---
title: "Deploy letta-nightly"
description: "Deploy a Letta server (uses the nightly Letta Docker image)"
category: "AI/ML"
url: https://railway.com/deploy/_vKUnL
---

# Deploy letta-nightly

Deploy a Letta server (uses the nightly Letta Docker image)

**[Deploy letta-nightly on Railway](https://railway.com/template/_vKUnL)**

- **Creator:** Charles Packer's Projects
- **Category:** AI/ML
- **Total deploys:** 17

## Template content

### letta/letta:nightly

- **Image:** letta/letta:nightly
- **Health check:** /v1/health/
- **Public domain:** Yes

## Documentation

### Letta

👾 Letta is an open source framework for building stateful LLM applications. You can use Letta to build stateful agents with advanced reasoning capabilities and transparent long-term memory. The Letta framework is white box and model-agnostic.

For more information see: https://github.com/letta-ai/letta

### Usage

1. Deploy the Railway template.
2. To use the Letta ADE, go to https://app.letta.com and connect to a remote development server. Use the IP address exposed by Railway as the server URL, and use the password set in the "Variables" section of your Railway deployment.
3. The Letta server will need to be configured with at least one LLM API provider, to do so set your environment variables (e.g. `OPENAI_API_KEY`) in the "Variables" section.

## 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/_vKUnL