EvoX Ecosystem

A collection of libraries, tools, and projects designed to accelerate computation and optimization research.

Featured Project

Genesis

Genesis decomposes any project — from a blank slate to millions of lines of code — and drives it to completion. Every agent works in its own isolated, sandboxed Git worktree, so parallel execution scales without limits. Fully autonomous, from first idea to shipped software.

Visit the Genesis site

EvoX

A distributed GPU-accelerated evolutionary computation framework compatible with PyTorch.

EMI-Group/evox

AutoPSO

A meta-framework for automated Particle Swarm Optimization that automatically constructs PSO variants through black-box optimization on GPUs.

EMI-Group/autopso

EvoCmo

A fully tensorized, GPU-accelerated multi-population evolutionary algorithm for efficiently solving constrained multi-objective optimization problems (CMOPs).

785509490/EvoCmo

EvoCoCo

A multi-agent framework for semantics-guided automatic tensorization of evolutionary multiobjective optimization (EMO) software.

EMI-Group/evococo

EvoGit

A decentralized multi-agent framework that reimagines software development as a collaborative, evolutionary process.

BillHuang2001/evogit

EvoGO

A fully data-driven framework for black-box optimization, replacing manual heuristic operators by learning search behaviors from historical data.

EMI-Group/evogo

EvoGP

A fully GPU-accelerated Tree-based Genetic Programming (TGP) framework built on PyTorch.

EMI-Group/evogp

EvoMO

A GPU-accelerated library for evolutionary multiobjective optimization (EMO) via advanced tensorization.

EMI-Group/evomo

EvoNAS

A framework for neural architecture search, implemented with PyTorch. It supports supernet training, evolutionary multi-objective optimization, and seamless integration with modern computer vision training pipelines.

EMI-Group/evonas

EvoRL

A fully GPU-accelerated framework for Evolutionary Reinforcement Learning.

EMI-Group/evorl

EvoXBench

A platform offering instant benchmarking of evolutionary multi-objective optimization (EMO) algorithms in neural architecture search (NAS).

EMI-Group/evoxbench

iStratDE

A GPU-accelerated Differential Evolution framework that enhances performance through individual-level strategy diversity.

EMI-Group/istratde

MetaDE

An advanced evolutionary framework that dynamically optimizes the strategies and hyperparameters of Differential Evolution.

EMI-Group/metade

TensorNEAT

A JAX-based library for NeuroEvolution of Augmenting Topologies (NEAT) algorithms.

EMI-Group/tensorneat

Community

Join the EvoX developer community to contribute, learn, and get your questions answered.

DiscordBrowse and join discussions with Discord