Deploy LibreChat + Meilisearch + RAG
LibreChat with Meilisearch search and a keyless RAG API for file chat
LibreChat
Just deployed
Meilisearch
Just deployed
MongoDB
Just deployed
Just deployed
VectorDB
Just deployed
Deploy and Host LibreChat on Railway
LibreChat is an enhanced, open-source ChatGPT clone that unifies OpenAI, Anthropic, Google, Azure, and local models behind one familiar chat interface. It adds agents, plugins, file uploads, multimodal conversations, and full-text search, giving teams a self-hosted, privacy-first alternative to commercial AI chat products.
About Hosting LibreChat
LibreChat is a Node.js and React application that stores users, conversations, presets, and messages in MongoDB and indexes messages in Meilisearch for fast search. Self-hosting normally means provisioning a database, standing up a search engine, generating four separate encryption and JWT secrets (the app refuses to boot without them), wiring every component over a private network, and mounting a volume so uploaded files survive restarts. This template does all of that wiring for you: it deploys LibreChat from the public GHCR image alongside MongoDB 8 and Meilisearch, generates the required hex secrets automatically, references the Meilisearch master key across services, and persists uploads on a Railway volume — a complete chat stack in a few minutes.
Common Use Cases
- Multi-provider AI chat — switch between OpenAI, Anthropic, Google, and local models in a single conversation, using your own API keys
- Team chat platform — self-hosted AI assistant with user registration, email login, and per-user conversation history
- Privacy-first deployments — keep prompts, files, and conversation data on infrastructure you control
- Agents and tooling — extend the assistant with plugins, code execution, and custom tool integrations
- Searchable knowledge base — Meilisearch-backed full-text search across every past message
Dependencies for LibreChat Hosting
- MongoDB 8 — primary datastore for users, conversations, presets, and messages (provisioned by this template)
- Meilisearch — full-text search index over message history (provisioned by this template)
- Persistent volume — stores user file uploads at
/app/uploads - LLM provider key (optional) — an OpenAI, Anthropic, or Google key to enable models account-wide; otherwise users supply their own in the UI
Deployment Dependencies
- LibreChat GitHub repository
- LibreChat documentation
- LibreChat environment variable reference
- Public LibreChat container image (GHCR)
- Meilisearch documentation
Why Deploy LibreChat 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 LibreChat on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. The MongoDB and Meilisearch services are pre-wired over Railway's private network, the four required encryption and JWT secrets are generated for you, and uploads persist on a managed volume. Host your servers, databases, AI agents, and more on Railway.
Template Content
LibreChat
ghcr.io/danny-avila/librechat:v0.8.7Meilisearch
getmeili/meilisearch:v1.35.1MongoDB
mongo:8.0.20VectorDB
pgvector/pgvector:pg16