Observed arrival · 2026-09-26
Network Builder makes neural networks drawable
A browser-based visual editor for assembling neural networks, inspecting their structure, and exporting PyTorch code.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Deep-learning students, teachers, and PyTorch developers
- Worth noticing
- The editor describes 130 building blocks and flags incompatible data shapes, with an explanation and a suggested fix.
Field notes
The editor is presented as a browser workspace: users place layers on a canvas, connect them, and inspect data shapes and parameter counts. The homepage lists 130 building blocks, including convolutions, LSTMs, and attention, and names exports such as notebooks and ONNX. It also describes training small models in-browser; its claims about local data handling and agreement with PyTorch are site statements, not independently verified here.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue