# CodeReclaimers/neat-python

Python implementation of the NEAT neuroevolution algorithm

Repository: https://github.com/CodeReclaimers/neat-python
Canonical: https://ross.abutalabs.com/products/neat-python
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: neuroevolution, python
Last push: 2026-05-23T10:31:08+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 62, longevity 100
- inputs: {"age_days": 3994, "days_push": 102, "days_rel": 172, "gap_med": 49.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1578, forks 509 (observed 2026-08-28T04:05:06.695912+00:00)

## What it is
A pure-Python implementation of NEAT (NeuroEvolution of Augmenting Topologies), an algorithm for evolving neural network topologies and weights. It has no dependencies beyond the Python standard library and supports Python 3.8 through 3.14 plus pypy3.

## Use cases
- evolve neural network topologies with neuroevolution
- train neural networks using a genetic algorithm instead of backpropagation
- run NEAT experiments for reinforcement learning or control tasks
- evolve recurrent neural networks with CTRNN
- learn how the NEAT algorithm works in Python
- benchmark evolutionary algorithms on custom fitness functions

## When to choose
- you want to evolve neural network architectures rather than train fixed ones
- you need a dependency-free, pure-Python neuroevolution library
- you want a well-documented, actively maintained NEAT implementation with checkpointing and reporting
- your fitness function is non-differentiable, making gradient-based training unsuitable

## When to avoid
- you need GPU-accelerated training for large-scale deep learning
- you want gradient-based optimization like backpropagation on fixed architectures
- you need a high-performance implementation for very large populations, since pure Python is slow
- you need a general-purpose deep learning framework

## Facets
- artifact type: library
- maturity: active
- function: machine-learning
- domain: machine-learning, artificial-intelligence
- platform: python
- tags: neuroevolution, neat, genetic-algorithm, evolutionary-algorithm, neural-networks, pure-python

## Member repositories
- CodeReclaimers/neat-python (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:06.695912+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 2026-08-30T03:56:53.497666+00:00, confidence not recorded.
  - readme: https://github.com/CodeReclaimers/neat-python (fetched 2026-08-28T04:05:06.695912+00:00, sha 73c8477a60b9)
  - registry_pypi: https://pypi.org/pypi/neat-python/json (fetched 2026-08-29T11:27:10.571090+00:00, sha fe56cfa1fb59)
- Data as of 2026-08-30T08:39:29.467469+00:00.