Deploy and Host ariadne-core on Railway

Ariadne Core is an open-source document extraction and retrieval pipeline. It converts PDFs and 20+ other formats into clean Markdown and searchable vector embeddings, reducing frontier-LLM token costs by 20x per document. Connect from Claude Code, Cursor, or any MCP client.

About Hosting ariadne-core

Ariadne Core deploys as a single Docker container with a pgvector PostgreSQL database. It exposes both an MCP server and REST API on a single port. After deploying, fill in your API key from Google or OpenAI — the embedding model, vision model, and client authentication key are pre-configured with sensible defaults. Connect your AI tools using the generated domain URL and the auto-generated ARIADNE_API_KEY from your Variables tab.

Common Use Cases

Extract and search across hundreds of documents from Claude Code or any MCP client
Build agentic systems with semantic document retrieval and agent-writable metadata
Replace expensive frontier-model PDF parsing with a deterministic pipeline at ~$0.002/doc

Dependencies for ariadne-core Hosting

pgvector/pgvector:pg18 — PostgreSQL 18 with the pgvector extension for vector similarity search
Google Gemini or OpenAI API key — for embedding and optional image description

Deployment Dependencies

Why Deploy ariadne-core 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 ariadne-core 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.