# business-science/ai-data-science-team

An AI-powered data science team of agents to help you perform common data science tasks 10X faster.

Repository: https://github.com/business-science/ai-data-science-team
Canonical: https://ross.abutalabs.com/products/ai-data-science-team
Language: Python
License: MIT
License Family: permissive
Topics: data-science, generative-ai, agents, ai, ai-engineer, ai-engineering, copilot, data-scientist, gpt, machine-learning, ml-engineer, ml-engineering, openai
Last push: 2026-01-28T15:44:35+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 64, release rhythm 62, longevity 45
- inputs: {"age_days": 630, "days_push": 217, "days_rel": 256, "gap_med": 6, "n_releases_24m": 16}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5385, forks 924 (observed 2026-08-28T04:09:17.112394+00:00)

## What it is
A Python library of specialized LLM-powered agents for common data science workflows such as data loading, cleaning, wrangling, visualization, EDA, and modeling. It also ships AI Pipeline Studio, a Streamlit app that turns agent work into visual, reproducible pipelines.

## Use cases
- automate data cleaning with an AI agent
- generate EDA and visualizations from a dataframe using LLMs
- build machine learning pipelines with AI assistance
- run a team of AI agents for data science tasks
- create reproducible data science pipelines visually
- query SQL databases with natural language agents

## When to choose
- you want LLM-driven automation of routine data science workflows in Python
- you use OpenAI or local Ollama models and want agent building blocks
- you want a visual pipeline app with lineage and reproducible scripts

## When to avoid
- you need a stable, production-hardened tool - the project is in beta with breaking changes expected
- you want fully deterministic pipelines without LLM involvement
- you cannot use OpenAI or local LLM backends

## Facets
- artifact type: library
- maturity: experimental
- function: agent-framework, machine-learning, data-science, data-visualization, etl, chatbot
- domain: data-science, machine-learning, artificial-intelligence, developer-tools
- platform: python, cross-platform
- tags: multi-agent, llm-agents, openai, streamlit, data-cleaning, eda, mlflow, copilot, generative-ai, ai-agents

## Member repositories
- business-science/ai-data-science-team (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:17.112394+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 2026-08-29T17:58:25.479481+00:00, confidence not recorded.
  - readme: https://github.com/business-science/ai-data-science-team (fetched 2026-08-28T04:09:17.112394+00:00, sha 16588973b3c2)
  - registry_pypi: https://pypi.org/pypi/ai-data-science-team/json (fetched 2026-08-29T08:52:42.904352+00:00, sha 87638cf217ff)
- Data as of 2026-08-30T08:39:29.467469+00:00.