Blog

• Releases
• Clawdite v0.4
• Clawdite v0.3
• Clawdite v0.2
• Clawdite v0.1
• News About Clawdite
• Skill Mapping in the Circular TwAIn Project
• Clawdite Joins XR5.0
• Clawdite will be presented at CIRP-CMS2022
• Selecting Wearable Devices using AHP
• Clawdite published in Procedia CIRP

Releases

Clawdite v0.4

We’re thrilled to announce the release of Clawdite v0.4, a substantial update powered by real-world feedback and the growing adoption of the platform across XR5.0 partners and pilots.
This version strengthens our commitment to intelligent, interoperable workforce data, with a sharp focus on integration, validation, and scalability.

What’s New?

Clawdite v0.4 delivers critical updates to both the technical infrastructure and user-facing services, ensuring the platform can support increasingly complex Human Digital Twin use cases in industrial environments.

JSON-Based IIoT Messaging Support

At the core of v0.4 is a major upgrade to the IIoT middleware, which now fully supports MQTT messages in JSON format for both measurements and states.

This makes it easier to:

• Integrate heterogeneous IIoT devices and data sources,
• Ensure consistent message structure across modules,
• Enable downstream applications (e.g., real-time dashboards, anomaly detectors) to parse and act on messages more efficiently.

Refactored Core Modules with Message Validation

To support this change, the HDM, HDM Web, and all publishers (including Functional Modules and the IIoT Layer) have been refactored and hardened.

These improvements bring:

• Stricter message validation, preventing malformed or incomplete data from entering the system,
• Greater reliability and robustness in high-frequency data environments,
• Easier debugging and extension through modular, version-aware design.

Documentation Improvements and Versioning for a Better User Experience

We’ve also focused on improving the documentation website’s usability and transparency.

• A new search bar is now live on the website, allowing users to quickly locate content, documentation, and updates.
• The entire website is now versioned, giving users full control over which instance of Clawdite they’re exploring. This is particularly useful for organizations operating across multiple deployments or needing backward compatibility.
• The documentation now supports JavaScript examples in addition to the existing Python and Java samples, making it easier for developers across different languages to follow along.

⚠️ Please note: A migration period will run throughout August 2025, after which v0.3 will be officially deprecated.

Why It Matters

These updates are not just quality-of-life improvements—they are enablers of scale and autonomy.

With JSON-based messaging and structured content validation, Clawdite v0.4 ensures that real-time data from the shop floor can be safely and meaningfully integrated into the Human Digital Twin ecosystem.
This directly supports predictive capabilities, adaptive task planning, and human-centered automation across different use cases.

Most importantly, we now have more than 5 partners actively working autonomously within the scope of XR5.0 project on a shared instance of Clawdite, a major milestone demonstrating real-world trust and scalability.

Looking Ahead

Clawdite v0.4 sets the stage for some exciting developments. Our upcoming roadmap includes:

• User Interfaces for entity creation and Human Digital Twin exploration,
• Platform Multitenancy for better organization-level management,
• Worker and User Skills Profiling for deeper human-aware adaptation,
• Dedicated Functional Modules to support the evolving XR5.0 pilot requirements.

Try It Out

Clawdite v0.4 is now available for all XR5.0 project partners and collaborators.
To explore the new features, migrate your instance, or get started with integrations, don’t hesitate to reach out to our team.

Let’s keep building smarter, more human-centric systems—together.

Clawdite v0.3

We’re excited to announce the release of Clawdite v0.3, a major step forward in our mission to create a more intelligent, structured, and actionable representation of workforce data. This version brings significant enhancements to the data model, focusing on a comprehensive approach to modeling worker skills, tasks, and exemptions, laying the foundation for AI-driven decision support in manufacturing and industrial environments.

What’s New?

The Clawdite v0.3 release introduces a suite of new capabilities specifically designed to support advanced workforce intelligence systems like the Human Digital Twin (HDT) used in the Circular TwAIn project.

Extended Data Model for Skills and Taxonomies

The core of Clawdite v0.3 lies in its extended data model that now supports:

• Structured skill representation, also aligned with external taxonomies (e.g., O*NET Content Model),
• Worker characteristics that differentiate between relevant data (skills, abilities, values) and unrelated traits (e.g., age),
• Taxonomy item linking, allowing any modeled skill to be anchored to a known reference taxonomy, ensuring consistency and interpretability across applications.

This model makes it easy to filter, query, and reason over operator skills using established frameworks like O*NET.

