Skillget

db-agent

agent
Security Audit
Pass
Health Pass
  • License — License: Apache-2.0
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 18 GitHub stars
Code Pass
  • Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

SQL AI Agent - Talk to your DB in Natural Language

README.md

DB Agent

Docker Image CI
Checkout the Website
Demo Video
Denvr Cloud
Live App

Latest News 🔥

A minimal, teachable natural-language-to-SQL system. Ask questions in plain English — DB Agent generates the SQL, validates it for safety, executes it, and shows you every step.

Two versions

This repo contains two independent, fully working versions of DB Agent — same concept, different deployment targets.

Streamlit App Full-Stack App
Stack Python + Streamlit Next.js + FastAPI
Best for Rapid prototyping, data teams Production deployments, enterprise demos
Deploy on Snowflake, Databricks, Docker AWS (Lambda + API Gateway), Neo Cloud

See each folder's README for setup and deployment instructions.

Features

  • Text-to-SQL — natural language to SELECT queries via any LLM
  • Safety layer — blocks all write/admin SQL before it reaches the database
  • Explainability — schema context, generated SQL, and validation all visible
  • Any OpenAI-compatible LLM — OpenAI, GitHub Models, Groq, Ollama, LM Studio
  • Any SQL database — SQLite by default; PostgreSQL and MySQL via one env var

Learning modules

New to AI agents? Work through the modules in order — each one builds on the last:

Module Concept What you build
01 — LLM Basics What is an LLM API call? Notebook: raw API call, messages, temperature
02 — Structured Output How to get reliable JSON from an LLM Notebook: JSON mode + Pydantic validation
03 — Tool Use LLM calls functions instead of generating text Agent that decides when to query the DB
04 — Agentic Loop Retry, reflect, recover from errors Agent with max-steps guard and error recovery
05 — MCP Server Expose tools via a standard protocol MCP server connectable to Claude Desktop

The streamlit_app/ is the finished product these modules build toward.
See CONCEPTS.md for a plain-English glossary of every term.

Repository structure

db-agent/
├── modules/           ← ★ learning modules (start here if you're new)
│   ├── 01_llm_basics/
│   ├── 02_structured_output/
│   ├── 03_tool_use/
│   ├── 04_agentic_loop/
│   └── 05_mcp_server/
├── streamlit_app/     ← Streamlit version (Snowflake / Databricks / Docker)
├── fullstack_app/     ← Full-stack version (AWS / Neo Cloud)
├── scripts/           ← shared utilities
├── tests/             ← shared test suite
└── CONCEPTS.md        ← plain-English glossary

Reviews (0)

No results found