’s changing today as the face of Hugging, a 10-year-old New York City startup best known for being the go-to place online to host and deploy low-level AI models, AIs, agents and apps, is launching a new App Store for Reachy Mini, its low-cost ($299) open-source robot that debuted back in July 2025 Robots).
The new Hugging Face Reachy Mini App Store already hosts a library of over 200 community-built apps, and Reachy Mini owners will be able to download any of these for free to get started (unlike smartphone apps, there’s no monetization option for app creators in this store – yet).
The Reachy Mini App Store will also provide owners of the Reachy Mini – about 10,000 units sold so far since last year – an easy way to create their own custom applications for the small, stationary desktop robot with built-in camera eyes, speaker, and microphone, using the Hugging Face, AI-powered agent called. "ML Intern."
The importance is not only in the hardware, but in the removal of "a roboticist" barrier; for the first time, people with no engineering or coding background are deploying functional robotics software in less than an hour.
"Anyone can build apps," said Clément Delanggue, CEO and founder of Hugging Face, in a video interview with VentureBeat. "My intuition is increasing [AI] model makers will release the Reachy Mini as a way to test the robot’s ability for new models."
Make robots accessible to common people like PCs and smartphones
A technical bottleneck in robotics has historically been the lack of high-quality training data.
While Large-scale Language Models (LLMs) can code for general purpose by training in large repositories such as Microsoft’s GitHub, a volume of robotics-specific code remains. "he is young" by comparison (although Github contains probably the largest publicly accessible robotics library to date, with over 17,000 different repositories or "repos" dedicated to the field).
This lack of data means that, until now, AI agents have been very poor at understanding the intangibles and firmware requirements of hardware.
The solution to Hugging Face is a tool kit who acts as a mediator. Rather than forcing the user to learn a specific robotics SDK or master the nuances of the robot’s firmware, the toolkit allows the user to define the desired behavior in plain English—for example, "wave when someone says hello".
The AI agent then handles the heavy lifting: it writes the code, checks it against the robot’s specific constraints, and sends the final package.
"Historically, it was very difficult," Delanggue told VentureBeat about building robotics applications. "But we’ve worked hard on the topic with a combination of open source everything we do, working on the right acronyms for robots, and making it easy for agents to understand and use it."
The platform is model agnostic, supporting many leading intelligence engines. Users can create applications using ML Intern’s own Hugging Face agent or use external models including GPT-5.5, Claude Opus 4.6, Kimmy 2.6, Mini Max GM5, and Deep Sig V4 Pro.
For real-time interaction, official chat apps use OpenAI Realtime and Gemini Live. By offering these high-quality snapshots, Hugging Face has broken the norm "integration weeks" The robots work in a process that takes minutes.
The affordable Reachy Mini is a hit
To use the new Hugging Face Reachy Mini App Store, users are encouraged to make purchases The Reachy Minicute desktop robot Hugging Face launched back in July 2025 as an affordable, open-source alternative to existing, commercially available robots from the likes of Boston Dynamics, whose popular robot dog sells for around $70,000. Even their Chinese competitors start at $1,900+.
In contrast, the Reachy Mini is more affordable for hobbyists and developers. It comes in two variants:
-
Reachy Mini Lite ($299 plus shipping): A version installed as a modem that connects via USB and uses an external computer for processing.
-
Reachy Mini Wireless ($449 plus shipping): A standalone version that includes a built-in Raspberry Pi CM 4 and Wi-Fi connection.
Delangue said that of the 10,000 Reachy Minis that have been sold so far, 3,000 have been sold in the past two weeks. Hugging Face expects to ship another 1,000 units within the next 30 days.
Even those who don’t own a Reachy Mini can still develop applications for it, however, using the Reachy Mini App Store and the Reachy App, which contains a 3D simulation of the robot and its responses.
I App Store which itself is hosted on Hugging Face Hub. It works like a normal software repository but with hardware behavior:
-
Search and install: Users can find apps, click a button, and install them directly on their robot.
-
Forkability: All app "hard," meaning that a user can replicate an existing application and ask an AI agent to modify it (eg "make it answer in French").
-
Simulation mode: Most importantly, the store includes a browser-based simulator. This allows users who don’t have a physical Reachy Mini to create, explore, and play through a catalog in a virtual environment.
