Added on Nov 21,2026

tensorViz is a PyTorch model visualiser that opens an nn.Module from your Python source as an interactive graph with measured tensor shapes, and lets AI coding agents such as Claude Code, Codex and Cursor see and work on the model with you.
It runs one ordinary eager forward call in your own Python environment and records shapes with forward module hooks, so there is no need for torch.export, TorchScript or ONNX conversion. An Inspect source only mode previews the graph without running the model at all.
The coding-agent plugin gives your agent the graph. The agent can call tools such as get_graph, inspect_nodes and propose_edit, then suggest a change to the model. You review the updated graph and the Python diff side by side, and accept or discard the edit, so you stay in control.
Key features include an expandable model canvas, code focus that links each layer in the graph to the Python that defines it, Graph review for comparing two revisions layer by layer with the code diff beside the graph, and recorded runs that make shape mismatches easy to spot and fix.
It can also bring supported Hugging Face models into your editor, capture a forward pass and let you follow the tensors through the real architecture. Graphs can be saved as .tensorviz.json files and shared, and published models can be browsed in the browser through the Model Explorer without installing anything.
tensorViz installs as an editor extension for VS Code, Cursor and VSCodium, or as a coding-agent plugin for Claude Code, Codex and Cursor. Your model runs on your own machine, including over VS Code Remote SSH.
Pricing: tensorViz is free to install. The core graph tools do not need an AI subscription or provider key, and the source code is public on GitHub under the MIT licence.
It is suited to machine learning engineers, researchers and students who build PyTorch models and want a clearer view of architecture, tensor shapes and changes between commits, especially when working alongside an AI coding agent.
Popular alternatives to tensorViz include Pollinations, NemoClaw and Agnes AI. Compare their pricing and what each is best for below.
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| OrcaRouter | Freemium | Developers and teams who want to balance AI quality and cost across many models. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
Leave a review for the community
No Review Found
Already a member? The same buttons sign you in.
We'll email you a 6-digit code. No password needed. By continuing you agree to our Privacy Policy.
We sent a 6-digit code to . It expires in 10 minutes.
No email? Check your spam folder, or ·