# EMI-Group/evox

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

Repository: https://github.com/EMI-Group/evox
Canonical: https://ross.abutalabs.com/products/evox
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: evolutionary-algorithms, neuroevolution, gpu-acceleration, ray, brax, derivative-free-optimization, evolutionary-optimization, evolutionary-reinforcement-learinig, gradient-free-optimization, jax, metaheuristics, multi-objective-optimization, population-based-optimization, gym, black-box-optimization, evolutionary-computation, evolutionary-strategies, pytorch
Last push: 2026-07-09T03:25:00+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 91, release rhythm 55, longevity 100
- inputs: {"age_days": 1498, "days_push": 55, "days_rel": 300, "gap_med": 22.0, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2526, forks 336 (observed 2026-08-28T04:06:58.595952+00:00)

## What it is
EvoX is a distributed GPU-accelerated framework for evolutionary computation, compatible with PyTorch and built on JAX. It provides 50+ evolutionary algorithms and 100+ benchmark problems/environments for scalable population-based optimization.

## Use cases
- run particle swarm optimization on GPU
- solve multi-objective optimization problems
- neuroevolution for reinforcement learning environments
- benchmark evolutionary algorithms on standard test problems
- scale black-box derivative-free optimization across GPUs
- evolve neural network policies with Brax/Gym environments

## When to choose
- you need GPU-accelerated or distributed evolutionary algorithms
- you want a large library of EAs and benchmark problems in one framework
- you work in Python with JAX or PyTorch ecosystems

## When to avoid
- you need gradient-based optimization instead of population-based methods
- you need a permissively licensed library (GPL-3.0)
- you need a non-Python or CPU-only minimal tool

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, simulation, benchmarking, math
- domain: machine-learning, artificial-intelligence, reinforcement-learning, gpu-computing
- platform: python, cross-platform
- tags: evolutionary-computation, evolutionary-algorithms, neuroevolution, jax, pytorch, black-box-optimization, multi-objective-optimization, metaheuristics, distributed, algorithms, gpu

## Member repositories
- EMI-Group/evox (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.595952+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 2026-08-30T02:25:25.404031+00:00, confidence not recorded.
  - readme: https://github.com/EMI-Group/evox (fetched 2026-08-28T04:06:58.595952+00:00, sha 236e4b94bd31)
  - registry_pypi: https://pypi.org/pypi/evox/json (fetched 2026-08-29T10:07:53.111568+00:00, sha 7322c6aea068)
- Data as of 2026-08-30T08:39:29.467469+00:00.