kieranklaassen/leva

LLM Evaluation Framework for Rails apps to be used with production data.

45
/ 100
Emerging

This framework helps product teams and machine learning engineers fine-tune and improve their AI models built into Ruby on Rails applications. It takes your existing application data and an AI model's outputs, then lets you systematically evaluate how well the AI performs on real-world scenarios. This allows you to continuously refine the AI's prompts and logic, ensuring it delivers accurate and useful results for your users.

133 stars.

Use this if you are a product manager or an engineer running a Rails application with an integrated AI model and need a structured way to test and improve its accuracy against production data.

Not ideal if your application isn't built with Ruby on Rails, or if you don't have an existing AI model integrated into a production environment.

AI-model-evaluation prompt-engineering product-quality-assurance machine-learning-operations application-development
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

133

Forks

7

Language

HTML

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/kieranklaassen/leva"

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