Task Assignment and Interventions

With v0.3, Clawdite revises the concept of tasks (aka interventions). This new layer allows the system to:

• Track who was assigned what, when, and why,
• Store metadata around tasks, including purpose, complexity, and required capabilities,
• Lay the groundwork for automated or assisted task planning systems.

Exemptions: Handling Real-World Constraints

We recognize that not every worker can perform every task. That’s why Clawdite v0.3 adds the concept of Exemptions, a dedicated mechanism to explicitly state when and why an operator should not be assigned a particular task.

This supports:

• Safety and compliance rules (e.g., certification required),
• Temporary unavailability (e.g., medical restrictions),
• Personal or contractual constraints.

Why It Matters

These new features are more than just data modeling improvements—they’re enablers of intelligent, human-centric automation.

With v0.3, Clawdite provides the foundation for AI-driven modules, such as the Operator2Task Assignment Engine developed in the Circular TwAIn project. These systems rely on structured, interoperable data to:

• Match the right worker to the right task using skill-based reasoning,
• Avoid incompatible assignments using exemption rules,
• Continuously learn and improve through feedback and historical data.

Looking Ahead

As Clawdite continues to evolve, we’re committed to pushing the boundaries of what Human Digital Twins can represent and enable. The roadmap for upcoming versions includes:

• Support for dynamic skill evolution over time,
• Integration with training programs and performance feedback,
• Better UI/UX for managing task planning and worker profiles.

Try It Out

Clawdite v0.3 is now available to partners and collaborators in the Circular TwAIn project. For more information, demos, or integration support, please contact our team.

Clawdite v0.2

We announce the release of Clawdite v0.2, a significant update focused on making the platform more resilient, modern, and developer-friendly. This release includes deep upgrades to our data infrastructure, enhanced data availability features, and a fully unified API documentation system designed to streamline integration and usage.

Key Highlights

Clawdite v0.2 is primarily a technical refinement release, aimed at making the platform faster, cleaner, and more accessible. While the functional data model from v0.1 remains stable, this version brings a host of improvements across the stack.

Migration to InfluxDB v2

We’ve fully migrated our time-series infrastructure to InfluxDB v2, adopting the latest features and architecture. This upgrade enables:

• Better performance and scalability,
• Native support for Flux, the new functional query language,
• Improved access control and data organization.

This change affects all components relying on historical time-series data, including HDM, Grafana, and HDM-Web.

MinIO Integration for Offline Data Handling

To support scenarios where Gateways operate offline, Clawdite now integrates MinIO, a high-performance object storage system. This allows us to:

• Store batches of data locally when live transmission is unavailable,
• Ensure data integrity and continuity, even in intermittent network conditions,
• Seamlessly ingest stored batches into Clawdite once connectivity is restored.

This makes Clawdite more robust and suitable for real-world industrial environments, where downtime or disconnection may occur.

HDM Updated for InfluxDB v2 and MinIO

The Historical Data Manager (HDM) has been refactored to:

• Interact with InfluxDB v2 using Flux queries,
• Retrieve and process offline-stored data from MinIO, ensuring that no operator or sensor data is lost,
• Provide a unified interface for historical data access regardless of the data’s source.

These changes improve the reliability and transparency of data within the HDT ecosystem.

HDM-Web Now Powered by Flux

The HDM-Web has also been updated to fully support the new Flux query language, replacing the deprecated InfluxQL syntax. This provides:

• More powerful and flexible query capabilities,
• Compatibility with InfluxDB v2,
• Improved query precision and filtering options in the web UI.

Grafana Dashboards Upgraded

Clawdite’s Grafana integration has received a full refresh:

• Updated to the latest Grafana version,
• Dashboards restructured to query InfluxDB via Flux,

Unified API Documentation with OpenAPI 3

We’ve taken a major step forward in developer experience by introducing complete API documentation using OpenAPI Specification v3. This includes:

• A unified Swagger UI entry point that aggregates all Clawdite API specs in one place,
• Interactive documentation for easier exploration and testing,
• Improved onboarding for integrators and partners.

What’s Next?

Clawdite v0.2 reflects our commitment to:

• Operational resilience through smarter data storage and fallback mechanisms,
• Modernization through upgraded infrastructure and tooling,
• Accessibility through well-documented, standards-compliant APIs.

As we look ahead to v0.3 and beyond, our roadmap includes:

• Advanced interfaces for task planning and operator profiling,
• Extended models for task performance tracking.

Clawdite v0.1

Checkout the first version of the Clawdite platform from GitLab.

