google-ai-edge/model-explorer

Health v2 · maintenance only

Adoption not part of the score

1542 stars · 166 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Model Explorer is a model graph visualizer and debugger from Google AI Edge that renders neural network graphs hierarchically with expandable layers, metadata overlays, and GPU-accelerated rendering. It supports TFLite, TF, TFJS, MLIR, and PyTorch exported programs, with an adapter extension framework for adding more formats.

Use cases

• visualize a tflite model graph
• debug pytorch exported model graph
• inspect mlir operations in a neural network
• explore tensorflow model layers interactively
• view onnx model graph structure
• overlay metadata on model graph nodes
• visualize model graphs in a colab notebook

When to choose

• you need hierarchical, interactive visualization of ML model graphs
• you work with TFLite, TF, TFJS, MLIR, or PyTorch exported programs
• you want to debug model structure with metadata overlays and search
• you want to embed a graph visualizer via npm or Python API

When to avoid

• you need training or inference tooling rather than graph inspection
• your model format has no adapter and you cannot write one
• you need a fully offline desktop app without a browser

Facets

application · maturity active

data-visualization developer-tools machine-learning machine-learning developer-tools deep-learning data-visualization python cli cross-platform model-graph-visualizer tflite pytorch tensorflow mlir onnx debugger gpu-rendering debugging web-server

Member repositories

For agents

markdown · JSON · MCP: product_card(name="google-ai-edge/model-explorer")