Active Agent
Build AI in Rails
Active Agents assist you, so you can focus on your product, and your customers don't even have to.
What's in the Box
Everything to build agents in Rails. Free forever.
Agents are Controllers
Actions, callbacks, views. Your agents speak Rails.
hover for code tap for codeclass TranslationAgent < ApplicationAgent
generate_with :openai, model: "gpt-4o"
def translate
prompt message: "Translate '#{params[:text]}' to #{params[:target_lang]}"
end
end
TranslationAgent.with(text: "Hello", target_lang: "es").translate.generate_now
docs/agents →
hover to flip back
tap to flip back
Action Prompt
Composable prompts. Like Action Mailer, but for AI.
hover for code tap for codedef summarize
prompt(
instructions: "Summarize in 2-3 sentences",
message: params[:text],
temperature: 0.3
)
end
SummaryAgent.with(text:).summarize.generate_now
docs/actions →
hover to flip back
tap to flip back
Any LLM
OpenAI, Anthropic, Ollama. Switch with one line.
hover for code tap for code# OpenAI
generate_with :open_ai, model: "gpt-4o"
# Anthropic
generate_with :anthropic, model: "claude-sonnet-4-5-20250929"
# Ollama (local)
generate_with :ollama, model: "llama3"
docs/providers →
hover to flip back
tap to flip back
Resilient by Default
Retries, backoff, graceful failures. Agents that don't give up.
hover for code tap for codeclass ReliableAgent < ApplicationAgent
generate_with :openai,
model: "gpt-4o",
retries: 3,
backoff: :exponential
on_error :handle_failure
end
docs/agents/retries →
hover to flip back
tap to flip back
Streaming
Real-time responses. Your agents think out loud.
hover for code tap for codeclass ChatAgent < ApplicationAgent
generate_with :openai, model: "gpt-4o", stream: true
on_stream :handle_chunk
def chat
prompt message: params[:message]
end
private
def handle_chunk(chunk)
print chunk.delta if chunk.delta
end
end
docs/streaming →
hover to flip back
tap to flip back
Structured Output
JSON schemas, typed data. Agents that follow instructions.
hover for code tap for codedef parse_resume
prompt(
message: "Extract: #{params[:data]}",
response_format: :json_schema
)
end
# Loads schema from views/agents/*/parse_resume.json
docs/structured_output →
hover to flip back
tap to flip back
Tool Calling
AI calls Ruby methods. Fetch data, take actions, make decisions.
hover for code tap for codedef weather_update
prompt(
message: params[:query],
tools: [{
name: "get_weather",
description: "Get weather for a location",
parameters: { type: "object", properties: {
location: { type: "string" }
}, required: ["location"] }
}]
)
end
def get_weather(location:)
# AI calls this method automatically
end
docs/tools →
hover to flip back
tap to flip back
MCP Support
Model Context Protocol. Connect agents to any MCP server.
hover for code tap for codegenerate_with :anthropic,
model: "claude-sonnet-4-5-20250929",
mcp_servers: {
filesystem: {
command: "npx",
args: ["-y", "@anthropic/mcp-fs"]
},
github: { url: "https://mcp.github.com" }
}
docs/mcp →
hover to flip back
tap to flip back
Background Jobs
ActiveJob integration. Run agents async, at scale.
hover for code tap for code# Queue for later
ApplicationAgent.prompt(message: "Analyze").generate_later
# With options
ApplicationAgent.prompt(message: "Report").generate_later(
queue: :reports,
wait: 5.minutes
)
# Configure queue at class level
self.generate_later_queue_name = :ai_tasks
docs/generation →
hover to flip back
tap to flip back
Observe Every Interaction
Trace, measure, and evaluate your agents. Built-in observability for production AI.
Measures semantic correctness of translation
Natural language flow and readability
Preservation of original meaning
The Gems
Give your Rails app an agent. MIT core, commercial extensions.
Ship your first agent today
Production-ready agents
activeagent-enterprise
Commercial License
Agents at scale
Gem Feature Comparison
| activeagent | activeagent-pro | enterprise | |
|---|---|---|---|
| Core Framework | |||
| Active Agent | |||
| Action Prompt | |||
| Generation Providers (RubyLLM, OpenAI, Anthropic) | |||
| Instrumentation, Error Handling, Retries | |||
| Streaming & Structured Output | |||
| Agent Management Web UI | |||
| Active Agent Pro | |||
| Observable Evaluations & Compliance | |||
| Generative UI & Generative Generators | |||
| Parallel tasks & advanced retries | |||
| HITL generative UI | |||
| Agentic workflows (pausable multi-agent) | |||
| Async tasks with external triggers | |||
| Agent rate limiting | |||
| Licensing | |||
| License type | MIT | Commercial | Commercial |
| Multi-app / embedded licensing | |||
| Custom terms | |||
| Support | |||
| Community (Discord, GitHub) | |||
| Email support | |||
| Priority support | |||
The Platform
See what your agents are up to. Hosted and monitored.
