www.craftworks.ai Open in urlscan Pro
34.117.168.233  Public Scan

Form analysis
0 forms found in the DOM

Text Content

 
Skip to Main Content


 * Solutions
   
   * Data Lake
   * Predictive Quality
   * Predictive Maintenance
   * Visual Inspection
   * Anomaly Detection
   * Software Solutions
   * Success Stories

 * Products
   
   * navio

 * Services
   
   * Consultancy
   * Research

 * About Us
   
   * Company
   * Team & Know-How

 * Careers

 * News
   
   * Blog
   * Tech Talks

 * More


Use tab to navigate through the menu items.
EN


EN


DE



NAVIO

Seamless machine learning model management, deployment and monitoring for
supercharging MLOps for any organization on the best AI platform



Use navio to perform various machine learning operations across an
organization's entire artificial intelligence landscape. Take your experiments
out of the lab and into production, integrate machine learning into your
workflow for a real, measurable business impact.



Talk to us




DEMO

https://navio-demo.craftworks.io






PRODUCT DEMO






MLOPS

navio provides various Machine Learning operations (MLOps) to support you during
the model development process all the way to running your model in production.
Automatically create REST endpoints and keep track of the machines or clients
that are interacting with your model.





WHY YOU SHOULD RUN YOUR MODELS ON NAVIO



Focus on exploration and training your models to obtain the best possible result
and stop wasting time and resources on setting up infrastructure and other
peripheral features. Let navio handle all aspects of the productionisation
process to go live quickly with your machine learning models. Security,
monitoring, deployment, and containerization all come as standard with
simplicity at the center of everything.




INTEROPERABILITY



Upload any custom python-compatible model to navio to make use of its user
interface to easily manage, deploy and integrate your models. navio makes use of
MLflow, a standard for packaging ML models so that you can continue to create
models using your favourite tools and deep learning frameworks.




EFFORTLESS INTEGRATION



Use REST endpoints to integrate model predictions into any application, machine,
or device. Effortlessly replace your model with a retrained version without
having to regenerate the endpoints or reconfigure access, speeding up
collaboration between departments and ensuring an efficient workflow.




ONE-CLICK DEPLOYMENT



Deploy models without the need for technical skills. Manage multiple deployments
and secure access to your deployed models with built-in security features and
access control.










MONITORING AND PERFORMANCE



Monitor deployed models to ensure robustness and model stability. Prevent data
drift with out-of-distribution detection and keep track of real-time changes in
incoming data and predictions.




RETRAINING

Retrain your models within navio when more data becomes available. Manage all
your retrained models in one use case and switch them out easily to compare
results. 




DEVICE OVERVIEW

Have an overview of all devices connected to your deployed models. From mobile
phones sending gyroscope data to your model to any industrial machine on the
shop floor requesting predictions with its sensor data.




DEPLOY MODELS AT THE EDGE



navio has partnered up with TTTech Industrial to offer users the ability to
deploy their machine learning models directly to edge devices. Integrated with
the Nerve Management System, users can now directly execute their models on
their connected Nerve devices. Connect to data streams produced by machines or
sensors via the Nerve’s data gateway and use these as input to get predictions
in real-time.



This results in

 * reduced latency

 * improved security and

 * better performance


x

 




Live
Your Video Title
Unmute
00:00 04:27







Leverage navio across any industry to gain a competitive advantage by applying
AI in real-time. Whatever your use case, navio helps you productionise your
anomaly detection, computer vision, or deep learning models for a real return on
investment.









INDUSTRY INDEPENDENT





MORE THAN JUST DEPLOYING A MODEL




ORGANIZATION AND SIMPLICITY

Stay organized by managing models in various workspaces and use cases. Control
access via user management.


OUT-OF-DISTRIBUTION DETECTION

Out-of-distribution detection (OOD) for detecting outliers in the data during
prediction.


EXPLANATIONS

SHAP explanations to get explainable predictions or configure your own
explanation visualizations for your custom models using Plotly.


GPU SUPPORT

Speed up model inference and get real-time predictions faster than ever before
with GPU acceleration. Performing computations on a GPU versus a traditional CPU
does not only benefit performance but also tends to be more energy-efficient.





AVAILABLE AS AN ON-PREMISE SOLUTION OR ON AZURE CLOUD.




NAVIO API



The navio API allows data engineers and data scientists to programmatically
include navio in their development or production workflow. Use the API to
perform various tasks including training, uploading, and deploying.



https://navio.craftworks.io/docs/navio-api






UPCOMING FEATURES



 * Integration of our labelling tool
   
   * Annotate your data for object detection to increase the accuracy of your
     model



 * ONNX models
   
   * Support managing of ONNX models 



 * Model versioning 
   
   * Extending retraining with fine-grained version management




 


ARE YOU INTERESTED? TALK TO US ABOUT NAVIO!






Solutions

Services

News

Contact

Data Lake

Predictive Quality

Predictive Maintenance

Visual Inspection

Anomaly Detection

Software Solutions

Success Stories

Consultancy

Research

About Us

Company

Team  & Know-How

Careers

Blog

Tech Talks

Others

craftworks GmbH
Schottenfeldgasse 20/6A
1070 Vienna



office@craftworks.at

+43 660 101 30 92

Terms and Conditions

Imprint

Data Protection / Cookie Policy






Products



navio


English


English


Deutsch




Copyright © 2022 craftworks | All Rights Reserved

 * 
 * 

 
AcceptSettings
We use cookies on our website to see how you interact with it. By accepting, you
agree to our use of such cookies.Data Protection / Cookie Policy