visual blocks

We have hosted the application visual blocks in order to run this application in our online workstations with Wine or directly.

Quick description about visual blocks:

Visual Blocks is a node-based, in-browser environment for building AI and data-processing workflows with drag-and-drop components. It lets you connect sources, transforms, models, and visualizers into a live graph, so changes propagate instantly and results are observable without writing glue code. Under the hood it leans on web-friendly runtimes (e.g., WebGPU/WebGL/WebNN or TensorFlow.js backends) to execute pipelines locally, which is great for demos, teaching, and privacy-sensitive prototypes. The block abstraction encourages modularity: you can package a preprocessor, a model, and a postprocessor as a reusable composite for others to slot into their graphs. Because everything lives in the browser, sharing is as simple as exporting a project or link, and collaborators can experiment without installing toolchains. For educators and product teams alike, Visual Blocks reduces the distance from idea to interactive proof-of-concept by turning ML diagrams.

Features:

• Drag-and-drop node graphs for data and ML pipelines
• Live execution in the browser with immediate visual feedback
• Reusable composite blocks to share preprocessing and model steps
• Support for common web ML runtimes and media sources
• Easy import/export for collaboration and teaching
• Visual debugging with inspectors, charts, and intermediate previews

Programming Language: TypeScript.
Categories: