explorerhq/sql-explorer

SQL reporting that Just Works. Fast, simple, and confusion-free. Write and share queries in a delightful SQL editor, with AI assistance.

SQL Explorer – A Django‑based BI tool with LLM‑assisted query writing

What it is – A web application you can plug into any Django project (or run standalone) that lets users run, share, and visualise SQL queries against any database Django supports, plus CSV/JSON uploads.

Why it matters – It speeds up the data‑to‑people pipeline by providing an in‑browser editor, schema‑aware autocomplete, result visualisations, and an optional AI assistant that can draft or debug queries using an LLM (e.g., OpenAI). This makes ad‑hoc analysis accessible to non‑SQL users while still serving power users.

Key capabilities

  • Connect to multiple databases (Postgres, MySQL, SQLite, etc.) and to user‑uploaded CSV/JSON files.
  • Write queries in a clean editor with schema helper and autocomplete.
  • AI‑powered SQL assistant – supply an OpenAI (or compatible) API key and get natural‑language help that automatically injects schema context into the LLM prompt.
  • Save queries, view history, schedule snapshots, and expose saved queries as a simple JSON API.
  • In‑browser analytics: quick stats, pivot tables, scatter plots – no need to export to Excel.
  • Parameterised queries generate a friendly UI for users who don’t know SQL.
  • Email results, view logs, and export data.

Getting started

  1. Clone the repo and run docker compose up (includes a demo Django project).
  2. Open http://127.0.0.1:8000/explorer/ and log in with admin/admin.
  3. The Docker setup also launches a Vite dev server for hot‑reloading front‑end changes.

Typical workflow

  1. Choose or add a data connection.
  2. Write a query (or ask the AI assistant to generate one).
  3. Run it, view results, and optionally create visualisations or export.
  4. Save the query for later reuse or share it with teammates.

Who should use it

  • Teams that already run Django and need an internal BI layer without deploying a heavyweight platform.
  • Analysts who want quick, shareable SQL dashboards and simple visualisations.
  • Developers looking for an LLM‑augmented way to help non‑technical users explore data.

Links

Related

  • Project
    microsoft/pg_durable

    pg_durable is a PostgreSQL extension that enables fault-tolerant, long-running background workflows directly inside the database, eliminating the need for external job queues or orchestrators.

  • Project
    rusq/slackdump

    A tool to archive private and public Slack messages, channels, and files without admin privileges, featuring an MCP server for AI-powered data analysis.

  • Project
    logpai/loghub

    Loghub is a free collection of real system log datasets for AI-driven log analytics research. It includes 20 datasets across six categories (distributed systems, supercomputers, OSes, mobile, server apps, standalone software), with metadata like line counts, sizes, and labeling status. Logs are intentionally unsanitized. Usage requires citing the Loghub paper and referencing the repo URL.

  • Project
    FreedomIntelligence/Awesome-AI4Med

    Awesome-AI4Med is a curated, structured repository of medical AI research resources, including models, datasets, and benchmarks, designed to help researchers and developers track field progress and accelerate innovation.