ScaleOut Software launches Version 7 with Claude integration
- ScaleOut Software launches Version 7 of its Product Suite for generative AI
- New integration allows Claude Desktop access to live digital twin data via MCP
- Unified interface combines management of Digital Twins and Active Caching
- Platform enables parallel analysis of large cached collections in memory

*this image is generated using AI for illustrative purposes only.
ScaleOut Software has launched Version 7 of its Product Suite, introducing a new data layer that enables generative AI models to monitor and analyze complex, live systems in real time.
The update addresses limitations in current retrieval-augmented generation (RAG) systems, which often rely on static databases or streaming platforms lacking descriptive context. By combining real-time telemetry with rich metadata about system structure and intended behavior, the new version provides AI with a continuously updated view of operational environments.
Key Features
The release introduces three primary capabilities designed to enhance AI integration and data management:
- Claude Integration: Claude Desktop can now connect securely to ScaleOut digital twin deployments via the Model Context Protocol (MCP). This allows direct access to live telemetry and contextual metadata for real-time analysis.
- Unified Interface: A new integrated user interface consolidates management of ScaleOut Digital Twins alongside ScaleOut Active Caching, simplifying deployment for applications tracking fast-changing data.
- Parallel Data Analysis: Developers can deploy data-parallel methods across entire collections of in-memory objects. This feature distributes work across the platform to enable fast, scalable analysis of cached datasets, such as customized text searches.
Strategic Context
Dr. William Bain, CEO and founder of ScaleOut Software, noted that operational managers are increasingly using AI to monitor large systems like transportation and logistics networks. He stated that digital twins offer the speed and richness required to overcome bottlenecks in ingesting live data and capturing system context.
Founded in 2003, ScaleOut Software specializes in distributed caching, in-memory computing, and digital twin technologies. The company is headquartered in Bellevue, Washington.
How might the integration of real-time telemetry with generative AI via MCP impact the latency and accuracy of decision-making in critical infrastructure sectors like transportation?
What competitive advantages does ScaleOut's approach to overcoming RAG limitations offer compared to traditional static database solutions used by other enterprise AI platforms?
Could the ability to perform parallel data analysis on in-memory objects enable new use cases for real-time fraud detection or dynamic pricing in high-frequency trading environments?