Watch
Traces, costs, latency. Know exactly what your agents are doing and what they cost.
Judge
LLM-as-judge evals, A/B testing. Let agents grade each other's work.
Ship
Team workspaces, dashboards, SSO. Built for teams shipping agents together.
Self-Hosted
For developers
Full control, your infrastructure
Pro Platform
For small/medium teams
Let us watch your agents so you don't have to
Enterprise Platform
For serious agent deployments
When your agents need enterprise-grade babysitting
Platform Feature Comparison
| Self-Hosted | Pro Platform | Enterprise | |
|---|---|---|---|
| Infrastructure | |||
| Web UI dashboard | Local | Hosted | Hosted |
| Agent deployments | Unlimited | 3 | Unlimited |
| Executions / month | Unlimited | 10,000 | Unlimited |
| Traces / month | Unlimited | 25,000 | 500,000+ |
| Trace retention | You control | 14 days | 400 days |
| Private VPC / on-premise | |||
| Agent rate limiting | |||
| Observability & Evaluation | |||
| Cost & latency analytics | |||
| LLM-as-judge evaluators | DIY | 5 prebuilt | Unlimited custom |
| A/B prompt testing | |||
| Anomaly detection (ML) | |||
| Team & Security | |||
| Team seats | Unlimited | 5 | Unlimited |
| Workspaces | Unlimited | 1 | Unlimited |
| SSO / SAML & RBAC | |||
| SOC 2 Type II & HIPAA | |||
| Support | |||
| Community support | |||
| Email support SLA | 48 hours | 4 hours | |
| Dedicated Slack channel | |||
Platform Add-Ons
Scale beyond your plan with usage-based pricing
Pro Add-Ons
Enterprise Add-Ons
Services
We'll help you ship agents faster
Workshops
$2,500 half-day | $4,500 full-day
Learn by building
Advisory
From $3,000/month
Expert on your team
Development
$250/hr or project-based
We ship, you own
FAQ
Common questions about Active Agent
How do I install Active Agent?
Add gem 'activeagent' to your Gemfile and run bundle install. Then run rails generate active_agent:install to set up the initial configuration.
What gems are included in the free tier?
The free tier includes the Active Agent gem, Action Prompt, and all Generation Provider modules (RubyLLM, OpenAI, Anthropic — both official and community gems). You also get Instrumentation, Error Handling, and Retries modules at no cost.
Which Generation Providers are supported?
Active Agent supports multiple providers through its Generation Providers module: RubyLLM, OpenAI (official and community gems), Anthropic (official and community gems), Ollama, and OpenRouter. Switch providers with one line of code.
What are the Reasonable Reasons gems in Pro?
The Reasonable Reasons gems are Pro-tier modules that include Observable Evaluations, Observable Compliance, Deterministically Generative, Generally Deterministic, Generative UI, and Generative Generators (with self-healing capabilities). These gems add advanced analytics and generative capabilities to your agents.
What's the difference between Community and Pro?
The Community (Dev) tier gives you full access to the open-source Active Agent gem, Action Prompt, all Generation Providers, and core modules (Instrumentation, Error Handling, Retries) — free forever. Pro ($99/mo or $995/yr) adds the Reasonable Reasons gems, HITL generative UI, parallel tasks & retries, agentic workflows with pausable multi-agent actions, async tasks with external triggers, hosted observability, and 48-hour email support SLA.
What are agentic workflows?
Agentic workflows in the Pro tier allow you to break complex tasks into many agents' actions, which can be paused between tasks. Combined with HITL generative UI and async tasks with external triggers (webhooks, human approval, timeouts), you can build sophisticated human-in-the-loop AI systems.
Can I use Active Agent with existing Rails apps?
Yes! Active Agent is designed to integrate seamlessly with existing Rails applications. It works alongside your existing models, controllers, and services.
Can I self-host Active Agent?
Absolutely! The core framework is MIT licensed and can be self-hosted without limits on any tier. The hosted services (observability, evaluation, collaboration) and Pro gems are what differentiate the paid tiers.
Start building agents today
Create your free account and deploy your first AI agent in minutes.
Free forever • No credit card required