Both are part of the ongoing Hugging Face "This Robot" efforts – a project started in 2024 by Hugging Face researchers specializing in robotics and AI who develop and publish on the web their open source code, tutorials, and hardware to make robotics development accessible to a wider audience.
And unlike Github, which is designed for a developer audience, the Hugging Face Reachy Mini App Store is designed for robot owners and users who may not have technical knowledge or training.
Continuing the open source ethos and practice
The Face of Celebration strategy is based on the belief that closed hardware and software are "almost impossible" build to scale.
Delanggue notes that closed systems prevent the training of agents and limit society’s ability to innovate. As a result, the entire Reachy Mini platform is open source.
This open licensing model has two main ecosystem implications:
-
Accelerated Development: Because the code is public and integrated into the Hugging Face ecosystem with "spaces," The Hugging Face feature for hosting AI-powered web applications launched in 2021, agents can easily learn to interact with the hardware.
-
Community Sovereignty: Apps are not locked behind a proprietary wall. Currently, all 200+ apps in the store are free, although the platform is open source "Vacancies" it provides an opportunity for creators to monetize their work in the future.
"Currently, all apps are free," Delanggue commented. "It’s flexible, it’s built on it [Hugging Face] Vacancies, so at some point maybe people will make them pay."
Robots are entering their accessible hobby
Hugging Face’s Reachy Mini app store launches with 200 apps already available.
So who built them, and how did they do it without this pre-existing platform?
Delanggue told VentureBeat that more than that 150 different creators had contributors to the store, most of whom had never written a line of robot code before.
However, they were able to do so thanks to Hugging Face’s ML Intern and Github. The new Hugging Face Reachy Mini App Store now puts existing tools and apps in one place for easy access.
Delangue was eager to highlight one of the developers of the Reachy robotics app in particular to VentureBeat: Joel Cohen, a 78-year-old retired marketing executive.
Cohen, who is color blind and has no technical background, spent two weeks assembling his Reachy Mini Lite (a task that usually takes three hours). Despite these physical challenges, he used an AI agent to build a "VP of Future Thinking" assistant to his Zoom-based CEO team. The app allows the robot to:
-
I greeted 29 members by name.
-
Real-time fact-checking interviews.
-
Summarize the key themes and go back to the top answers.
"I built this by explaining what I needed in plain English," Cohen said in a press release provided to VentureBeat ahead of the launch. "There is no SDK. There are no robot backgrounds. No developer experience".
Other community-driven apps include:
-
Chess for Trauma: A robot that plays chess and mocks the user’s mistakes.
-
Reach Phone Home: An anti-procrastination tool that detects when the user picks up their phone and tells them to get back to work.
-
Language Teacher: A physical companion that listens to speech and corrects pronunciation.
-
F1 Race Commentator: A desk companion that calls Formula 1 races live as they happen.
Delanggue himself related to VentureBeat that in just a few hours, he built an app for his Reachy Mini robot in the Hugging Face Miami office so that the robot could act as a receptionist.
“Of course seeing a face is seeing when you get to the office, and it looks at you and rides you," Related to Delangue. "Say, ‘Hey, welcome to the office. Who are you here?’ Then he sends me a message: ‘Carl just arrived at the office. He is here to meet you, and for these reasons.’ It works a little bit like my office lobby, and it took me less than two hours to build that.”
Even with an experienced inventor and engineer like Delanggue, applications for building a robot were out of the question until the combination of Reachy Mini and ML Intern.
“It wouldn’t have happened to me," said the Hugging Face CEO. "If you weren’t a robotics developer, it probably wouldn’t happen, or it would take a few months."
Democratizing robotics
The introduction of the App Store agent marks a significant change in the way we interact with devices. For sixty years, the field was closed by the need for deep technical expertise.
By combining cheap open source hardware with the thinking power of modern AI agents, Hugging Face moves forward where the hardware is the product and the behavior is limited only to what the user can define.
As Delangue noted at the launch, the goal was to provide a platform for people who do it "i want to get into robotics but i don’t have the hardware or skills".
About 10,000 robots now "in the wild" and a growing store of agent-written applications, Reachy Mini has become the most widely used open source desktop robot in history.
The question is no longer how to build a robot, but what—now that the gate is open—will we ask them to do it.
