GitHub Repository

A Rails agent framework for RubyLLM — define AI agents with prompts, schemas, caching, logging, cost tracking, and a built-in dashboard for monitoring LLM usage in production.

129 starsRuby

RubyLLM:Agents – A Rails engine for building and monitoring LLM agents

Name: RubyLLM:Agents – A Rails engine for building and monitoring LLM agents
Availability: InStock
Author: adham900

by adham900·Feb 26, 2026·4 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemSlick

Rails-native LLM agent DSL with built-in cost tracking and multi-tenant dashboard.

Strengths

•Middleware pipeline handles retries, fallbacks, circuit breakers, and caching automatically.
•Multi-provider support (OpenAI, Anthropic, Google, ElevenLabs) via RubyLLM abstraction.
•Complete observability: execution history, spending charts, per-agent stats, budget enforcement.

Weaknesses

•Narrow audience: only useful for Rails shops building agents specifically.
•Competes against LangChain, CrewAI, and framework-agnostic agent tools already mature.

Post Description

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