# RamiAwar/dataline

Chat with your data - AI data analysis and visualization on CSV, Postgres, MySQL, Snowflake, SQLite...

Repository: https://github.com/RamiAwar/dataline
Canonical: https://ross.abutalabs.com/products/dataline
Homepage: https://dataline.app
Language: TypeScript
License: GPL-3.0
License Family: copyleft
Topics: ai, chart, data-science, data-visualization, llm, sql
Last push: 2026-02-11T11:11:58+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 28, longevity 88
- inputs: {"age_days": 1237, "days_push": 203, "days_rel": 461, "gap_med": 36, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1594, forks 164 (observed 2026-08-28T04:05:08.935422+00:00)

## What it is
DataLine is an open-source, privacy-focused AI data analysis and visualization application that lets users chat with their data in natural language. It connects to CSV files and databases like Postgres, MySQL, Snowflake, SQLite, and SQL Server to generate charts, tables, and reports locally without sending raw data to the cloud.

## Use cases
- chat with my csv files using natural language
- generate charts from a postgres database with ai
- text2sql tool for non-technical users
- self-hosted ai data analysis tool
- visualize mysql data without writing sql
- build reports and dashboards from sqlite
- query snowflake data with an llm locally
- explore a new database quickly with natural language

## When to choose
- you want natural-language querying of SQL databases or CSVs without writing SQL
- data privacy matters and you want everything stored locally with data hidden from LLMs
- non-technical team members need to explore data and export charts or reports
- you want a self-hosted, open-source alternative to cloud BI chat tools

## When to avoid
- you need a full-featured traditional BI suite with pixel-perfect dashboards
- you require guaranteed SQL correctness for production-critical queries since LLM output can be wrong
- you need a managed cloud service with no local installation
- your data sources are outside its supported connectors (e.g., NoSQL databases)

## Facets
- artifact type: application
- maturity: active
- function: data-visualization, chatbot, llm-inference, rag, search-engine, database
- domain: data-visualization, data-science, analytics, databases, artificial-intelligence, self-hosted
- platform: windows, self-hosted, cross-platform
- tags: text2sql, chat-with-data, ai-data-analysis, privacy-focused, charts, sql, csv, postgres, mysql, snowflake, sqlite, dashboards, macos, linux, docker

## Member repositories
- RamiAwar/dataline (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:08.935422+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:54:09.604474+00:00, confidence not recorded.
  - readme: https://github.com/RamiAwar/dataline (fetched 2026-08-28T04:05:08.935422+00:00, sha fe4b6da3487a)
  - homepage: https://dataline.app (fetched 2026-08-29T11:25:16.055153+00:00, sha 601a11183436)
  - site_page: https://dataline.app/about (fetched 2026-08-29T11:25:16.057911+00:00, sha 601a11183436)
  - site_page: https://dataline.app/faq (fetched 2026-08-29T11:25:16.059763+00:00, sha 601a11183436)
- Data as of 2026-08-30T08:39:29.467469+00:00.