About Us

We develop high-performance video inferencing pipelines and train neural networks. The In-Sight team is an ML/AI department of Bitworks Software.

We develop custom high-performance AI/CV applications for various industries providing full-cycle processes, including but not limited to data labeling, model evaluation, training, pruning, quantization, validation, verification, pipeline development, and CI/CD. We mainly focus on Nvidia hardware (both data center and edge).

We have developed Savant to democratize Nvidia DeepStream and make it available to ML and CV engineers. We use it ourselves to deliver flexible production-ready video analytics pipelines to our customers as quickly as possible.

To acquire custom services, contact us.

What We Do

• Data Labeling – preparing high-quality training datasets
• Model Evaluation & Training – developing and refining neural network models
• Pruning & Quantization – optimizing models for deployment
• Validation & Verification – ensuring model quality and reliability
• Pipeline Development – building end-to-end computer vision pipelines
• CI/CD – continuous integration and deployment for CV systems

The Savant Framework

Savant is our flagship open-source project. It is built on top of NVIDIA DeepStream and provides:

• A Python-first developer experience
• 30+ ready-to-use real-world samples
• Edge and data center support
• Docker-based deployment
• High-performance streaming API
• OpenTelemetry and Prometheus integration

Learn more on GitHub or read the documentation.