{"repo":"0xSanei/darwinia","free":true,"listed":false,"github":"https://github.com/0xSanei/darwinia","clone":"git clone https://github.com/0xSanei/darwinia.git","description":"The Self-Evolving Agent Ecosystem — Trading agents that evolve through Darwinian selection and adversarial self-play","language":"Python","stars":86,"topics":["adversarial-testing","ai-agents","autonomous-agents","backtesting","bitcoin","darwinian-evolution","evolutionary-computing","genetic-algorithm","multi-agent-system","openclaw"],"license":"MIT","category":"ai-agents","readme_excerpt":"🧬 Darwinia Give your AI agent the power to evolve its own trading strategies. Trading agents that discover strategies through Darwinian selection and adversarial self-play — not human-written rules. --- For OpenClaw / Claude Code agents Darwinia ships as an OpenClaw skill and Claude Code skill. Your agent can install it, run evolution, and report results — all through natural language. Manual skill installation OpenClaw: Claude Code: Auto-detected from .claude/SKILL.md in project root. --- The problem You hand-code RSI 70 = sell . Market regime changes. Strategy dies. You tweak parameters manually. Repeat forever. The Darwinia approach 50 agents with random DNA compete on real BTC data. The weak die. The strong breed. After 50 generations, survivors handle rug pulls, fake breakouts, and whipsaws — not because you told them to, but because agents that couldn't handle these attacks didn't survive to reproduce . --- Quick Start No API keys. No cloud. Just Python + numpy. BTC data included. Demo Output (click to expand) Evolution run: Adversarial arena test: --- How It Works Each generation: Compete → Survive attacks → Select → Breed → Mutate → Discover 17-Gene DNA Every trading decision lives in a genome: Category Genes Controls ---------- ------- ---------- Signal 5 What matters — momentum, volume, volatility, mean reversion, trend Threshold 4 When to act — entry/exit triggers, stop loss, take profit Personality 5 How to behave — risk appetite, time horizon, contrarian bias, p","default_branch":null,"files":null,"tree":[],"storefront":"/r/0xSanei","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/0xSanei/darwinia/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}