---
title: "Deploy robinwiki"
description: "Fullstack deployment of the Robin Second brain and Wiki"
category: "AI/ML"
url: https://railway.com/deploy/robinwiki
---

# Deploy robinwiki

Fullstack deployment of the Robin Second brain and Wiki

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

- **Creator:** Determined Mustard's Projects
- **Category:** AI/ML
- **Total deploys:** 77

## Template content

### Redis https://cdn.sanity.io/images/sy1jschh/production/0ce0bfdcfbdbf69662b1116671f97c2dd788b655-157x157.svg

- **Image:** redis:8.2.1
- **Start command:** `/bin/sh -c "rm -rf $RAILWAY_VOLUME_MOUNT_PATH/lost+found/ && exec docker-entrypoint.sh redis-server --requirepass $REDIS_PASSWORD --save 60 1 --dir $RAILWAY_VOLUME_MOUNT_PATH"`

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

- **Image:** pgvector/pgvector:pg17

### @robin/wiki

- **Source:** https://github.com/withrobinhq/robinwiki
- **Start command:** `pnpm --filter @robin/wiki start`
- **Public domain:** Yes

### @robin/core

- **Source:** https://github.com/withrobinhq/robinwiki
- **Start command:** `pnpm --filter @robin/core start`
- **Public domain:** Yes

## Documentation

# Deploy and Host robinwiki on Railway

robinwiki is an AI-powered second brain. You talk to your
  AI client (Claude Desktop, Cursor, anything that speaks
  MCP); robinwiki listens in the background, extracts atomic ideas, classifies them into wikis, and builds a searchable knowledge base in Postgres. No manual organising.

## About Hosting robinwiki

robinwiki runs as two services: a Node.js core that handles auth, the API, the MCP server, and the background pipeline that processes ingested content; and a Next.js wiki for browsing and editing. Storage is Postgres with the pgvector extension for embedding-based search. BullMQ on Redis runs the extraction and classification workers. You'll need an OpenRouter API key for the LLM calls. The server is single-user one operator, one deployment and refuses to boot in production until every required secret is set, so configuration is intentional rather than accidental.

## Common Use Cases

  - Personal second brain capture thoughts during AI
  conversations, return to them later as structured,
  interconnected wikis.
  - Solo research workspace feed long documents,
  transcripts, or article dumps and let robinwiki extract
  atomic ideas and group them by topic.
  - Long-term project memory track decisions, beliefs,
  people, and projects across years without manual filing.

## Dependencies for robinwiki Hosting

  - PostgreSQL 17 with the `pgvector` extension (HNSW indexes
   power semantic search)
  - Redis (BullMQ background workers)
  - OpenRouter API key (LLM extraction, classification,
  embeddings)

  ### Deployment Dependencies

  - pgvector — https://github.com/pgvector/pgvector
  - OpenRouter — https://openrouter.ai/
  - robinwiki source —
  https://github.com/withrobinhq/robinwiki

  ### Implementation Details

Generate every required secret before deploying. robinwiki refuses to boot in production until each of these is set:

  ```bash
  # 32+ byte hex secrets
  openssl rand -hex 32   # BETTER_AUTH_SECRET
  openssl rand -hex 32   # MASTER_KEY
  openssl rand -hex 32   # KEY_ENCRYPTION_SECRET
  openssl rand -hex 32   # RECOVERY_SECRET
  openssl rand -hex 32   # JOB_SIGNING_SECRET
  ```

Plus: `WIKI_ORIGIN` (your wiki frontend URL, must start
 with `https://`), `SERVER_PUBLIC_URL` (your core API URL, also `https://`), `INITIAL_USERNAME`, `INITIAL_PASSWORD`,
 `OPENROUTER_API_KEY`. Postgres and Redis URLs are wired automatically by Railway.

## Why Deploy robinwiki 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 robinwiki 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/robinwiki