Deploy and Host Chatty on Railway

Chatty is a free, open-source AI agent platform built for small business owners. Create custom AI agents with their own personality, knowledge, and tools — powered by your own API keys. No SaaS fees, no vendor lock-in. Supports Anthropic, OpenAI, Google Gemini, and Ollama.

About Hosting Chatty

Deploying Chatty on Railway takes about 5 minutes. Click the deploy button, set a login password, and Railway handles the rest — building the Docker image, provisioning persistent storage, and giving you a public URL. Once deployed, log in and paste your AI provider API key in the setup wizard. Your data is stored on a persistent volume so it survives redeploys and updates. No external database, Redis, or additional services required — Chatty runs as a single container with SQLite.

Common Use Cases

Customer-facing AI assistant — Create a branded chatbot with your company name, logo, and accent color that knows your business
Internal knowledge agent — Upload documents, SOPs, and FAQs to give your team an AI assistant that answers questions with company-specific context
Multi-channel support — Connect agents to WhatsApp, Telegram, Gmail, and Google Calendar to handle customer conversations and scheduling across platforms

Dependencies for Chatty Hosting

AI provider API key — At least one of: Anthropic, OpenAI, Google Gemini, or a local Ollama instance
Railway Hobby plan — $5/month (includes $5 usage credit, typically covers a single-user instance)

Deployment Dependencies

Anthropic API — Create an API key for Claude models
OpenAI API — Create an API key for GPT models
Google AI Studio — Create an API key for Gemini models
Chatty Documentation — Full deployment guide with environment variables, custom domains, and troubleshooting

Why Deploy Chatty on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.