---
title: "Deploy OpenViking"
description: "Persistent memory and RAG for AI agents. Store context across sessions."
category: "AI/ML"
url: https://railway.com/deploy/openviking-aug-26-agent-memory
---

# Deploy OpenViking

Persistent memory and RAG for AI agents. Store context across sessions.

**[Deploy OpenViking on Railway](https://railway.com/template/openviking-aug-26-agent-memory)**

- **Creator:** judetelan's Projects
- **Category:** AI/ML
- **Total deploys:** 1

## Template content

### OpenViking

- **Source:** volcengine/OpenViking

## Documentation

# Deploy and Host OpenViking [Aug '26] on Railway

OpenViking stores memory, knowledge, and skills for AI agents. Your coding tools forget everything when they restart. This fixes that. Point your agent at this server and it reads and writes context over HTTP.

## About Hosting OpenViking

One service from the upstream repo. Builds from the Dockerfile. Data persists on a Railway volume. Railway handles HTTPS so the bundled Caddy proxy is not needed.

## Common Use Cases

- Persistent memory for Claude Code and Cursor across coding sessions
- Shared knowledge base multiple agents read from
- RAG context store your agents pull from while they work

## Dependencies for OpenViking Hosting

- Nothing external. The Docker image ships everything.

## Why Deploy OpenViking on Railway?

Railway handles the server so you just connect your agents. One click, one URL., persistent context.

## 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/openviking-aug-26-agent-memory