Autograd
/All repositories
Overview
HEALTH SCORE
Excellent*
Partial score (2/3 categories)
59out of 65
Strong maintainer coverage. Development cadence is the only remaining gap. Security & Supply Chain is unavailable, so weights were redistributed.
LIFECYCLE
Active
Consistent commits, responsive maintainers, regular releases, and healthy issue triage.
Health breakdown
Excellent*(59/65)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
Median response time is 0 days.
Bus factor
5 active maintainers currently have merge rights.
Organization Diversity
Contributors span 67 organizations.
Project Achievements
Leaderboards
About
Autograd is a Python library that automatically differentiates native Python and NumPy code. It can compute derivatives of arbitrary Python/NumPy functions through the use of reverse-mode differentiation (a.k.a. backpropagation). The library is particularly useful for gradient-based optimization in machine learning and other scientific computing applications.
First commit
Software value
$325K
License(s)
MIT
Links
Data sources
Git
GitHub