Active Agent: Build AI in Rails

Agents

Controllers for AI. Define actions, use callbacks, render views. Rails conventions for LLM interactions.

🔧

Tool Calling

AI calls Ruby methods to fetch data and make decisions. Works like RPC for agents.

📊

Structured Output

Extract typed data with JSON schemas. Validated responses for forms and APIs.

🏭

Providers

OpenAI, Anthropic, Ollama, OpenRouter. Switch providers with one line of code.

📡

Streaming

Real-time response streaming with callbacks for dynamic UIs and live updates.

🎯

Embeddings

Generate vectors for semantic search, RAG, and clustering applications.

🧪

Testing

Test with fixtures and VCR cassettes. Mock providers for fast tests.

⏳

Background Jobs

Process generations async with Active Job. Scale AI operations in the background.

🛡️

Error Handling

Automatic retries with exponential backoff. Graceful degradation for production.