Skip to Content Facebook Feature Image

Yarbo Takes Next Step Toward an Open Robotics Ecosystem with SDK Beta

Business

Yarbo Takes Next Step Toward an Open Robotics Ecosystem with SDK Beta
Business

Business

Yarbo Takes Next Step Toward an Open Robotics Ecosystem with SDK Beta

2026-11-18 21:58 Last Updated At:22:35

Yarbo opens applications for its SDK Beta, the first tangible milestone in its Open Platform strategy introduced in April.

CHICAGO, Nov. 18, 2026 /PRNewswire/ -- Yarbo, a developer of modular yard robots, is accepting sign-ups for a closed beta test (CBT) of its SDK Beta, inviting homeowners and developers to explore new ways to build on its modular yard robot system. The software development kit (SDK) provides tools for creating custom applications or plugins that connect Yarbo devices with external systems, opening up new possibilities for how people interact with and extend their robots. The Beta marks the first step in Yarbo's broader effort to build an open robotics ecosystem.

The announcement builds on Yarbo's Open Platform strategy, first introduced in April 2026 during the M Series Kickstarter campaign. The Yarbo Open Platform brings together the SDK and hardware development kit (HDK). Designed to support all Yarbo product series, the platform will also be supported by future Yarbo hardware products. When the strategy was first introduced, Yarbo outlined its ambition to give homeowners and developers more ways to build on its robotic system. With the SDK Beta now open for applications, the company is turning that vision into an opportunity for real-world development and collaboration.

The Evolution of Modularity

Yarbo's modular design gives one robotic core the flexibility to take on different tasks through interchangeable modules. The SDK Beta takes this idea a step further by extending this modularity beyond hardware into software.

This opportunity is emerging alongside a broader shift in software development. With the rise of Vibe Coding and AI Agents, creating software is becoming more accessible. As a result, individuals and organizations can more easily turn their ideas into practical solutions tailored to their own needs, rather than relying solely on tools and functions already available on the market.

Yarbo sees the SDK Beta as a way to bring together these different needs and ideas around the same modular robotic system, opening the door to applications and solutions beyond those originally envisioned by the company. This reflects the belief in flexibility and adaptability that underpins Yarbo's Open Platform vision: One Yarbo, More Possibilities.

Possibilities with the Yarbo SDK Beta

The Yarbo SDK Beta provides development tools that allow users to connect their authorized devices with external tools and systems, such as smart home interfaces, dealer service platforms, and research applications. Users can create apps that provide interfaces for interacting with or viewing device information, or plugins that monitor specific changes in the background and support automated workflows. This gives users more flexibility to explore how Yarbo devices can work with other software beyond their built-in functions.

To illustrate the possibilities, Yarbo has identified several application concepts. For homeowners, the platform creates opportunities to tailor yard management to their individual routines and preferences. For example, developers could use mowing data to inform smart irrigation systems, helping coordinate different aspects of yard care. Other potential ideas include scheduling snow removal in stages during a major snowstorm or creating custom voice prompts to make device interactions more personal.

For dealers and commercial operators, integrations could help connect individual robots with broader service and operational workflows. A dealer, for instance, could use device alerts to identify potential maintenance needs and proactively arrange service visits. Integrations with service ticketing systems could also help streamline customer support and equipment maintenance. In commercial settings, operators could develop scheduled workflows for environments such as golf courses, where tasks may need to be coordinated across different areas and time windows.

Universities and research institutions may also use Yarbo to study robotics in real outdoor environments. With technologies such as RTK, IMU, stereo vision, and odometry, researchers could investigate how robotic systems perform in practical field conditions and use the platform as a basis for testing outdoor navigation and other robotics applications.

These examples are potential directions for exploration, rather than features currently offered by Yarbo. From residential yards and commercial properties to academic research, the range of possible applications illustrates the value of an open platform.

Building Toward a Long-Term Open Ecosystem

"Modularity has always been at the heart of Yarbo. Different users have different needs, and we don't expect one predefined set of functions to address every possibility. We believe the same principle should apply to how people use and develop our platform," said Jay Li, Product Director of Yarbo. "Yarbo SDK Beta lets our users add jobs we never planned for. That is what an open platform means in practice: the product keeps growing after it leaves our hands."

The SDK Beta is an early milestone in Yarbo's broader Open Platform strategy, not the endpoint of its development. Yarbo will also progressively open access to hardware interfaces and provide development resources through the HDK, supporting the development of accessories, functional modules, and other hardware extensions. The long-term value of this initiative lies not only in providing development tools but also in establishing the foundation for a sustainable, collaboration-driven ecosystem. The platform and its collaboration models will continue to evolve as this ecosystem takes shape.

