# google-ai-edge/model-explorer

A modern model graph visualizer and debugger

Repository: https://github.com/google-ai-edge/model-explorer
Canonical: https://ross.abutalabs.com/products/model-explorer
Language: JavaScript
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T18:54:05+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 99, longevity 69
- inputs: {"age_days": 972, "days_push": 7, "days_rel": 9, "gap_med": 20, "n_releases_24m": 24}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1542, forks 166 (observed 2026-08-28T04:05:01.117011+00:00)

## What it is
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
- artifact type: application
- maturity: active
- function: data-visualization, developer-tools, machine-learning
- domain: machine-learning, developer-tools, deep-learning, data-visualization
- platform: python, cli, cross-platform
- tags: model-graph-visualizer, tflite, pytorch, tensorflow, mlir, onnx, debugger, gpu-rendering, debugging, web-server

## Member repositories
- google-ai-edge/model-explorer (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:01.117011+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:30:44.395665+00:00, confidence not recorded.
  - readme: https://github.com/google-ai-edge/model-explorer (fetched 2026-08-28T04:05:01.117011+00:00, sha 69f50d4c5ca0)
- Data as of 2026-08-30T08:39:29.467469+00:00.