---
title: "Deploy Moltis"
description: "A personal AI gateway written in Rust. One binary, no runtime, no npm."
category: "Other"
url: https://railway.com/deploy/moltis
---

# Deploy Moltis

A personal AI gateway written in Rust. One binary, no runtime, no npm.

**[Deploy Moltis on Railway](https://railway.com/template/moltis)**

- **Creator:** Techulus
- **Category:** Other
- **Total deploys:** 9

## Template content

### moltis https://raw.githubusercontent.com/moltis-org/moltis-website/main/favicon-512.svg

- **Image:** ghcr.io/moltis-org/moltis
- **Start command:** `moltis --bind 0.0.0.0 --port 8080 --no-tls`
- **Public domain:** Yes

## Documentation

# Deploy and Host Moltis on Railway

Moltis is a personal AI gateway written in Rust — a single binary with no runtime dependencies. It sits between you and multiple LLM providers (OpenAI Codex, GitHub Copilot, local models), offering streaming responses, tool execution in sandboxed containers, memory, hooks, and a built-in web UI.

## About Hosting Moltis

Deploying Moltis involves running its pre-built Docker image (`ghcr.io/moltis-org/moltis:latest`) with the `--no-tls` flag, since Railway handles TLS termination. Moltis needs persistent storage for its configuration and data (SQLite databases, session history, memory). On first run, a one-time setup code is printed to logs — you'll use it to set a password or register a passkey. You'll also want to set `MOLTIS_PASSWORD` as an environment variable for cloud auth. Note that sandboxed command execution requires Docker socket access, which isn't available on Railway — chat and tool-calling still work, but shell-based tools won't.

## Common Use Cases

- Running a private, multi-provider AI chat gateway accessible from anywhere with built-in authentication, session persistence, and a web UI
- Connecting to LLM providers with agent capabilities — tool calling, sub-agent delegation, web browsing, and memory-powered context injection
- Integrating AI into workflows via Telegram, webhooks, scheduled tasks, and MCP tool servers without managing complex infrastructure

## Dependencies for Moltis Hosting

- Pre-built Docker image: `ghcr.io/moltis-org/moltis:latest` (multi-arch: amd64/arm64)
- Persistent volume mounted at `/data`

### Deployment Dependencies

- [Moltis GitHub Repository](https://github.com/moltis-org/moltis)
- [Moltis Cloud Deploy Docs](https://docs.moltis.org/cloud-deploy.html)
- [Moltis Website](https://moltis.org)

### Implementation Details

Set the following environment variables in your Railway service:

```
MOLTIS_PASSWORD=your-secure-password
```

The start command binds to all interfaces on port 8080 with TLS disabled (Railway handles TLS termination):

```
moltis --bind 0.0.0.0 --port 8080 --no-tls
```

Mount a persistent volume at `/data` to preserve configuration, databases, sessions, and memory across deployments.

## Why Deploy Moltis 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 Moltis 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

- [Rocky Linux](https://railway.com/deploy/rocky-linux) — Hosted Rocky Linux 9 workspace with SSH and persistent storage. 🚀
- [Foundry Virtual Tabletop](https://railway.com/deploy/X5tR6G) — A Self-Hosted & Modern Roleplaying Platform
- [Letta Code Remote](https://railway.com/deploy/letta-code-remote) — Run a Letta Code agent 24/7. No inbound ports, just deploy.

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