geek-fun/sqlkit

Agentic SQL database manager for 40+ databases — PostgreSQL, MySQL, SQL Server, SQLite, DuckDB, ClickHouse, Oracle and more. Lightweight, privacy-first, AI-powered, cross-platform. Built with Tauri (Rust).

What it solves

SqlKit is a cross-platform desktop database client that simplifies database management by integrating an AI agent. It replaces heavyweight tools like DBeaver or DataGrip by providing a lightweight, native experience that allows users to interact with their databases using natural language instead of writing complex SQL manually.

How it works

Built with Rust and Tauri v2, the application provides a native binary for macOS, Windows, and Linux. It uses a "Agentic Data Studio" that connects to LLMs (via OpenAI, Anthropic, DeepSeek, or Ollama) to translate natural language requests into SQL queries. The agent is schema-aware, meaning it reads the database schema to ensure queries are accurate. It also provides a professional SQL editor powered by Monaco, supports over 70 different database engines through various adapter strategies (Native, PG-wire, MySQL-wire, JDBC, and HTTP bridges), and handles secure connectivity via SSH tunnels and OS-level encrypted storage.

Who it’s for

Developers, database administrators, and data analysts who need a single, high-performance tool to manage multiple diverse database types across different operating systems.

Highlights

  • AI-powered SQL: Generates queries, optimizes slow SQL, explains execution plans, and fixes errors using natural language.
  • Massive Database Support: Compatible with 70+ databases including PostgreSQL, MySQL, Oracle, SQL Server, and ClickHouse.
  • Native Performance: Built with Rust and Tauri to avoid the overhead of Electron or Java runtimes.
  • Cross-Engine Data Transfer: Move data between different database types (e.g., PostgreSQL to ClickHouse) without intermediate files.
  • Privacy-First: Credentials are encrypted via OS keychain and are never exposed to the LLM.

Related

  • Project
    geek-fun/dockit

    A native desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, and MongoDB that features an AI-powered agent to translate natural language into database queries.

  • Project
    OtterMind/Chat2DB

    An AI-powered database client and SQL workspace that allows users to generate, explain, and optimize SQL queries using natural language across 40+ supported databases.

  • Project
    sjjian/openhare

    An AI-powered, cross-platform desktop SQL client that supports multiple databases and helps users write and optimize queries.

  • Project
    Lamatic/AgentKit

    AgentKit is an open‑source SDK that provides a catalog of 70 ready‑made “kits” (full apps, pipelines, or templates) for building, testing and deploying AI agents. Kits are defined by a simple config file, can be edited in a visual flow studio, and are shipped as Next.js apps that run server‑less. The collection covers support triage, code review, RAG chat, hiring assistants, legal/medical bots, and many other business‑focused agents, making it a turnkey platform for creating reliable, enterprise‑grade AI agents.

  • Project
    dataease/SQLBot

    An intelligent data questioning system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language into SQL queries.