PyKAN (Kolmogorov-Arnold Networks)
/All repositories
Overview
HEALTH SCORE
Critical*
Partial score (2/3 categories)
19out of 65
Development cadence is the primary crisis signal. Maintainer coverage shows little to offset it. Every health signal is at or near zero. Security & Supply Chain is unavailable, so weights were redistributed.
LIFECYCLE
Abandoned
No maintainer activity in over 18 months.
Health breakdown
Critical*(19/65)
Maintainer availability, known risks and supply chain posture, and whether the project is actively developed or appropriately stable.
Maintainer responsiveness
No PRs or issues were opened in the review window, so response time could not be measured.
Bus factor
No data available. Repository has not been indexed for bus factor.
Organization Diversity
Contributors span 65 organizations.
Project Achievements
Leaderboards
About
PyKAN (Kolmogorov-Arnold Networks) is a Python library for implementing and training Kolmogorov-Arnold neural networks, which are universal function approximators based on Kolmogorov's superposition theorem. The project provides tools for constructing and experimenting with these specialized neural network architectures.
First commit
Software value
$2.5M
License(s)
MIT
Links
Data sources
Git
GitHub