DeepAnalyze and Auto-Analyst

DeepAnalyze
70
Verified
Auto-Analyst
61
Established
Maintenance 25/25
Adoption 10/25
Maturity 13/25
Community 22/25
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 22/25
Stars: 3,800
Forks: 548
Downloads:
Commits (30d): 105
Language: Python
License: MIT
Stars: 582
Forks: 97
Downloads:
Commits (30d): 4
Language: TypeScript
License: MIT
No Package No Dependents
No Package No Dependents

About DeepAnalyze

ruc-datalab/DeepAnalyze

DeepAnalyze is the first agentic LLM for autonomous data science. 🎈你的AI数据分析师,自动分析大量数据,一键生成专业分析报告!

Implements an agent-based architecture with planning and tool-use capabilities, executing code in sandboxed environments to iteratively refine analyses across multiple data formats. Built on a specialized 8B instruction-tuned model trained on 500K data science tasks, with support for multiple interfaces (WebUI, Jupyter, CLI, OpenAI-compatible API) and deployment options including Docker-based execution sandboxes.

About Auto-Analyst

FireBird-Technologies/Auto-Analyst

Open-source AI-powered data science platform.

Automates end-to-end data science workflows using a modular agent architecture built on DSPy, with specialized agents for preprocessing (pandas/numpy), statistical analysis (statsmodels), ML (scikit-learn), and visualization (plotly). LLM-agnostic design supports any API provider, while a planner component automatically routes queries to appropriate agents or coordinates multi-agent workflows. Integrates with Google Ads, Meta, HubSpot, Salesforce, and SQL databases via built-in connectors.

Scores updated daily from GitHub, PyPI, and npm data. How scores work