GEPAzilla

Web · Self-hosted · API

Freedom report

One barScore 5.3

GEPAzilla is ranked #17 of 29 in AI prompt generators on Freedom251. It runs on API, Self-hosted, Web.

Compared on AI prompt generators

Purpose: GEPAzilla is an open-source GEPA prompt optimizer that iterates on system prompts using datasets and scorers.
Dataset input: You can load your own dataset or start with the included sample dataset.
Scoring: It supports combining deterministic checks with LLM judges, with configurable scorer weights and duplicates.
Telemetry: The maker says run telemetry stays on your machine and includes tokens, routing, costs, and errors.
Validation: Validation rows are kept out of reflection and used to rank candidate prompts on the Pareto frontier.
Diagnostics: Results include scorer failure rates, averages, and common notes, alongside candidate prompts and iteration trends.
Model access: The project requires users to supply an AI Gateway API key for GEPA runs, scorer previews, and model discovery; its README specifies Vercel AI Gateway.
Data handling: The README says telemetry events are not sent to a remote service and run data is not exfiltrated.
Data import limit: Dataset tools currently support copying or pasting JSON payloads from the clipboard.
Deployment: The project is a standard Next.js application that can be built and started with pnpm.
License: The project is released under the MIT License.
Intended users: The maker describes the console as a way for curious builders to experiment with prompt optimization using their own API key.

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.