Building RagRabbit, An Open Source RAG Search with Postgres as the Vector Store

Marco D'Alia, a software architect behind RagRabbit, built the tool to simplify his own workflow by combining multiple systems for web scraping, vector search, and AI responses into one single, open-source toolkit. RagRabbit crawls websites, converts pages to Markdown, generates embeddings with Postgres via pgVector, provides AI Q&A using OpenAI or Claude, and offers an MCP server for read-only doc chunks directly into IDEs or chat apps. The tool accommodates different authentication setups, including user/password, GitHub OAuth, and magic links, and can be deployed on Vercel's Neon with a single click, taking advantage of its serverless scaling and Postgres features like full-text search.