The Infrastructure for Evolutionary AI Systems

Enabling intelligence to adapt, create, and evolve across digital and physical worlds.

Get StartedGitHub

Latest News

View All News
News

Genesis Continues Compiler Development Across a Model Handoff

A Genesis continuation experiment reports 1,820/1,820 retained LLVM SingleSource cases passing after development moved from GLM 5.2 to DeepSeek V4 Flash.

News

EvoX Compiler: An Explicit Tensor-Graph Stack Built with Genesis

Genesis’s EvoX Compiler case documents a Python tensor-graph compiler and runtime with NumPy, IREE, XLA and TVM execution paths.

Releases

EvoX v1.4.1 Release Note

A maintenance release correcting CMA-ES, DE variants, PSO, evolution strategies, tournament selection, and hypervolume calculation.

01Why Evolution

The Power of Evolution

Evolution is nature's most proven way to create intelligence. EvoX brings that loop to AI: generate many candidates, test them for real, keep what works, and build on it — so capability compounds through experiment instead of hand-tuning.

An animated evolution cycle: generate, execute, evaluate, select, and improve.

02Applications

Evolution Across AI Paradigms

From models to agents, robots, and scientific discovery — one evolutionary loop, applied wherever intelligence needs to adapt.

01

Generative AI

Evolving the models themselves — merging expert models, optimizing generation, and searching new architectures.

EvoGM · Evolutionary model merging
02Featured

Agentic AI

Recursive agents that decompose, build, and evolve entire codebases — from a blank repository to shipped software.

Genesis · Recursive agentic system
03

Physical AI

Evolving robot control policies through massively parallel interaction with simulated environments.

EvoRL · Evolutionary reinforcement learning
04

AI for Science

Data-driven black-box optimization for scientific and engineering design, validated on supercritical airfoils.

EvoGO · Supercritical airfoil design

03Hardware

Computing Without Boundaries

Turn batches of complex tasks into tensor computation.

  1. 01Batched complex tasks

  2. 02EvoX · Tensorization

  3. 03Heterogeneous computing

    CPU
    GPU
    Accelerator
  • NVIDIA GPUSupported
  • AMD GPUSupported via ROCm
  • VulkanSupported via EvoX Compiler
  • Apple SiliconSupported via MPS
  • Huawei AscendProject-level validation
  • CPUSupported
  • DistributedExperimental

04Resources

Explore EvoX

Featured Project

Genesis

Watch software evolve autonomously

01

Ecosystem

Libraries for optimization, RL, GP, NAS, and more

02

Documentation

Guides, tutorials, and API reference

03

GitHub

Star, fork, and contribute to the source