To ensure responsible access, device information and functions are subject to an authorization review by Yarbo. When users apply for access permissions, Yarbo will review each request and determine the applicable authorization scope and accessible data. This process is intended to ensure that integrations operate within the permissions granted for each use case.

Applications for the CBT are now open to users and developers worldwide at sdk.yarbo.ai. Yarbo staff will review applications and select participants for the Beta program. Interested participants can visit the website to learn more and submit their applications.

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

Yarbo Takes Next Step Toward an Open Robotics Ecosystem with SDK Beta

Yarbo Takes Next Step Toward an Open Robotics Ecosystem with SDK Beta

  • Delivers PCIe Gen 6 performance with up to 100% greater sequential read bandwidth in the now-shipping all-flash servers
  • Expands the Petascale portfolio as the first of multiple new storage products based on AMD EPYC™ 9006 SP7 and SP8 CPUs
  • Validates the platform, which includes the CloudDC, GrandTwin®, and Hyper families, with solutions from leading software-defined storage partners including Hammerspace, IBM, MinIO, Nutanix, Scality, VAST Data, VDURA, WEKA for AI-scale deployments

SAN JOSE, Calif., and CHICAGO, Nov. 18, 2026 /PRNewswire/ -- Supercomputing Conference - Supermicro, Inc. (NASDAQ: SMCI), an AI, Enterprise, Storage, and 5G/Edge Total IT Solution Provider featuring Data Center Building Block Solutions® (DCBBS), today announced new extensions to the broad portfolio of AMD EPYC based all-flash storage servers. The first systems, now shipping, include the Petascale system powered by the 6th Gen AMD EPYC 9006 Series processors (formerly codenamed "Venice"), with more products to follow as AMD launches new SP8 CPU versions. These are the first storage products supporting the PCIe Gen 6 I/O specification with 100% greater sequential read bandwidth over PCIe Gen 5.

"Expanding AI and HPC workloads require storage that can match the performance of today's CPU and GPU clusters," said Vik Malyala, chief business officer at Supermicro. "With our new all-flash storage servers based on AMD EPYC processors, and the flexibility of the DCBBS architecture, we are delivering improved PCIe Gen 6 bandwidth, high density, and scalable capacity. These platforms can be customized for HPC, AI training, and inference workloads, while providing software-defined storage partners with proven, validated systems they can rely on."

For information on Supermicro's AI storage solution portfolio, click here, and watch a video summary of the release here.

Supermicro will be showing the new Petascale all-flash storage server in booth #4017 at Supercomputing 2026, in Chicago, November 15-20.

The first system in the new family packs exceptional density into a 2U chassis with support for up to 32 E3.S NVMe SSDs—delivering as much as 3.93 PB of capacity with 122 TB drives. Its balanced I/O architecture supports up to four x16 high-performance networking cards, enabling the sustained bandwidth required for AI data lakes, large-scale analytics, and high-throughput storage networking while giving customers the flexibility to optimize for their specific workload and fabric requirements.

Supporting Partner Quotes

AMD
"We have worked with Supermicro for years, bringing AMD EPYC processing capabilities to Petascale all-flash servers," said Dan McNamara, senior vice president and general manager, Compute and Enterprise AI, AMD. "As software-defined storage architectures demand greater energy efficiency, high single-socket performance, and large numbers of PCIe lanes, the AMD EPYC family is ideally suited. The latest Venice SP7 and SP8 platforms deliver the core density and PCIe Gen 6 connectivity that modern storage workloads require."

Hammerspace
"The future of AI infrastructure is about maximizing performance per dollar, per watt, and per rack," said Gregg Machon, SVP Business Development & Worldwide Partners Hammerspace. "Supermicro's new Petascale platform delivers exceptional NVMe performance density and efficiency. With Hammerspace's standards-based Data Platform, customers can easily incorporate this high-performance storage into a single global namespace alongside existing, cost-optimized capacity storage. This gives organizations the performance AI workloads demand, while maximizing infrastructure utilization, avoiding costly over-provisioning, and delivering better overall price-performance." 

IBM
"AI inference is no longer a single workload – it's a pipeline that spans data ingest, model loading, retrieval, and KV cache and each stage must maximize GPU utilization efficiency," said Vincent Hsu, IBM Fellow, VP & CTO of IBM Storage. "IBM Storage Scale on Supermicro's newest AMD-based Petascale server is designed to give customers a high-performance, resilient platform for the entire inference pipeline, with PCIe Gen 6 bandwidth and greater headroom for both performance and capacity growth.

