# 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.

## Install

Copy the content below into your project:

## Quick Use

```bash
# Gemfile:
gem "ruby_llm-agents"
bundle install
rails generate ruby_llm_agents:install
rails db:migrate
rails ruby_llm_agents:doctor
```

## 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

---

<!-- ZH -->

## Quick Use

```bash
# Gemfile:
gem "ruby_llm-agents"
bundle install
rails generate ruby_llm_agents:install
rails db:migrate
rails ruby_llm_agents:doctor
```

## Intro

RubyLLM::Agents 是 Rails 引擎，用 DSL 构建可观测的 LLM agent：自动重试/降级、预算与成本统计、实时 dashboard；已验证 124★，更新于 2026-04-19。

**Best for:** 希望把 agent 的成本/tokens/耗时/错误等可观测能力直接内置在 Rails 应用里的团队

**Works with:** Ruby 3.1+ / Rails 7.0+，以及 RubyLLM 支持的模型提供商（README 列出 OpenAI/Anthropic/Gemini 等）

**Setup time:** 20-45 minutes

### Key facts (verified)

- GitHub：124 stars · 6 forks；最近更新 2026-04-19。
- 许可证：MIT；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中可对照的入口命令：`rails generate ruby_llm_agents:install`。

## Main

- 把 agent 当成应用代码：用 DSL 写成类，像 Rails 的其它组件一样进行 review、发布与运维。

- 上线前先跑 doctor：README 给出 `rails ruby_llm_agents:doctor` 用于验证配置与 provider key。

- 先把预算与成本打通：README 提到成本统计与预算控制；建议按环境/租户设置预算，避免上线后失控。

- 用评测 + 告警闭环：README 列出 evaluation 与 alerts 能力，用于长期量化质量并及时发现回归。

### Source-backed notes

- README 的 Quick Start 给出 Gemfile 安装与 `rails generate ruby_llm_agents:install`、`rails db:migrate` 步骤。
- README 展示 `rails ruby_llm_agents:doctor` 用于验证安装与配置，并可生成 demo agent。
- README 列出 Ruby/Rails 版本要求，并强调成本/耗时/错误等可观测能力。

### FAQ

- **需要数据库吗？**：需要；Quick Start 包含 `rails db:migrate`，dashboard 依赖持久化执行数据。
- **支持哪些模型提供商？**：README 说明它通过 RubyLLM 接入，并点名 OpenAI、Anthropic、Gemini 等（以 RubyLLM 支持为准）。
- **如何验证安装成功？**：按 README 运行 `rails ruby_llm_agents:doctor`。

## Source & Thanks

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


---
Source: https://tokrepo.com/en/workflows/rubyllm-agents-rails-engine-for-production-agents
Author: Agent Toolkit