ActiveGenie 🧞♂️
The Lodash for GenAI: Real Value + Consistent + Model-Agnostic
ActiveGenie is a developer-first library for GenAI workflows, designed to help you compare, rank, and score LLM outputs with consistency and model-agnostic flexibility. Think of it as the Lodash for GenAI: built for real value, consistent results, and freedom from vendor lock-in. It solves the biggest pain in GenAI today: getting predictable, trustworthy answers across use cases, models, and providers.
Behind the scenes, a custom benchmarking system keeps everything consistent across LLM vendors and versions, release after release.
For full documentation, visit activegenie.ai.
Installation
- Add to your Gemfile:
gem 'active_genie'
- Install the gem:
bundle install
- Generate the configuration:
echo "ActiveGenie.load_tasks" >> Rakefile
rails g active_genie:install
- Configure your credentials in
config/initializers/active_genie.rb
:
ActiveGenie.configure do |config|
config.providers.openai.api_key = ENV['OPENAI_API_KEY']
end
Quick start example
Extract structured data from text using AI-powered analysis, handling informal language and complex expressions.
text = "Nike Air Max 90 - Size 42 - $199.99"
schema = {
brand: {
type: 'string',
enum: ["Nike", "Adidas", "Puma"]
},
price: {
type: 'number',
minimum: 0
},
size: {
type: 'number',
minimum: 35,
maximum: 46
}
}
result = ActiveGenie::DataExtractor.call(
text,
schema,
config: { provider: :openai, model: 'gpt-4.1-mini' } # optional
)
# => {
# brand: "Nike",
# brand_explanation: "Brand name found at start of text",
# price: 199.99,
# price_explanation: "Price found in USD format at end",
# size: 42,
# size_explanation: "Size explicitly stated in the middle"
# }
Documentation
For full documentation, visit activegenie.ai.
Contributing
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature
) - Commit your changes (
git commit -m 'Add amazing feature'
) - Push to the branch (
git push origin feature/amazing-feature
) - Open a Pull Request
License
This project is licensed under the Apache License 2.0 License - see the LICENSE file for details.