---
title: "Deploy Langflow on Bifrost: Visual AI Agent Builder, Any Model"
description: "Host Langflow on Bifrost: Visual AI Agent Builder, Any Model with Railway"
category: "AI/ML"
url: https://railway.com/deploy/langflow-on-bifrost-visual-ai-agent-buil
---

# Deploy Langflow on Bifrost: Visual AI Agent Builder, Any Model

Host Langflow on Bifrost: Visual AI Agent Builder, Any Model with Railway

**[Deploy Langflow on Bifrost: Visual AI Agent Builder, Any Model on Railway](https://railway.com/template/langflow-on-bifrost-visual-ai-agent-buil)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/langflow-on-bifrost-visual-ai-agent-buil/manifest.json

- **Creator:** Maxim AI's Projects
- **Category:** AI/ML
- **Total deploys:** 5

## Template content

### Langflow https://docs.langflow.org/img/langflow-icon-black-transparent.svg

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

### Bifrost https://www.getmaxim.ai/bifrost/brand-assets/bifrost-logo.svg

- **Image:** maximhq/bifrost:latest
- **Health check:** /health
- **Public domain:** Yes

### Postgres https://cdn.jsdelivr.net/gh/homarr-labs/dashboard-icons/svg/postgresql.svg

- **Image:** ghcr.io/railwayapp-templates/postgres-ssl:18

## Documentation

# Deploy and Host Langflow with Bifrost on Railway

Langflow is an open source visual builder for AI agents, RAG pipelines, and chat flows. This template runs Langflow on top of Bifrost, the open source AI gateway from Maxim AI, so every model node in your flows reaches 20+ providers through one OpenAI compatible endpoint, with failover, virtual keys, and request logs handled at the gateway.

## About Hosting Langflow with Bifrost

The stack runs three services: Langflow as the visual builder with its flows stored on a volume, Bifrost as the AI gateway, and Postgres as Bifrost storage for configuration and request logs. Langflow is pre wired to Bifrost through the OPENAI_API_BASE setting, so when you drop an OpenAI model component onto the canvas it already points at the gateway. After deploy, log in with the admin account, add a provider key in Bifrost under Model Providers, then in your flow set the model component API key to sk-bifrost and pick a model Bifrost serves. From then on you manage providers and keys in Bifrost instead of inside every flow.

## Common Use Cases

- Prototype AI agents and RAG flows visually, then swap providers without editing each flow.
- Give a team a shared visual builder with all model traffic logged and budgeted through one gateway.
- Fail over between providers automatically when one is degraded or hits a rate limit.

## Dependencies for Langflow with Bifrost Hosting

- Postgres for Bifrost configuration and request log storage.
- One or more model provider keys, added in the Bifrost dashboard after deploy.

### Deployment Dependencies

- Langflow: https://github.com/langflow-ai/langflow
- Bifrost docs: https://docs.getbifrost.ai
- Bifrost Docker Hub: https://hub.docker.com/r/maximhq/bifrost

### Why Deploy Langflow with Bifrost 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.

With Langflow and Bifrost on Railway, you get a private visual AI builder wired to every major provider in minutes, with cost control, failover, and logging built in.

## 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/langflow-on-bifrost-visual-ai-agent-buil