This is the version we demoed during the first STAR project review meeting. While the core functionalities of Clawdite are there, this version is still not production-ready, thus we recommend to use it in development environments only.

News About Clawdite

Skill Mapping in the Circular TwAIn Project

The Circular TwAIn project is redefining workforce optimization by integrating AI technologies into the industrial ecosystem. At the heart of this transformation lies Clawdite, our versatile platform, which plays a pivotal role in the Human Digital Twin (HDT) component. One of the project’s key achievements is the successful mapping of operator skills to the O*NET Content Model, enabling smarter and more efficient workforce management through AI-powered task assignment.

Mapping Operator Skills with O*NET

To model and standardize operator skills, we leveraged the O*NET Content Model (O*NET Content Model), a comprehensive taxonomy designed by the U.S. Department of Labor. This model serves as a structured foundation to describe work and worker characteristics in a consistent and analyzable format.

In Clawdite, the mapping process employed AbstractDescriptors to associate high-level worker data with O*NET taxonomy items. This design enables us to:

• Model skills as characteristics,
• Link each skill to a corresponding taxonomy item, and
• Connect each taxonomy item to a known Taxonomy instance, representing the O*NET model.

By structuring data this way, Clawdite makes it straightforward to retrieve an operator’s skills while filtering out unrelated characteristics (like age or height) stored in the HDT.

An Enriched Data Model for Clawdite

To support this advanced skill mapping, Clawdite’s data model was extended to:

1. Represent skills and values in alignment with a given taxonomy (O*NET),
2. Track task assignments and include a mechanism to model exemptions—tasks that an operator is explicitly prevented from performing.

Tasks, or interventions, are considered assignments issued by an orchestrator (e.g., a manager) to a factory entity (a worker). The new Exemption concept allows us to annotate specific cases where an operator cannot perform a task, further enhancing the precision of task assignment.

Introducing the Operator2Task Assignment Module

Building on this skill mapping infrastructure, within the Circular TwAIn project our lab developed the Operator2Task Assignment module. This AI-driven component intelligently matches workers to tasks based on skill compatibility, making it a cornerstone for efficient workforce orchestration.

Key Capabilities

• Skill Profiling: The HDT continuously records operator skills and task history, creating a comprehensive profile.
• Task Analysis: When task requirements are not predefined, the system uses AI (language models) to analyze task descriptions and infer needed skills via sentence embeddings.
• Vector-Based Matching: Both operator profiles and task descriptions are converted into vectors. Using similarity metrics (e.g., cosine similarity), the system computes a compatibility score.
• AI-Powered Recommendation Engine: The module suggests the best-matching worker for each task, along with a confidence score to aid decision-making.

This approach ensures not only that the most suitable operators are assigned to each task but also promotes higher job satisfaction by aligning tasks with workers’ strengths.

Conclusion

By enriching the Clawdite platform with skill mapping aligned to the O*NET Content Model and integrating AI for intelligent task assignments, the Circular TwAIn project is paving the way for next-generation workforce management. The Human Digital Twin becomes not just a data repository, but an active, intelligent system that transforms how organizations allocate human resources—optimizing efficiency, ensuring worker satisfaction, and embracing the power of AI in industry.

For more information about the project, visit the official site: circular-twain-project.eu

This work has received funding from the Swiss State Secretariat for Education, Research and Innovation (SERI) and has been partly supported by the European Union’s research and innovation programme under project Circular TwAIn (Grant n. 101058585).

Clawdite Joins XR5.0

Clawdite is now an integral component of the newly launched XR5.0 project, a forward-looking European initiative that merges cutting-edge XR technology, AI, and Human Digital Twins to redefine how people and machines collaborate in Industry 5.0 environments.

What Is XR5.0?

XR5.0 aims to revolutionize industrial extended reality (XR) by combining AI, human-centric digital twins, and European-made XR technologies to support a wide range of Industry 5.0 applications. These include:

• Ergonomic and personalized training,
• Intelligent asset maintenance,
• Worker guidance and monitoring,
• Human-AI collaboration via explainable and generative AI.

XR5.0 will implement and test six high-TRL pilot applications across real manufacturing environments, creating a strong foundation for sustainable industrial XR adoption in Europe.

Clawdite’s Role in XR5.0

To support the ambitious goals of XR5.0, we’ve deployed a dedicated shared instance of Clawdite. This instance acts as the central Human Digital Twin (HDT) knowledge base, storing structured data about workers and devices that feed into functional XR modules.

