# 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！

Repository: https://github.com/ruc-datalab/DeepAnalyze
Canonical: https://ross.abutalabs.com/products/deepanalyze
Homepage: https://ruc-deepanalyze.github.io
Language: Python
License: MIT
License Family: permissive
Topics: agent, agentic, agentic-ai, chatbot, data, data-analysis, data-engineering, data-science, data-visualization, llm, ai, ai-scientist, database, qwen, science, python, open-source, python-programming, deep-research, jupyter
Last push: 2026-08-26T14:01:40+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 23
- inputs: {"age_days": 326, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4565, forks 725 (observed 2026-08-28T04:08:53.532825+00:00)

## What it is
DeepAnalyze is the first agentic LLM (DeepAnalyze-8B, built on Qwen) for autonomous data science, capable of running the full pipeline from raw data sources to analyst-grade research reports without human intervention. It is fully open-source, including the model, code, training data (DataScience-Instruct-500K), and demo.

## Use cases
- automatically analyze large datasets and generate professional analysis reports
- run end-to-end data science pipelines without manual coding
- conduct deep research across CSV, Excel, JSON, and databases
- automate data preparation, modeling, and visualization
- self-host an AI data analyst assistant
- generate analyst-grade research reports from raw data

## When to choose
- you want fully autonomous data analysis from raw files to finished reports
- you need an open-source, self-hostable alternative to workflow-based data agents
- you want to extend or fine-tune an agentic data science model yourself

## When to avoid
- you need a polished no-code BI dashboard for business users
- you lack GPU resources to run an 8B LLM locally
- your tasks require guaranteed correctness of statistical results without review

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, data-science, data-visualization, chatbot, rag
- domain: data-science, artificial-intelligence, large-language-models, data-visualization, analytics
- platform: python, self-hosted, cross-platform
- tags: agentic-llm, autonomous-data-science, deep-research, report-generation, qwen, open-source-model, jupyter, ai-agents, gpu

## Member repositories
- ruc-datalab/DeepAnalyze (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.532825+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 2026-08-29T18:19:59.183629+00:00, confidence not recorded.
  - readme: https://github.com/ruc-datalab/DeepAnalyze (fetched 2026-08-28T04:08:53.532825+00:00, sha 3dc087f92ea6)
  - homepage: https://ruc-deepanalyze.github.io (fetched 2026-08-29T09:05:32.143862+00:00, sha b9dbb367fb3b)
- Data as of 2026-08-30T08:39:29.467469+00:00.