Tensor Spy: inspect NumPy and PyTorch tensors in the browser, no upload
Details
- External ID
- 47221645
- Source
- HN
- Company
- —
- Product
- Tensor Spy: inspect NumPy and PyTorch tensors in the browser, no upload
- Website domain
- tensorspy.com
- Launched
- March 2, 2026
- Cohort
- —
- Upvotes
- 22
- Upvotes percentile
- 0.7570725707257072
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
We needed a side project to give agentic coding a try, and created tensorspy.com together with Junie and ChatGPT 5.2.Tensor Spy lets you quickly inspect the contents of numpy & pytorch tensors locally (your tensors are not uploaded to any servers).This is useful to validate your deep learning data pipelines, to check which layers in your diverging model are actually going haywire, and just because it's kind of cool & a lot more convenient for one-off inspections than loading things up in python.If you work with diffusion models, inspecting the latent space can be quite informative: you want some "noise" in there but it should probably be fairly smooth for your LDM (Latent Diffusion Model) to be able to target it well.Also, if you haven't looked at your data, it's probably not what you think it is ;)Basic stats are auto-computed, and any inf/nan values are both counted and rendered with contrasting colors, to help you quickly identify issue hotspots.The site is free, and our broad intention is to keep it that way (we run a bunch of pro-bono little utility sites in addition to our commercial ones, they're all linked on the about page).Would love to hear your thoughts, I'm sure there are some stats or utility features we missed, so please give it a spin and let us know!---Agentic coding is a brave new world. Three years ago, after the initial rush of ChatGPT's launch, I commented to some friends that "we're standing on the beach and the water just receded". The tsunami is really hitting now. As in: this project took about 2 weeks, and not only would we not have done it without agentic coding, it would have taken months using "traditional methods". With agentic coding, adding .pt/.pth support was basically a single request. And it just worked. Time to adapt yet again.
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- —
- Function
- Dev tools
- Audience
- Developer
- AI stance
- Not AI
- Project type
- Commercial product
- Normalized one-liner
- tensor inspection tool for numpy and pytorch
- Manually corrected
- False
Could you build this?
Yes Tensor Spy runs entirely client-side, parsing standard binary tensor formats (.npy, .pt) using WebAssembly/JavaScript libraries and rendering slices via HTML canvas. The authors explicitly state they built it in a few sessions using AI coding assistants.
Discussion
1 comment analyzed.
Competitors mentioned: threejs-based client-side webapp for trajectory visualization
Competitors
Other products that read as similar to this one — 64 launches clear the similarity bar, closest 8 shown.
Attention rank: #22 of 65 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 119 days after the earliest competitor.
- Axiom · hn · 2026-02-02 · 5 upvotes · similarity 0.45
- Morph Reflexes · hn · 2026-06-30 · 20 upvotes · similarity 0.40
- Agentic Data Analysis with Claude Code · hn · 2026-03-10 · 6 upvotes · similarity 0.40
- GitHub · hn · 2026-01-16 · 6 upvotes · similarity 0.38
- FeyNoBg · hn · 2026-07-27 · 121 upvotes · similarity 0.37
- I wrote my first neural network · hn · 2026-03-14 · 6 upvotes · similarity 0.37
- Ontological Directed Synthesis Network · ph · 2026-09-22 · 1 upvotes · similarity 0.37
- Autonomous recovery for distributed training jobs · hn · 2026-01-29 · 12 upvotes · similarity 0.37
Other launches for this product
- No other launches for this product.