#mine see if potential averages in the fitness function are worth the overhead

Magpie (Machine Automated General Performance Improvement via Evolution of software)

Magpie: your software, but more efficient!

Introduction

Magpie is a tool for automated software improvement. It implements MAGPIE, using the genetic improvement methodology to traverse the search space of different software variants to find improved software.

Magpie provides support for improvement of both functional (automated bug fixing) and non-functional (e.g., execution time) properties of software.
Two types of language-agnostic source code representations are supported: line-by-line, and XML trees. For the latter we recommend the srcML tool with out-of-the-box support for C/C++/C# and Java.
Finally, Magpie also enables parameter tuning and algorithm configuration, both independently and concurrently of the source code search process.

LLM assited crossover

This version of magpie provides LLM assisted crossover. Use:

In your scenario files, the LLM-assisted crossover algorithm. Key settings include:

• algorithm = GeneticProgrammingLLM
• For documentation references in API calls:

  llm_documentation_path = /path/to/documentation

Requirements

• Unix (Linux/macOS/etc; untested on Windows)
• Python 3.8+

Try it now!

git clone https://github.com/bloa/magpie.git
cd magpie
python3 magpie local_search --scenario examples/triangle-c/_magpie/scenario_slow.txt

Documentation

Everything you need to know about Magpie.

Tutorials

• Quick start (start here!)
• Search for improved variants

How-to guides

• Write a custom fitness function

Explanations

• Project structure

Reference guides

• Entry points
• Fitness functions
• Scenario files
• Algorithm configuration model

Acknowledgements

Magpie is based on PyGGI 2.0, developed at COINSE KAIST in collaboration with UCL SOLAR.
Part of its development was supported by UK EPSRC Fellowship EP/P023991/1.

If you use Magpie for a publication, we kindly ask you to cite the following ArXiV paper that describes MAGPIE's approach:

@article{blot:2022:corr_1,
  author    = {Aymeric Blot and
               Justyna Petke},
  title     = {{MAGPIE:} {M}achine Automated General Performance Improvement via Evolution of Software},
  journal   = {Computing Research Repository},
  volume    = {abs/2208.02811},
  url       = {https://arxiv.org/abs/2208.02811},
  year      = {2022},
}