Rails Agent — Build AI agents in Rails like a walk in the park
The fullstack agentic platform for Rails. One gem install, chat in the dashboard, and we handle the code, infra and deploys — you focus on the business logic.
Works with Rails 7+ · Ruby 3.2+ · Cloud runtime included
Make AI agent development
a zero-knowledge task
for Rails developers.
You shouldn't have to become an AI engineer to add agentic features to your app. Rails Agent turns the Rails skills you already have into production-ready agents — one install, one chat, one deploy.
Zero AI knowledge
You don't need to understand LLMs, embeddings, or prompt engineering. If you can write Rails, you can ship agents.
Zero config
No API keys, no vector database, no Redis, no Vercel setup. Install the gem and we run the entire stack.
Vibe coding experience
Describe what you want in the dashboard chat. Rails Agent scaffolds the agent folder and writes the files in your repo.
Build to deploy to monitor
One platform covers the whole lifecycle: draft, test, ship, and watch — no separate tools to wire up.
Scalable agentic infra
Hosted runtime, autoscaling, retries, and tracing are included. We handle the hard parts so you don't have to.
Unified monitoring & debugging
Every trace, log, error, and cost is searchable in /agents. One place to understand every run.
You write the agent.
We run everything else.
No OpenAI account. No Anthropic account. No vector database, no Redis to provision, no Vercel setup. Rails Agent Cloud is the only thing you sign up for — and the only bill you pay.
Your job stops at describing how the agent behaves. Everything past that line is ours.
Models
GPT, Claude, Gemini — routed and paid for by us. No BYOK.
Vector store
Embed and retrieve knowledge. No pgvector, no Pinecone.
Queue & workers
Long-running tools, streaming, retries — all handled.
Deploys & scaling
Push once, we autoscale. Rollbacks in one click.
Traces & logs
Every run, every tool call, every token — searchable.
Secrets & auth
Store credentials once. Agents get them at runtime.
Your agent is a directory.
No YAML soup. No hidden config. Every agent is one folder inside your existing Rails app — and you can read it top to bottom in a minute.
- ▸app/agents/support/
- •agent.rb
- ▸tools/
- •memory.rb
- ▸knowledge/
- ▸evals/
- •prompt.md
generated by rails agent new support
Your agent is a folder
app/agents/support/One directory per agent. Everything it needs lives inside it — nothing hidden in config, nothing scattered across the repo.
The brain
agent.rbA plain Ruby class. Pick a model, write the instructions in English. That's the whole agent.
Things the agent can do
tools/Each file is one action — look up an order, send an email, refund a charge. Just Ruby methods on your existing models.
What it remembers
memory.rbPer-user, per-thread or per-org. We store it, back it up and expire it. You just say what to remember.
What it knows
knowledge/Drop in PDFs, markdown, or point at a database. We chunk, embed and retrieve — no vector DB to run.
How you know it works
evals/Example conversations with the answers you expect. Every change runs through them before shipping.
How it talks
prompt.mdThe system prompt in plain markdown. Edit it in the dashboard, commit it in git — same file, same source of truth.
Ship the same agent to every channel.
Slack, Teams, WhatsApp, a web widget, a cron job or a JSON endpoint — one command from the CLI or one click in the dashboard. Everything lives inside your agent's channels/ folder.
Slack
channels/slack.rb
Discord
channels/discord.rb
Web Chat
channels/web.rb
Google Chat
channels/google_chat.rb
Microsoft Teams
channels/teams.rb
channels/whatsapp.rb
HTTP API
channels/api.rb
Cron
channels/cron.rb
Twilio (SMS + Voice)
channels/twilio.rb
Linear
channels/linear.rb
GitHub
channels/github.rb
Telegram
channels/telegram.rb
From gem install to live agent, in an afternoon.
"I'll take it from here."
— Kip
- 01
Install once
bundle add rails-agent-stack, then rails agent install. The CLI adds the engine, scaffolds app/agents/, and opens your dashboard. No routes to edit.
- 02
Describe in plain English
Open /agents and chat: “an agent that answers refund questions and looks up orders.” No prompt engineering. No AI knowledge needed. It writes the folder in your repo.
- 03
Test and inspect
Talk to your agent live. Every response shows the tools it called, what it remembered, and why. Fix issues in the chat or the generated Ruby.
- 04
Deploy in one command
rails agent deploy. Your agent runs on Rails Agent Cloud — scaling, retries, tracing and model routing included. One bill, no infra to manage.
Everything you need for production agents
Durability, sandboxing, human-in-the-loop, and evals are built into the framework. Focus on building your agent.
Durable Execution
Workflows survive crashes and restarts. Every step is checkpointed. Agents park when waiting, resume on the next message.
Sandboxed Compute
Agents run code in isolated sandboxes. File system access, bash execution, and code, all fully isolated.
Multi-Channel Delivery
One agent codebase deploys to web chat, Slack, API, cron, CLI, and custom apps.
Human-in-the-Loop
Tools that need confirmation trigger approval gates. Sessions park until resolved, then resume seamlessly.
Subagents
Delegate specialized work to child agents with their own prompts, tools, and sandbox.
Evaluations
Define test suites with scoring rubrics. Run evals on every deployment and on a schedule.
Other Rails AI gems give you a client. We give you the whole platform.
RubyLLM and ActiveAgent are great libraries. But you still need AI knowledge, build the dashboard, and run the runtime yourself. Rails Agent ships the whole platform — no AI expertise required.
| Feature | Rails Agentus | RubyLLM | ActiveAgent | DIY (LangChain + glue) |
|---|---|---|---|---|
| Setup | One gem, one CLI command | Wire clients manually | Wire mailer-style classes | Python + YAML + glue |
| AI knowledge required | None — just Rails | You wire models & prompts | You wire models & prompts | Deep LLM & ops expertise |
| Dashboard included | ✓ | — | — | — |
| Build agents by chatting | ✓ | — | — | — |
| Hosted runtime | Included, one-command deploy | Bring your own | Bring your own | You build & run it |
| Traces, evals, monitoring | ✓ | — | — | Wire it yourself |
| Memory & knowledge (RAG) | Built-in, no vector DB | Wire pgvector yourself | Wire it yourself | Wire it yourself |
| Model neutral (OpenAI, Claude, Gemini) | ✓ | ✓ | ✓ | ✓ |
| Human-in-the-loop approvals | ✓ | — | — | DIY |
| Uses your Rails app as-is | ✓ | ✓ | ✓ | — |
| Time to first agent in prod | An afternoon | A week | A week | A month+ |
One bill. Inference included.
Pay per developer, plus a small margin on model spend. We handle the hosting, scaling, retries and cold-starts — you just ship agents.
Developer
For building and testing on the cloud sandbox.
- 1 workspace
- Cloud sandbox for dev & testing
- Full dashboard, traces and evals
- Community Discord
- Not for production traffic
Studio
Deploy agents to production on Rails Agent Cloud.
- Production hosted runtime
- Unlimited workspaces & environments
- Custom domains and secrets
- Traces, evals and human review
- Model spend at cost + small margin
Enterprise
For teams that need dedicated support and SLAs.
- Dedicated support & solutions engineer
- SSO / SAML, RBAC, audit logs
- SLA, region pinning, priority routing
- Security review and MSA
gem install rails-agent-stack
rails agent install
Two commands. A dashboard, a CLI and a hosted runtime. No AI course required — your first agent is live before your coffee gets cold.