ruc-datalab/DeepAnalyze

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4565 stars · 725 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

framework · maturity active

agent-framework llm-inference data-science data-visualization chatbot rag data-science artificial-intelligence large-language-models data-visualization analytics python self-hosted cross-platform agentic-llm autonomous-data-science deep-research report-generation qwen open-source-model jupyter ai-agents gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ruc-datalab/DeepAnalyze")