business-science/

ai-data-science-team

GitHub

AI Data Science Team is a Python library of agents for data science workflows plus a flagship app called AI Pipeline Studio, with ongoing releases and multiple apps. It targets Python 3.10+ and OpenAI/Ollama integrations.

5.4kstars

921forks

29issues

MITlicense

2024since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

rohitg00/

ai-engineering-from-scratch

▲ 1.3k/wk

Learn it. Build it. Ship it for others.

46k7.9kPython

langflow-ai/

langflow

▲ 295/wk

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.

153k9.8kPython

langchain-ai/

langchain

▲ 595/wk

The agent engineering platform.

143k24kPython

langchain-ai/

langgraph

▲ 509/wk

Build resilient agents.

39k6.5kPython

wshobson/

agents

▲ 148/wk

Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI

38k4.1kPython

deepset-ai/

haystack

▲ 61/wk

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

26k3.0kPython

Compareai-data-science-team vs ai-engineering-from-scratch ai-data-science-team vs langflow ai-data-science-team vs langchain

Reviewgenerated from repository data · Aug 5, 2026

What it is

AI Data Science Team is a Python library of specialized agents for common data science workflows, plus a flagship app named AI Pipeline Studio. The Studio provides a visual, reproducible pipeline environment with data loading, cleaning, visualization, and modeling components.

How it works

The project provides agent building blocks and multi-agent workflows for data loading, cleaning, wrangling, visualization, EDA, modeling, and SQL database interaction. It includes multiple apps such as AI Pipeline Studio and Exploraratory Data Analysis tools that integrate with tools like dtale. Run the flagship app via a Streamlit command. OpenAI or Ollama can be used for language models.

Getting started

Requirements:

Python 3.10+
OpenAI API key (or Ollama for local models)

Install the app and library:

pip install -e .

Run the AI Pipeline Studio app:

streamlit run apps/ai-pipeline-studio-app/app.py

Recent releases

0.0.0.9017 ai-data-science-team 0.0.0.9017 (2025-12-20): # ai-data-science-team v0.0.0.9017. This release introduces the flagship AI Pipeline Studio app and major advancements in agent capabilities, security, mu
0.0.0.9016 0.0.0.9016 (2025-04-03): Enhancements. - Exploratory Data Analysis Agent: New dtale tool integration - Exploratory Data Analysis Copilot App: New dtale tool integration
0.0.0.9015 ai-data-science-team 0.0.0.9015 (2025-03-08): New Apps. - Open Pandas AI Data Analyst App
0.0.0.9014 ai-data-science-team 0.0.0.9014 (2025-02-23): New Multi-Agent. - PandasDataAnalyst(): Combines Pandas Data Wrangling and Plotly Data Visualization Agents - SQLDataAnalyst
0.0.0.9013 ai-data-science-team 0.0.0.9013 (2025-02-13): New App. - Exploratory Data Analysis Copilot

Traction

Stars: 5367 (as per repository stats)
Forks: 921
Open issues: 29

Behind the repo

Not applicable (no linked startup/company in provided data).

Caveats

License: MIT. Created 2024-12-11. Last push 2026-01-28. Language: Python. The README notes status as Beta with potential breaking changes until 0.1.0. Users should review release notes for compatibility.

SharePost on X LinkedIn