Plain-AyI
← All projects
Developer building blocks

GEPA

A Python tool that uses AI to automatically improve prompts, code and other text by testing and refining them.

Widely usedResearch-backedNew this week

What it does

GEPA is a programming library for improving any piece of text that a system depends on, such as prompts (the instructions given to an AI model), code, or settings. You give it a starting version and a way to score how well it works, and it searches for better versions.

It works in rounds. It tries a version, records what happened (error messages, logs and reasoning), and then asks a large language model (LLM, the kind of AI behind chatbots) to read those records and explain why it failed. It then writes an improved version and keeps the best ones.

Its makers say it needs far fewer test runs than other training methods. It can be used on its own, through the DSPy framework, or as a skill that AI coding assistants like Claude Code can run for you.

Who it's for

Developers and researchers who build AI apps or agents and want to improve their prompts or code automatically against a score they can measure.

Can I use it without coding?

Developers only. You use it by writing Python code that defines what to optimise and how to score it. New to this? Start here.

Can I run it?

Cost
Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • Plain-AyI is an independent guide and doesn't host or review the software it lists. Please check each project's official page before installing.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it