ruby_llm-agents

I've been building a Rails engine for managing LLM-powered agents in production. The main problem it solves: you define agents with a Ruby DSL, and everything else — cost tracking, retries, fallbacks, circuit breakers, caching, multi-tenancy, and observability — is handled by a middleware pipeline. It ships with a mountable dashboard that shows execution history, spending charts (cost/tokens over time), per-agent stats, model breakdowns, and multi-tenant budget management with hard/soft enforcement. Works with OpenAI, Anthropic, Google, ElevenLabs via RubyLLM. Supports text agents, embedders, TTS, transcription, image generation, message routing, and agent-as-tool composition. v3.7, MIT licensed, ~4000 specs. Would appreciate feedback on the DSL design and middleware architecture

I built a Rails engine for building and managing LLM-powered agents. It wraps RubyLLM and adds the production infrastructure I kept rebuilding across projects: - Execution tracking with cost/token analytics - Reliability (retries, model fallbacks, circuit breakers) - Budget controls (daily/monthly limits per agent or tenant) - Workflow orchestration (pipelines, parallel, routers) - Real-time monitoring dashboard Example: class SearchAgent < ApplicationAgent model "gpt-4o" reliability do retries max: 3, backoff: :exponential fallback_models "gpt-4o-mini", "claude-3-5-sonnet" end param :query, required: true def user_prompt "Extract search intent from: #{query}" end end result = SearchAgent.call(query: "red shoes under $50") r