Description

<p align="center"> <img src="https://raw.githubusercontent.com/gepa-ai/gepa/refs/heads/main/assets/gepa_logo_with_text.svg" alt="GEPA Logo" width="450"> </p> <p align="center"> <strong>Optimize any text parameter — prompts, code, agent architectures, configurations — using LLM-based reflection and Pareto-efficient evolutionary search.</strong> </p> <p align="center"> <a href="https://gepa-ai.github.io/gepa/"><strong>Website</strong></a> &ensp;|&ensp; <a href="https://gepa-ai.github.io/gepa/guides/quickstart/"><strong>Quick Start</strong></a> &ensp;|&ensp; <a href="https://arxiv.org/abs/2507.19457"><strong>Paper</strong></a> &ensp;|&ensp; <a href="https://gepa-ai.github.io/gepa/blog/"><strong>Blog</strong></a> &ensp;|&ensp; <a href="https://discord.gg/WXFSeVGdbW"><strong>Discord</strong></a> </p> <p align="center"> <a href="https://pypi.org/project/gepa/"><img src="https://img.shields.io/pypi/v/gepa?logo=python&logoColor=white&color=3776ab" alt="PyPI"></a> <a href="https://pepy.tech/projects/gepa"><img src="https://static.pepy.tech/badge/gepa" alt="Downloads"></a> <a href="https://github.com/gepa-ai/gepa"><img src="https://img.shields.io/github/stars/gepa-ai/gepa?style=flat&logo=github&color=181717" alt="GitHub stars"></a> <a href="https://opensource.org/licenses/MIT"><img src="https://img.shields.io/badge/License-MIT-green?style=flat" alt="License"></a> </p> <p align="center"> <a href="https://join.slack.com/t/gepa-ai/shared_invite/zt-3o352xhyf-QZDfwmMpiQjsvoSYo7M1_w"><img src="https://badgen.net/badge/icon/Slack?icon=slack&label&color=4A154B" alt="Slack"></a> <a href="https://discord.gg/WXFSeVGdbW"><img src="https://dcbadge.limes.pink/api/server/https://discord.gg/WXFSeVGdbW?style=flat" alt="Discord"></a> </p> --- ## What is GEPA? **GEPA** (Genetic-Pareto) is a framework for optimizing any system with textual parameters against any evaluation metric. Unlike RL or gradient-based methods that collapse execution traces into a single scalar reward, GEPA uses LLMs to *read* full execution traces — error messages, profiling data, reasoning logs — to diagnose *why* a candidate failed and propose targeted fixes. Through iterative reflection, mutation, and Pareto-aware selection, GEPA evolves high-performing variants with minimal evaluations. **If you can measure it, you can optimize it**: prompts, code, agent architectures, scheduling policies, vector graphics, and more. ### Key Results | | | |---|---| | **90x cheaper** | Open-source models + GEPA beat Claude Opus 4.1 at [Databricks](https://www.databricks.com/blog/building-state-art-enterprise-agents-90x-cheaper-automated-prompt-optimization) | | **35x faster than RL** | 100–500 evaluations vs. 5,000–25,000+ for GRPO ([paper](https://arxiv.org/abs/2507.19457)) | | **32% → 89%** | ARC-AGI agent accuracy via [architecture discovery](https://gepa-ai.github.io/gepa/blog/introducing-optimize-anything/#5-agent-architecture-discovery) | | **40.2% cost savings** | Cloud scheduling policy [discovered by GEPA](https://gepa-ai.github.io/gepa/blog/introducing-optimize-anything/#3-systems-research), beating expert heuristics | | **55% → 82%** | Coding agent resolve rate on Jinja via [auto-learned skills](https://gepa-ai.github.io/gepa/blog/automatically-learning-skills-for-coding-agents/) | | **50+ production uses** | Across Shopify, Databricks, Dropbox, OpenAI, Pydantic, MLflow, Comet ML, and [more](https://gepa-ai.github.io/gepa/guides/use-cases/) | > *"Both DSPy and (especially) **GEPA are currently severely under hyped** in the AI context engineering world"* — **Tobi Lutke**, CEO, Shopify --- ## Installation ```bash pip install gepa ``` To install the latest from `main`: ```bash pip install git+https://github.com/gepa-ai/gepa.git ``` --- ## Quick Start ### Simple Prompt Optimization Optimize a system prompt for math problems from the AIME benchmark in a few lines of code ([full tutorial](https://dspy.ai/tutorials/gepa_aime/)): ```python import gepa trainset, valset, _ = gepa.examples.aime.init_dataset() seed_prompt = { "system_prompt": "You are a helpful assistant. Answer the question. " "Put your final answer in the format '### <answer>'" } result = gepa.optimize( seed_candidate=seed_prompt, trainset=trainset, valset=valset, task_lm="openai/gpt-4.1-mini", max_metric_calls=150, reflection_lm="openai/gpt-5", ) print("Optimized prompt:", result.best_candidate['system_prompt']) ``` **Result:** GPT-4.1 Mini goes from 46.6% → 56.6% on AIME 2025 (+10 percentage points). ### With DSPy (Recommended for AI Pipelines) The most powerful way to use GEPA for prompt optimization is within [DSPy](https://dspy.ai/), where it's available as `dspy.GEPA`. See [dspy.GEPA tutorials](https://dspy.ai/tutorials/gepa_ai_program/) for executable notebooks. ```python import dspy optimizer = dspy.GEPA( metric=your_metric, max_metric_calls=150, reflection_lm="openai/gpt-5", ) optimized