#118118th of 118 in Agent frameworks and SDKsFor data and documents, data analysis
ai-data-science-team
Python library of data science agents with a Streamlit pipeline app
- Stars
- 5.5k
- License
- MIT
- Last commit
- Jan 2026
- Last release
- Dec 2025
- Language
- Python
5,111 on 21 Apr 20265,511 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Python library of LangChain-based agents for data loading, cleaning, wrangling, feature engineering, visualization, SQL and H2O/MLflow modeling, plus a supervisor agent that coordinates them. It ships AI Pipeline Studio, a Streamlit app that records manual and AI steps as a visual pipeline with lineage and reproducible scripts. Works with OpenAI or local models through Ollama.
Who it is for: Data scientists and analysts building agent-driven data workflows in Python
Strengths
- Agents cover the data science loop: cleaning, EDA, feature engineering, SQL, H2O modeling, MLflow
- Pipeline Studio keeps lineage and exports reproducible scripts for each step
- Runs with OpenAI or local Ollama models such as llama3.1:8b
- Includes example apps: EDA Explorer, Pandas Data Analyst, Pipeline Studio
Weaknesses
- Beta status; README warns of breaking changes until 0.1.0
- No Docker or compose files; install is a clone plus pip install -e
- Model setup uses LangChain chat classes, so LangChain is required
- Quickstart documents only OpenAI and Ollama as model providers
What it needs
- GPU optional
- Needs Python 3.10+, Streamlit, OpenAI API key or Ollama, H2O, MLflow
- Models: OpenAI, Ollama
Quick answers
Is ai-data-science-team open source?
Yes. Its code is on GitHub under the MIT license.
Does ai-data-science-team need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |