Agenta

Open-source LLM app testing and evaluation platform

Code & DevelopmentFreemium

Agenta is an open-source platform for building, testing, and evaluating LLM-powered applications. It provides a prompt playground for rapid experimentation, evaluation pipelines for measuring output quality, and a deployment layer for managing multiple prompt versions in production. Teams use Agenta to systematically compare prompts, models, and parameters so they can make data-driven decisions about their AI products.

Key Features

• ✓Prompt playground
• ✓A/B testing
• ✓Evaluation pipelines
• ✓Version management
• ✓Self-hostable
• ✓SDK integration