doganarif/promptpilot

A fast, lightweight CLI tool for versioning, testing, and optimizing your AI prompts across multiple providers. Easily track prompt evolution, run A/B tests, and measure performance without Git dependencies. Supports OpenAI, Claude, Llama, and HuggingFace.

41
/ 100
Emerging

This tool helps AI engineers, prompt engineers, and product managers refine the instructions given to large language models (LLMs). You input different versions of a prompt and a test text, and it shows you which prompt generates the best response based on quality and token usage across providers like OpenAI, Claude, and Llama. This allows you to continuously improve how your AI applications interact with users.

No commits in the last 6 months.

Use this if you are regularly creating and iterating on prompts for AI models and need a structured way to track changes, compare performance, and ensure your prompts are optimized for cost and quality.

Not ideal if you only use simple, static prompts that rarely change or if you prefer to manage all your prompt iterations manually without automated testing.

prompt-engineering AI-application-development LLM-testing AI-workflow-optimization generative-AI
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

71

Forks

11

Language

Python

License

MIT

Last pushed

Apr 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/doganarif/promptpilot"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.