IshaanLabs/langgraph-text-to-sql-agent

Offline Text-to-SQL Agent – Convert natural language questions into SQL queries with explanations. Fully open-source, runs locally, and features a Streamlit UI, multi-table support, and configurable SQLite databases. Built with LangChain, LangGraph, Ollama (CodeGemma 7B).

42
/ 100
Emerging

This project helps anyone explore and get answers from a database using everyday language, eliminating the need to write SQL queries. You type in a question like "How many customers are from the USA?", and it generates the SQL, runs it, and provides the results along with a plain-English explanation. Data analysts, business users, or anyone needing quick insights from structured data can use this.

Use this if you need to quickly ask questions and get answers from a relational database without learning or writing SQL.

Not ideal if you require complex data manipulation (writes, updates, deletions) or if your data is unstructured.

data-exploration business-intelligence database-querying data-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

11

Forks

6

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/IshaanLabs/langgraph-text-to-sql-agent"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.