ai-agent

SQLBot: Generate SQL

Get conversational data analysis with SQLBot, ideal.
intermediate30 minutes💵 Free (self-hosted)
6,787 stars871 forksJavaScriptGuide quality 8/10 · reviewed Jun 6Updated 9/14/2026100% free · open source
What it is

Use SQLBot to generate SQL code from text, ideal for quick data analysis.

Real use case example

"A founder wants to know their top-selling product on Amazon. They ask SQLBot to 'Show me the best-selling product category on Amazon.' SQLBot generates the SQL code, and the founder runs it on their database, getting the desired insights in minutes."

Best insideClaude DesktopCursor
When to use it
  • You need to analyze data in a database without writing SQL queries
  • You want to quickly explore data in a database using natural language
  • You need to generate SQL queries for a database without extensive SQL knowledge
Ready-to-paste prompt
curl -X POST -H 'Content-Type: application/json' -d '{"query": "What is the average order value for customers in the US?"}' http://localhost:3000/query
Heads up: Make sure you have Node.js 16 or later installed, as SQLBot uses features not available in earlier versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/sqlbot && curl -fsSL https://workflowstacks.com/api/skills/sqlbot/claude-skill -o ~/.claude/skills/sqlbot/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How SQLBot: Generate SQL works
Codeflow
Free to inspect

SQLBot: Generate SQL is a very large JavaScript project (~93k lines across 547 code files, plus 9 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Other license, has a test suite.

Size
Very large codebase
~93k lines · 547 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Docker
No API keys detected
JavaScript 49%Python 39%CSS 8%TypeScript 3%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    g2-ssr/app.js
    Where the program starts running
What's in each folder
frontend/Frontend / UI627 files
backend/Backend / API275 files
docs/Documentation1 files
g2-ssr/Folder10 files
installer/Folder6 files
.github/CI / automation (GitHub Actions)9 files
tests/Tests — proof it works6 files
.idea/Editor / agent settings1 files
READMEHas testsDocumentedCI checksDocker readyOther licenseUpdated this month
Quick Actions
Details
Creator
dataease
Language
JavaScript
Category
ai-agent
Published
4/21/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/sqlbot.svg)](https://workflowstacks.com/skills/sqlbot?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.