yimindev/dati

English | 简体中文
DatI (Data Intelligence) is a lightweight semantic gateway connecting **AI Agents with enterprise databases**. Simply connect your database, enrich semantic metadata, and configure built-in or parameterized SQL tools to publish an MCP service — ready for your agents or any MCP host.
Try It Online
Demo URL: https://dati-demo.zhangyimin.me
The demo instance is preloaded with sample data and reset periodically.
Demo
Data and configuration reference the AdventureWorks sample and can be automated via the dati-ops skill.
1. Data Source Metadata Configuration (configurable tables, columns, and values)
View Demo
2. Business Subject Configuration (select relevant tables, define business terms)
View Demo
3. MCP Service Configuration (choose business subjects, enable built-in tools, add parameterized SQL tools)
View Demo
4. Configure MCP in Agent (e.g., Antigravity)
View Screenshot
5. Query Data in Agent
View Demo
Quick Start
Open http://localhost:8085. Register with username admin to get super admin role. For production tuning and external DB setup, see Deployment Guide.
Why DatI?
1. **Multi-Database Support**: Supports MySQL, PostgreSQL, ClickHouse, Doris, and other relational and analytical databases
2. **Semantic Enhancement**: Supports business terms, column aliases, and automatic enum dictionary extraction. Combined with semantic search, it helps models understand business jargon and find the right tables
3. **Flexible Integration**: Based on standard MCP (Streamable HTTP), easily integrates into your existing agents or workflows
4. **Effortless MCP Publishing**: Ready-to-use built-in tools (schema inspection, SQL execution) and parameterized SQL tools to publish MCP services with zero extra deployment
5. **Security & Governance**: Centrally managed database credentials with user-level permission and data scope isolation
Use Cases
- **Conversational Data Analysis (NL2SQL)**: Connect business databases and support NL2SQL analysis workflows with semantic metadata and built-in tools
- **Lightweight App Development**: Wrap databases as MCP services so agents can query and update data through conversation to build lightweight applications
Tech Stack
- **Backend**: Spring Boot 3.5.x + Java 21 + JPA
- **Frontend**: Vue 3 + TypeScript + Vite + Element Plus + TailwindCSS 4
- **Database**: H2 (Development) / MySQL / PostgreSQL (Production)
- **Search Engine**: Elasticsearch (Semantic Retrieval)
Documentation
- Local Development Guide: Environment setup, backend/frontend startup, and project conventions
- Server Deployment Guide: Architecture overview, Docker Compose deployment, and operational maintenance
- Architecture Overview: High-level architecture, module index, and key design conventions
- **Examples**:
- Enterprise BI & Retail Analytics (AdventureWorks DW): Star schema Text-to-SQL, metric governance, multi-table joins, and parameterized acceleration