ABMeter

# ABMeter > ABMeter is an AI-first platform for feature flagging and A/B experimentation. It provides a Ruby SDK (`abmeter` gem), a REST API, and an MCP server that lets AI assistants design, launch, and analyze experiments through natural conversation. Users interact with parameters in their code without knowing what experiments are running -- ABMeter handles variant assignment, exposure tracking, and statistical analysis. ## Docs - [Quick Start Guide](https://abmeter.ai/lab/quick-start): Get ABMeter running in your application in minutes - [Setup MCP Connection](https://abmeter.ai/lab/connect-mcp): Connect the ABMeter MCP server to your MCP client - [Setup Browser Link](https://abmeter.ai/lab/link-ai-assistant): Enable human-in-the-loop confirmations for critical operations - [API Documentation](https://abmeter.ai/lab/api-docs): Interactive OpenAPI documentation for the REST API ## API - [OpenAPI Specification](https://abmeter.ai/lab/api-docs/spec.yaml): Machine-readable OpenAPI 3.0 spec for all REST endpoints ## SDK - [abmeter gem on RubyGems](https://rubygems.org/gems/abmeter): Ruby SDK for feature flags and A/B testing - [SDK Source Code](https://github.com/abmeter/abmeter-ruby): SDK source repository ## Key Concepts - [Domain Model](https://abmeter.ai/llms-full.txt): Complete reference including Users, Spaces, Parameters, Variants, Experiments, Feature Flags, Audiences, Events, Metrics, Effects, and the Assignment Algorithm ## Optional - [Comprehensive Reference](https://abmeter.ai/llms-full.txt): Full documentation in a single file for LLMs with larger context windows