Intelligent Data Dictionary – AI-Powered Multi-Database Discovery Platform
Link to open source: https://github.com/narang25/intelligent-data-dictionary-agent
Intelligent Data Dictionary (IDD) is an AI-powered platform that helps teams understand, discover, and manage data across multiple databases through natural language.
The platform connects to databases such as PostgreSQL, MySQL, MongoDB, and Snowflake, automatically extracts metadata, and creates a centralized knowledge layer for tables, collections, columns, relationships, and data definitions.
Users can search and explore datasets using natural language queries instead of manually navigating complex schemas. The system is being designed to support semantic search, automated metadata extraction, data profiling, AI-generated documentation, and cross-database discovery.
Key Features:
- Multi-database connectivity (PostgreSQL, MySQL, MongoDB, Snowflake)
- Automated metadata extraction
- Centralized data catalog
- Schema and relationship discovery
- Data profiling and statistics
- Semantic search using embeddings
- AI-powered data exploration
- Scalable connector architecture for future data sources
The goal is to simplify data discovery and make organizational data accessible to developers, analysts, and business users through an intelligent conversational interface.
This build was uploaded as a hackathon project
