---
title: "Deploy Langflow"
description: "Drag-and-drop interface for building AI-powered agents and workflows."
category: "AI/ML"
url: https://railway.com/deploy/LcJLmZ
---

# Deploy Langflow

Drag-and-drop interface for building AI-powered agents and workflows.

**[Deploy Langflow on Railway](https://railway.com/template/LcJLmZ)**

- **Creator:** alphasec
- **Category:** AI/ML
- **Total deploys:** 1,295

## Template content

### Langflow

- **Image:** langflowai/langflow:latest
- **Public domain:** Yes

### Postgres https://devicons.railway.app/i/postgresql.svg

- **Image:** ghcr.io/railwayapp-templates/postgres-ssl:latest

## Documentation

# Deploy and Host Langflow on Railway

Langflow is an open-source visual platform for building, testing, and deploying AI workflows and agents. It provides a drag-and-drop canvas for connecting LLMs, prompts, memory, tools, vector databases, and APIs into production-ready pipelines — no coding required to prototype, coding-friendly when you need it.

## About Hosting Langflow

Langflow is a Python application served via Docker. This Railway template deploys the official Docker image, alongside a Railway-provisioned PostgreSQL service for production-grade storage. Langflow is available on a Railway-provided HTTPS domain immediately after deployment. On first launch, the setup wizard creates an initial admin account.

## Common Use Cases

- **Visual AI workflow prototyping** — build and test LLM pipelines by connecting components (models, prompts, memory, tools, vector stores) on a drag-and-drop canvas without writing boilerplate code
- **RAG pipeline development** — prototype and iterate on retrieval-augmented generation pipelines with support for popular vector databases like Pinecone, Weaviate, Chroma, and PostgreSQL with pgvector
- **Agent deployment** — build, test, and expose AI agents as REST API endpoints using Langflow's built-in API server, consumable from any external application

## Dependencies for Langflow Hosting

- [Langflow Docker image](https://hub.docker.com/r/langflowai/langflow)
- PostgreSQL — provision a Railway PostgreSQL service

### Deployment Dependencies

- [Langflow GitHub repository](https://github.com/langflow-ai/langflow)
- [Langflow documentation](https://docs.langflow.org/)
- [alphasec guide: Prototype LangChain Flows Visually with LangFlow](https://alphasec.io/prototype-langchain-flows-visually-with-langflow/)

### Implementation Details

The following environment variables are pre-configured by the template:
 
```env
LANGFLOW_PORT=7860                       # Default Langflow port
LANGFLOW_SECRET_KEY=     # Required: long random string for session signing
LANGFLOW_LOG_LEVEL=info
LANGFLOW_DATABASE_URL=${{Postgres.DATABASE_URL}}   # Auto-wired from Railway PostgreSQL service
```

## Why Deploy Langflow 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.

By deploying Langflow on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.

## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage.
- [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

Open this page in a browser: https://railway.com/deploy/LcJLmZ