darwinian-evolver

You can optimize SQL queries using evolutionary search by running an LLM-driven loop that iteratively refines your query against a custom fitness function to produce a more efficient version.

LLM-driven evolutionary search for code optimization is a process that applies mutation and evaluation loops to your code snippets, systematically evolving them to improve performance based on a defined fitness metric.

Yes, you need an API key to run prompt engineering evolution loops, requiring one of OPENROUTER_API_KEY, ANTHROPIC_API_KEY, or OPENAI_API_KEY to process the LLM-driven mutations.

Yes, you can define a custom fitness function for regex pattern optimization by specifying your own organism, evaluator, and mutator within the evolutionary search loop.

Python version 3.11 or higher is required for LLM-driven evolutionary search, alongside git and uv, to execute the optimization loop environment.

The best way to automate prompt refinement against a fitness metric is using an evolutionary search loop that mutates and evaluates prompts iteratively, allowing continuous optimization until your target performance is achieved.