The Smart Document Router is an open source Document Understanding and Data Extraction tool. It is like LLamaCloud, but for Enterprises using ERP systems.

• It ingests unstructured docs from faxes, email, and ERPs.
• It selects streams of docs that can be processed autonomously with LLMs and NLP - reducing the need for time-consuming, expensive manual workflows.

The Document Router is designed to work with a human-in-the-loop and can processes financial data correctly 'on the nose'. (We are not doing RAG!)

• NextJS, NextAuth, MaterialUI, TailwindCSS
• FastAPI
• MongoDB
• Pydantic
• LiteLLM
• OpenAI, Anthropic, Gemini, Groq/DeepSeek...

PyData Boston DocRouter Slides (Feb '24) have more details about tech stack, and how Cursor AI was used to build the DocRouter.

• Smart Document Router Slides from Boston PyData, Spring 2025
• DocRouter.AI: Adventures in CSS and AI Coding, Summer 2025

• Installation
  • Local Development Setup
  • Docker Setup
  • AWS Setup
• Development
  • Environment Variables Guide
  • Database Migrations Guide