Prompt Optimizer
A tool for iteratively optimizing, testing and comparing AI prompts across multiple models, available as a web app, desktop app, Chrome extension or Docker deployment.
Prompt Optimizer takes a prompt from manual writing, a template, a local import, or a shared Prompt Garden code, then optimizes it through one-click, multi-round iteration, supporting separate optimization modes for system prompts and user prompts. It can analyze a single result or compare multiple optimization results to help judge whether a change actually improved the prompt, and includes an advanced testing mode with context variable management, multi-turn conversation testing and function-calling support.
It supports mainstream text models including OpenAI, Gemini, DeepSeek, Grok, Zhipu AI, SiliconFlow and MiniMax, and can also optimize prompts for text-to-image and image-to-image generation with models such as Gemini and Seedream. Optimized prompts can be saved as reusable, versioned assets. The project describes its architecture as processing data on the client side, communicating directly with the chosen AI provider rather than through an intermediate server, and it supports the Model Context Protocol.
It is written in TypeScript.