PromptOn/prompton

Chat prompt template evaluation and inference monitoring

22
/ 100
Experimental

This tool helps professionals who build applications using large language models (LLMs) to refine how those models respond to user queries. It allows you to test different versions of your prompt templates and model settings to see which combinations generate the best results. You put in various prompt designs and model configurations, and it helps you understand which ones produce the most desired outputs for your end-users.

No commits in the last 6 months.

Use this if you need to systematically evaluate, A/B test, and continuously monitor the performance of your chat prompt templates and model configurations in a real-world setting.

Not ideal if you are looking for a simple, one-off prompt engineering playground and don't require structured testing, comparison, or long-term performance tracking.

LLM application development prompt engineering model evaluation A/B testing AI product management
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

MIT

Last pushed

Sep 24, 2025

Commits (30d)

0

Get this data via API

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

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