MinIO
"Supermicro's new Petascale platform offers a compelling foundation for the full AI data pipeline," said Ugur Tigli, MinIO CTO. "Combined with MinIO AIStor and MemKV, it becomes a data and memory foundation for modern AI infrastructure. Enterprises can put its dense flash capacity and PCIe Gen 6 bandwidth to work across ingestion, training, and inference, serving all of their throughput, IOPS, and latency needs. Together, we're helping customers build a compact foundation that delivers performance and capacity from every rack unit."

Nutanix
"Unlocking the value of agentic AI requires seamless optimization across compute, networking, and storage. Nutanix is thrilled to expand its full-stack agentic AI collaboration with Supermicro and AMD," said Ketan Shah, SVP, Product Management, Nutanix. By bringing together AMD EPYC processors, Supermicro's high-density Petascale all-flash platform, and Nutanix software-defined storage with built-in data security, we are giving customers a secure validated AI platform that fuels real-time inference, retrieval, and data-intensive enterprise workloads at scale.

Scality
"Scality has recently introduced new storage solutions for AI, including Autonomous Data Infrastructure (ADI) and AI Inference Factory, building on our ongoing collaboration with Supermicro," said Paul Speciale, chief strategy officer, Scality. "The latest Petascale platform provides an ideal foundation for these solutions, delivering the performance and scalability our customers require."

VAST Data
"AI infrastructure is not one-size-fits-all, and our longstanding partnership with Supermicro is built around giving customers the flexibility to deploy the right infrastructure for their workloads," said Phil Manez, vice president, Global Partnerships at VAST Data. "With Supermicro's latest AMD EPYC-based systems, we're expanding that choice, combining the performance and efficiency of the VAST AI Operating System with next-generation hardware to help customers optimize for performance, cost, power, and scale."

VDURA
"VDURA's software-defined data platform runs on Supermicro's latest Petascale systems built on AMD's Venice CPU," said Ken Claffey, CEO of VDURA. "With Supermicro's broad all-flash and HDD platforms unified in a single VDURA namespace, together we deliver more performance per watt and per rack unit at the best cost per terabyte, so customers can maximize the efficiency of their AI infrastructure."

WEKA
"AI labs and neoclouds want more performance for less power in the smallest footprint, and that's where our partnership with Supermicro truly delivers. WEKA NeuralMesh is fully software-defined and distributed, so it scales uniformly across Supermicro's new Petascale server and puts the full bandwidth of PCIe Gen 6 and AMD EPYC 9006 processors to work from day one, with no hardware tiers to create bottlenecks. That's how NeuralMesh keeps pushing throughput higher and latency lower as AI workloads evolve. Together, we're giving customers the performance density that large-scale training and inference demand," said Ajay Singh, chief product officer at WEKA.

About Super Micro Computer, Inc.
Supermicro (NASDAQ: SMCI) is a global leader in Application-Optimized Total IT Solutions. Founded and operating in San Jose, California, Supermicro is committed to delivering first-to-market innovation for Enterprise, Cloud, AI, and 5G Telco/Edge IT Infrastructure. We are a Total IT Solutions provider with server, AI, storage, IoT, switch systems, software, and support services. Supermicro's motherboard, power, and chassis design expertise further enables our development and production, enabling next-generation innovation from cloud to edge for our global customers. Our products are designed and manufactured in-house (in the US, Asia, Malaysia, and the Netherlands), leveraging global operations for scale and efficiency and optimized to improve TCO and reduce environmental impact (Green Computing). The award-winning portfolio of Server Building Block Solutions® allows customers to optimize for their exact workload and application by selecting from a broad family of systems built from our flexible and reusable building blocks that support a comprehensive set of form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air-conditioned, free air cooling or liquid cooling).

Supermicro, Server Building Block Solutions, and We Keep IT Green are trademarks and/or registered trademarks of Super Micro Computer, Inc.

All other brands, names, and trademarks are the property of their respective owners.

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

Supermicro Ships First All-Flash Storage Servers, Delivering PCIe Gen 6 Performance and Broad Software-Defined Storage Support for AI Training and Inference

Supermicro Ships First All-Flash Storage Servers, Delivering PCIe Gen 6 Performance and Broad Software-Defined Storage Support for AI Training and Inference

Recommended Articles