Developing NVIDIA Holoscan Applications with CLI, Skills, and AI Coding Agents

Summary

NVIDIA Holoscan is a platform for real-time AI applications at the edge, and HoloHub provides reference applications and components. This post describes an engineer-guided workflow in which a coding agent builds a separate Python endoscopic tool segmentation application from the existing MONAI model, sample video, and Holoscan patterns. The Holoscan CLI, invoked through ./holohub, exposes shared commands for scaffolding, running, modes, tests, and benchmarking, while development skills and documentation guide the agent through project-specific operations. The application connects video replay, preprocessing, TensorRT inference, segmentation postprocessing, telemetry, and HoloViz visualization, with visual, smoke, and benchmark modes; the post reports that the CLI-plus-skills-plus-docs/examples configuration produced a separate application in 40 minutes using 11M tokens, and concludes that this combination offered the lowest resource overhead among the compared configurations.

Takeaways

1. 1

   The workflow uses small, verifiable iterations so code, outputs, and tests can inform the next engineering prompt and design decision.

2. 2

   Benchmark mode processes 300 frames using Holoscan Data Flow Tracking and exports measurements and plots, making latency review more repeatable.

3. 3

   In the comparison, CLI guidance, development skills, and documentation/examples produced a separate application in 40 minutes with 11M tokens; the other configurations used 15M and 20M tokens and had implementation or efficiency drawbacks.