Key Use Cases Supported by Clawdite:

• Worker Movements Prediction:
  Clawdite stores and structures real-time and historical data on operator positions, enabling predictive models to monitor and forecast worker movements in shared spaces (e.g., environments with Autonomous Mobile Robots (AMRs)). This enhances safety and collaborative efficiency.

• Worker Shadowing & Monitoring:
  Leveraging Clawdite’s ability to represent skills, tasks, and device usage, this module supports the supervision and real-time assistance of less experienced technicians. The HDT data ensures that support is context-aware and personalized, aligning with XR5.0’s person-centric philosophy.

Why Clawdite?

Clawdite brings to XR5.0 a mature, modular platform designed to support Human Digital Twins (HDTs) in complex, real-world industrial scenarios. Building on the enhancements introduced in previous versions, Clawdite offers:

• A robust worker modeling framework, allowing precise representation of worker capabilities, assignments, and interactions.
• Real-time and historical data management, also ensuring continuity even in offline or disconnected environments.
• Flexible data access via HDM and HDM-Web, enabling retrieval of time-series and batch data.
• Unified and developer-friendly APIs, documented with OpenAPI 3 and accessible through a centralized Swagger UI, simplifying integration with XR functional modules.

With these capabilities, Clawdite serves as a core enabler of intelligent and person-centric XR applications, providing the intelligence layer needed to personalize, monitor, and optimize human-machine interaction in Industry 5.0.

This work has received funding from the Swiss State Secretariat for Education, Research and Innovation (SERI) and has been partly supported by the European Union’s research and innovation programme under project XR5.0 (Grant n. 101135209).

Clawdite will be presented at CIRP-CMS2022

Our paper on Clawdite will be presented at CMS2022, the 55th edition of the CIRP International Conference on Manufacturing Systems. The conference is organised by the University of Applied Sciences and Arts of Southern Switzerland - Department of Innovative Technologies and it will be held in Lugano between the 28th of June and the 1st of July.

Selecting Wearable Devices using AHP

Adopting wearable devices is crucial in Industry 5.0 applications, where humans become part of the digital representation of the factory, the so called Human Digital Twins. However, the selection of the devices to use turns to be cumbersome for practitioners and researchers, because of the wide availability of devices in the market.

We faced this criticality while adopting Clawdite in a real-world application, where the aim was to monitor worker’s physiological data so that to enhance the human-in-the-loop control of a production system.

We thus defined a methodology to support the devices selection, focusing on wearable devices for Industry 5.0 applications. The methodology is based on the Analytic Hierarchy Process method, and it allows us to successfully identifying the two devices that satisfy our needs the most, among a list of 110 alternatives.

Here below we report the list of the 89 devices we ranked using our methodology (we discarded obsolete devices and those not fitting the application requirements from the initial list of 100 devices). The top-20% devices are highlighted.

Wearable Classification

Clawdite published in Procedia CIRP

In the context of the Industry 4.0 approach, applications and solutions supporting monitoring, simulation, optimisation, and decision-making in production systems are exponentially growing.

Digital twins are the silver bullet for these solutions, given their capability of providing comprehensive digital representations of production systems, which are continuously updated by leveraging IIoT (Industrial Internet of Things) systems.

However, digital twins designed for Industry 4.0 applications are limited in representing human operators, which instead are a key component in the emerging Industry 5.0 paradigm.

Cognitive automation is spreading increasingly, and it becomes essential to have a digital representation of humans for improving their well-being and performance, but also to monitor and simulate their interactions with the factory.

A standardised solution for creating digital twins is currently missing. Industrial solution architects are forced to resort to ad-hoc implementations and models, which lack re-usability, scalability and extensibility. These limitations prevent a smooth introduction of a human digital representation in existing digital twins, so hindering the complete shift to the new Industry 5.0 paradigm.

The SPS Lab worked on a solution to bridge the existing gaps with current digital twins, by introducing Clawdite, an extensible and flexible IIoT-based platform for creating Human Digital Twins. Clawdite supports the creation of customised data representations of production systems, including machines, devices, and humans. Moreover, Clawdite has been designed to be modular, so that to ease the integration of new components (e.g., for simulations), the digital twin instantiation, and the system ramp-up.

Clawdite has been tested in different projects (STAR, SCOUT), showing its capability to fit different applications and laboratory settings. The resource is publicly available in GitLab.

Want to know more about Clawdite, its architecture and flexible data model? Checkout our paper! If you have any questions, contact us (project key people: Andrea Bettoni, Elias Montini).