stepll2026/OntiCards

OntiCards 是面向企业的 AI 数据中枢（AI Data Hub），围绕业务数据库提供一站式能力：数据源连接、元数据理解、自然语言查询、跨源融合、数据质检、查询审计与数据资产管理等

What it solves

OntiCards addresses the gap between powerful large language models (LLMs) and fragmented enterprise databases. It solves the problem of "data silos" where information is scattered across various database types (MySQL, Oracle, etc.) without unified business definitions, making it difficult for AI to understand private company data or for non-technical staff to retrieve information without writing complex SQL queries.

How it works

OntiCards acts as an intelligent middleware hub between business databases and AI applications. It connects to existing databases without intrusion and uses AI to automatically generate "intelligent data cards"—structured business descriptions of tables and fields. It then leverages Natural Language to SQL (NL2SQL) technology to translate user questions into executable SQL queries across multiple data sources, while applying security filters to prevent high-risk operations.

Who it’s for

  • Technical Leaders and Architects: To build a standardized AI data foundation for the enterprise.
  • Developers and Data Engineers: To reduce repetitive SQL writing and cross-database debugging.
  • Data Analysts: To perform self-service cross-source analysis without manual data extraction.
  • Data Governance Specialists: To standardize data inventory, quality checks, and terminology.
  • Business Managers: To retrieve business data using natural language without technical knowledge.
  • AI Application Developers: To use OntiCards as a secure data entry point for AI agents, RPA, or BI platforms.

Highlights

  • Broad Database Compatibility: Supports MySQL, PostgreSQL, SQLite, Oracle, SQL Server, and domestic Chinese databases like Dameng and OceanBase.
  • AI-Driven Data Understanding: Automatically generates business manuals for tables and identifies sensitive fields and relationships.
  • NL2SQL Capabilities: Enables natural language querying with support for multi-step reasoning and cross-source data fusion.
  • Automated Data Quality Control: Includes 14 built-in quality check rules for validity, consistency, and completeness.
  • Enterprise-Grade Security: Features data masking, row/column level permission isolation, and SSO integration.

Related

  • Project
    apache/datafusion-python

    DataFusion Python is a bridge that exposes Apache DataFusion's high-performance Rust-based SQL and DataFrame query engine to Python, letting developers run optimized SQL queries on CSV/Parquet/JSON data, plug in custom Python functions, and exchange results with Pandas. It is widely used as the foundation for other data systems, is installable via common package managers, and includes tooling for contributors and AI-assisted development.

  • Project
    OvidijusParsiunas/myvision

    A free online image annotation tool for generating computer vision ML training data with support for automated bounding box generation and dataset format conversion.

  • Project
    scverse/squidpy

    A scalable toolkit for the analysis and visualization of spatial molecular data and tissue microscopy images.

  • Project
    dbt-labs/dbt-mcp

    dbt‑MCP Server is an open‑source service that exposes a large catalog of dbt‑related tools (SQL execution, semantic‑layer queries, model discovery, dbt CLI commands, job administration, code generation, and documentation lookup) via the Model Context Protocol. It lets LLM‑powered agents understand and act on a dbt project—generating SQL from natural language, running dbt jobs, fetching lineage, and even creating new model files—making it a concrete bridge between data‑engineering metadata and AI assistants.