SkillsMay 14, 2026·2 min read

RubyLLM::Agents — Rails Engine for Production Agents

Rails engine for building and monitoring LLM agents with a DSL, retries/fallbacks, cost analytics, and a dashboard; verified 124★, pushed 2026-04-19.

Agent Toolkit
Agent Toolkit · Community
Agent ready

Review-first install path

This asset needs a review step. The copied prompt tells the agent to dry-run, show the writes, then proceed only after confirmation.

Needs Confirmation · 66/100Policy: confirm
Agent surface
Any MCP/CLI agent
Kind
Skill
Install
Single
Trust
Trust: Established
Entrypoint
Asset
Review-first command
npx -y tokrepo@latest install a1d6b7ef-39c8-5431-8d8e-9b8f803d49bd --target codex

Dry-run first, confirm the writes, then run this command.

Intro

Rails engine for building and monitoring LLM agents with a DSL, retries/fallbacks, cost analytics, and a dashboard; verified 124★, pushed 2026-04-19.

Best for: Rails teams who want agent observability (cost/tokens/duration/errors) baked into their app

Works with: Ruby 3.1+ / Rails 7.0+ and RubyLLM-supported providers (README lists OpenAI/Anthropic/Gemini, etc.)

Setup time: 20-45 minutes

Key facts (verified)

  • GitHub: 124 stars · 6 forks · pushed 2026-04-19.
  • License: MIT · owner avatar + repo URL verified via GitHub API.
  • README-backed entrypoint: rails generate ruby_llm_agents:install.

Main

  • Keep agents as application code: define agents as classes with a DSL and treat them like any other Rails component (jobs/models/routes).

  • Use the built-in “doctor” task to validate provider keys and configuration before shipping the dashboard to prod.

  • Gate spend early: README highlights cost analytics and budget controls; set budgets per environment or tenant before onboarding users.

  • Use evaluation + alerts as your feedback loop: README lists evaluation and alerting features to keep quality measurable over time.

Source-backed notes

  • README Quick Start shows installing via Gemfile + rails generate ruby_llm_agents:install + rails db:migrate.
  • README shows verifying setup via rails ruby_llm_agents:doctor and generating a demo agent.
  • README lists requirements (Ruby >=3.1, Rails >=7.0) and highlights observability (cost/tokens/duration/errors).

FAQ

  • Do I need a database?: Yes — Quick Start includes rails db:migrate and the dashboard relies on persisted execution data.
  • Which providers are supported?: README states it works through RubyLLM and names OpenAI, Anthropic, Gemini, and others supported there.
  • How do I verify my install?: Run rails ruby_llm_agents:doctor as shown in README.
🙏

Source & Thanks

Source: https://github.com/adham90/ruby_llm-agents > License: MIT > GitHub stars: 124 · forks: 6

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

InvokeAI — Professional Creative Engine for Stable Diffusion

A leading open-source creative engine for Stable Diffusion and Flux models with a polished WebUI, node-based workflows, and production-grade image generation.

Skills
Script Depot

KoboldCpp — Single-File Local LLM Inference Engine

KoboldCpp is a self-contained local LLM inference engine that runs GGUF models with GPU acceleration on consumer hardware, providing an OpenAI-compatible API and built-in web UI without requiring Python or complex setup.

Skills
Script Depot

Quickwit — Cloud-Native Sub-Second Search Engine

Quickwit is a cloud-native search engine built in Rust for log management and distributed search on object storage. It indexes data directly to S3-compatible stores, enabling cost-efficient search at petabyte scale.

Skills
Script Depot

nano-vllm — Lightweight LLM Serving Engine

nano-vllm is a minimal, educational, and performant LLM inference engine that reimplements core vLLM concepts in clean Python for easy understanding and extension.

Skills
AI Open Source
◈Home🔍Search👤Me