K-Dense-AI/agentic-data-scientist
An end-to-end Data Scientist
Implements a multi-agent workflow that separates planning from execution, using Claude Code for implementation and OpenRouter-based agents for planning and validation. Integrates with Model Context Protocol (MCP) servers for extensible tool access and includes adaptive replanning when execution reveals new requirements. Built on Google's Agent Development Kit and supports both orchestrated multi-phase workflows and direct execution modes via CLI.
579 stars. Available on PyPI.
Stars
579
Forks
87
Language
Python
License
MIT
Category
Last pushed
Dec 07, 2025
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/K-Dense-AI/agentic-data-scientist"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
issdandavis/SCBE-AETHERMOORE
AI Governance API | 14-Layer Hyperbolic Security Pipeline | EU AI Act Ready | From $49/mo
marvin-ai/marvin-python-toolbox
Marvin AI has been accepted into the Apache Foundation and is now available at...
K-Dense-AI/karpathy
An agentic Machine Learning Engineer
SullyGreene/TinyAGI
A Python-based framework for developing and orchestrating AI agents. TinyAGI is built with...
getbasedai/basedai
Develop on and interact with BasedAI.