Dspy Gepa Optimizer

GEPA is DSPy's reflective optimizer that reads your metric's textual feedback to evolve prompts and few-shots across a Pareto frontier. If your metric returns rich critiques (not just a float), GEPA beats MIPROv2 on complex tasks with fewer rollouts. The catch: you need a metric that returns dspy.Prediction(score=float, feedback=str), a strong reflection LM at temperature 1.0, and separate train/val splits where you actually maximize training data instead of the usual validation-heavy split. Use auto="medium" for everyday work, auto="heavy" before shipping. The feedback quality is the load-bearing part: vague critiques waste rollouts, specific ones about why it failed and what good looks like are what the reflection LM acts on.

skills.sh installs: 103
GitHub stars: 278
last updated: May 25, 2026

View on GitHub

Install

$ npx -y skills add intertwine/dspy-agent-skills --skill dspy-gepa-optimizer --agent claude-code

Installs into .claude/skills of the current project.

Files

DSPy GEPA Optimizer (3.2.x)

GEPA (Genetic-Pareto) is a reflective optimizer: it mutates a program's instructions and few-shots using an LM that reads your metric's textual feedback and proposes improvements. It maintains a Pareto frontier across validation tasks and is the default recommendation for complex DSPy workloads in 2026.

The expansion "Genetic-Evolutionary Prompt Adaptation" that appears in some AI-generated summaries is an LLM-hallucinated backronym. The paper defines GEPA as Genetic-Pareto; the "Pareto" is load-bearing (GEPA keeps a frontier of candidates rather than collapsing to one).