meta-evolution

MetaDE is a GPU-accelerated evolutionary framework that optimizes Differential Evolution (DE) strategies via meta-level evolution. Supporting both JAX and PyTorch, it dynamically adapts mutation and crossover strategies for efficient large-scale black-box optimization.

Evolutionary Computation: A Modern Perspective |<...>| This is an online book, which is free-access and actively-updated (1st Edition: from 2023 to 2027).

Official Implementation of VisualClaw: A Real-Time, Personalized Agent for the Physical World

元构·智能生命体（MetaGO Intelligent Lifeform）— 守律·进化·可溯的智能体运行时。114 技能 · 35 专家子智能体 · 927 算法 · 43 公理 · 47 属性 · 597 原子 · 11 平台适配 · 3 个 DSH 原生插件 · Engine 2.1.5

The code for paper "AutoPSO: A Meta-Framework for Automated Particle Swarm Optimization"

Next evolution of grounded evolution: evolves full agent blueprints (system prompt + tools + memory + planning + self-evaluation) using Docker sandboxing, multi-objective fitness, meta-evolution, and task specialization. Built using DeepSeek V4.

Quantum-enhanced framework uniting ancient wisdom with modern technology to transform AI interaction. Open-source system making complex simple through precise application of quantum principles. Free tools and frameworks.

Self-referential Darwin-style agent forge that evolves its own mutation operators, evaluators, and core components. Built with DeepSeek V4.

Revolutionary blockchain architecture applying quantum principles to create truly semantic distributed systems. Open-source implementation uniting ancient wisdom with cutting-edge technology. Free framework for building next-generation blockchain solutions with quantum-enhanced security and meaning preservation.

Evaluator-grounded autonomous prompt evolution. Genetic algorithms + runtime validation + meta-evolution to evolve prompts that generate better AI agent code. 150 generations, 862/1000 best score.