AI tools for data analysts

Data analysis is a good fit for AI because the answers can be checked. A query either returns the right rows or it does not, and a chart either matches the table or it does not. The tools here let an assistant write SQL against your real schema, work inside a notebook or a spreadsheet, and read from the database directly, so you spend less time on syntax and more on the question.

Text-to-SQL is only as good as its context

A model that has never seen your schema will invent column names. The useful text-to-SQL tools give it the schema, the relationships and sometimes a layer of business definitions, such as what counts as an active customer. That context is the product; the model is the easy part.

Always read the query before you trust the number. Ask the assistant to show its SQL and the row count, and spot-check a few rows.

Notebooks, spreadsheets and databases

AI notebooks and spreadsheets keep the analysis where people already look at it, with the model as a helper in the margin. Database MCP servers go the other way and give an assistant like Claude a direct, ideally read-only, connection.

Use read-only credentials for any server that can reach production data, and keep personal data out of prompts unless your company has cleared the model provider for it.

The list

From SkillScout's catalogue, counted on 27 October 2026: 162 entries matched this topic, and these are the 12 with the most GitHub stars, one per project, after a review for false matches. Descriptions are each project's own. Stars show popularity, not fit.

  1. Chat2DB

    Open-source tool · GitHub · 25,891 stars

    AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.

    Get the code, then follow its README: git clone https://github.com/OtterMind/Chat2DB

  2. teable

    Open-source tool · GitHub · 21,594 stars

    AI Spreadsheet for Business

    Get the code, then follow its README: git clone https://github.com/teableio/teable

  3. marimo

    Open-source tool · GitHub · 20,832 stars

    A reactive notebook for Python, run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a...

    Get the code, then follow its README: git clone https://github.com/marimo-team/marimo

  4. WrenAI

    Open-source tool · GitHub · 15,082 stars

    The open context layer that gives AI agents grounded, governed SQL across 20+ data sources.

    Get the code, then follow its README: git clone https://github.com/Canner/WrenAI

  5. univer

    Open-source tool · GitHub · 12,928 stars

    Build AI-native spreadsheets. Univer is a full-stack framework for creating and editing spreadsheets on both web and server. With Univer Platform, Univer Spreadsheets is...

    Get the code, then follow its README: git clone https://github.com/dream-num/univer

  6. databend

    Open-source tool · GitHub · 9,279 stars

    Data Agent Ready Warehouse : One for Analytics, Search, AI, Python Sandbox., rebuilt from scratch. Unified architecture on your S3.

    Get the code, then follow its README: git clone https://github.com/databendlabs/databend

  7. lightdash

    Open-source tool · GitHub · 5,911 stars

    Agentic BI. Analytics at the speed of code

    Get the code, then follow its README: git clone https://github.com/lightdash/lightdash

  8. jupyter-ai

    Open-source tool · GitHub · 4,289 stars

    An open source extension that connects AI agents to computational notebooks in JupyterLab.

    Get the code, then follow its README: git clone https://github.com/jupyterlab/jupyter-ai

  9. OfficeCLI

    Command-line tool · GitHub · 3,097 stars

    OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary...

    Get the code, then follow its README: git clone https://github.com/iOfficeAI/OfficeCLI

  10. dbhub

    MCP server · GitHub · 3,018 stars

    Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.

    Add it to Claude Code (from the official MCP Registry): claude mcp add dbhub -- npx -y @bytebase/dbhub

  11. rill

    Open-source tool · GitHub · 2,610 stars

    The fastest business intelligence tool for humans and agents.

    Get the code, then follow its README: git clone https://github.com/rilldata/rill

  12. codex-lb

    Open-source tool · GitHub · 2,169 stars

    Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints

    Get the code, then follow its README: git clone https://github.com/Soju06/codex-lb

Questions

Can ChatGPT or Claude analyse my data?

Yes, if you give them the data or a connection to it. Uploading a CSV works for small files. For a database, a database MCP server or a text-to-SQL tool is safer and scales further.

Which AI tool is best for SQL?

The one that can read your schema. Compare the text-to-SQL entries here on which databases they support and whether they let you add business definitions.

Related

Your own list

This page ranks by popularity. SkillScout's scan ranks by fit: the AI you already use writes a short profile of how you work, and SkillScout scores about 22,000 AI tools against your gaps and hands back a short list with install steps. It is free, and the server never saves your profile.

Run your scan