brennanmceachran/gepazilla
GEPAzilla: open-source GEPA prompt optimizer with datasets, scorers, and telemetry.
This tool helps AI developers and prompt engineers refine their large language model (LLM) system prompts. You input a dataset of examples and define various scoring criteria, including deterministic checks and LLM-powered judges. The system then automatically iterates on your prompt, tracking performance metrics like latency and cost, and outputs optimized prompt candidates.
Use this if you are an AI developer or prompt engineer struggling to optimize your LLM's performance and want an automated way to test and refine system prompts.
Not ideal if you are looking for a no-code solution or do not have a Vercel AI Gateway API key and some technical comfort with environment variables and local development.
Stars
25
Forks
2
Language
TypeScript
License
MIT
Category
Last pushed
Dec 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/brennanmceachran/gepazilla"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/promptflow
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
pezzolabs/pezzo
🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version...
cremich/promptz
Resource Library for AI-assisted software development with kiro
scafoldr/scafoldr
Building an open-source alternative to v0 and Lovable.
promptdesk/promptdesk
Promptdesk is a tool designed for effectively creating, organizing, and evaluating prompts and...