evolutionary-ai

Infrastructure for evolutionary AI systems. GPU-accelerated, PyTorch-based optimization with an ecosystem of algorithm libraries, benchmarks, and tools.

Evolution for the Agent Era. Inspired by Darwin, an open framework for experience-driven recursive self-improvement of AI agents.

A genetic AI framework that evolves its own neural networks - modelled on how life actually evolves. Evolutionary Genetic AI that designs itself automatically (AutoML). The winners reproduce and they get better in every new generation.

Code evolution AI written in C++/CUDA optimized for GPU computation.

MYND Prompt Phylogeny — World's first prompt evolutionary lineage system. Biological phylogenetics applied to AI prompt engineering.

Forkling is the founding species of the Forkland family: a self-contained, self-improving AI agent whose substrate is git, whose evaluator is pytest, and whose family is opt-in.

MYND Prompt Phylogeny — Evolutionary Intelligence for Prompt Engineering. Production engine with Kubernetes, D3.js, pgvector.

Open-source evolutionary post-training lab powered by the Tinker API

Quality-Diversity (QD) MAP-Elites Evolutionary Growth Playbook Discovery Swarm. Illuminates multi-dimensional archives of phenotypic marketing elites to discover non-intuitive, high-performing compounding growth strategies.

Framework for AI Structural Philosophy, Royalty OS, and AI Structural Genetics in human-AI co-evolution.