# apoorvnandan/tensor.h

creating a tiny tensor library in raw C

Repository: https://github.com/apoorvnandan/tensor.h
Canonical: https://ross.abutalabs.com/products/tensorh
Language: C
License Family: other
Last push: 2025-03-05T16:27:23+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 9, release rhythm 35, longevity 49
- inputs: {"age_days": 692, "days_push": 546, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1468, forks 129 (observed 2026-08-28T04:04:48.926080+00:00)

## What it is
A tiny tensor library written in raw C, built as a step-by-step educational project explaining neural networks, autograd, and training from absolute scratch with no dependencies like PyTorch or NumPy. The repository doubles as a readable tutorial for programmers with no machine learning background.

## Use cases
- learn how neural networks work from scratch
- understand autograd and backpropagation internals
- build a minimal tensor library in C
- train small neural networks without pytorch or numpy
- teach machine learning fundamentals to programmers
- study matrix operations and loss functions in plain C

## When to choose
- you want to deeply understand neural networks and autograd internals
- you prefer learning through minimal, dependency-free C code
- you need a readable educational resource rather than a production framework

## When to avoid
- you need a production-ready, performant tensor library
- you require GPU acceleration or a mature ecosystem
- you need a licensed, stable library for real projects since it has no license and is experimental

## Facets
- artifact type: learning-resource
- maturity: experimental
- function: machine-learning, deep-learning, math
- domain: deep-learning, machine-learning, education, tutorials
- platform: c, cross-platform, cli
- tags: tensor-library, autograd, neural-networks, from-scratch, educational, no-dependencies

## Member repositories
- apoorvnandan/tensor.h (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:48.926080+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 2026-08-30T04:34:55.668557+00:00, confidence not recorded.
  - readme: https://github.com/apoorvnandan/tensor.h (fetched 2026-08-28T04:04:48.926080+00:00, sha cb65fcb16ef6)
- Data as of 2026-08-30T08:39:29.467469+00:00.