DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Authors: Shaolei Zhang, Ju Fan*, Meihao Fan, Guoliang Li, Xiaoyong Du

Renmin University of China, Tsinghua University

DeepAnalyze is the first agentic LLM for autonomous data science. It can autonomously complete a wide range of data-centric tasks without human intervention, supporting:

• 🛠 Entire data science pipeline: Automatically perform any data science tasks such as data preparation, analysis, modeling, visualization, and report generation.
• 🔍 Open-ended data research: Conduct deep research on diverse data sources, including structured data (Databases, CSV, Excel), semi-structured data (JSON, XML, YAML), and unstructured data (TXT, Markdown), and finally produce analyst-grade research reports.
• 📊 Fully open-source: The model, code, training data, and demo of DeepAnalyze are all open-sourced, allowing you to deploy or extend your own data analysis assistant.

🔥 News

• [2026.07]: We look forward to releasing DeepPrep, a data-preparation companion to DeepAnalyze that turns raw tables into analysis-ready data.

  DeepPrep is an LLM-powered agentic system for autonomous data preparation. It constructs data-preparation pipelines through execution-grounded interaction with intermediate table states and runtime feedback, helping clean, transform, and standardize raw data before downstream analysis.

  ▶️ Demo:

  https://github.com/user-attachments/assets/6b94927f-5c0c-4cfe-bc33-de56b8e459cd

• [2026.06.15]: We release CoDA-Bench, a benchmark for evaluating whether code agents can handle data-intensive analytical tasks, closely aligned with DeepAnalyze's target scenarios.

  CoDA-Bench evaluates agents in a Linux sandbox with hundreds of data files. Given a natural-language question, an agent must discover relevant data, write executable code, and produce the final answer. It provides a benchmark setting for the same type of data discovery and code-execution challenges targeted by DeepAnalyze.

  ▶️ Demo:

  https://github.com/user-attachments/assets/34e50a62-744b-4079-8988-6a8bbfe166a0

• [2026.05.31]: DA-Studio, the system behind DeepAnalyze WebUI v2 (demo/chat_v2), has been accepted to the VLDB 2026 Demonstration Track.

• [2026.03.16]: Update DeepAnalyze WebUI v2, featuring a smoother UI, support for the HeyWhale API, and support for Docker-based sandboxed code execution. More details in Readme .

• [2026.01.31]: 🎉🎉🎉DeepAnalyze served as the official agent supporting the 2026年(第19届)中国大学生计算机设计大赛大数据主题赛 (2026 (19th) China Collegiate Computer Design Contest – Big Data Track).

• [2025.12.28] ANNOUNCEMENT: DeepAnalyze API Keys Are Now Available 🎉🎉🎉 You can now apply for your API key via this or this . For full details and usage instructions, please refer to the or the .

🖥 Demo

WebUI

https://github.com/user-attachments/assets/04184975-7ee7-4ae0-8761-7a7550c5c8fe

• Clone this repo and download DeepAnalyze-8B.
• Deploy DeepAnalyze-8B via vllm: vllm serve DeepAnalyze-8B
• Run these scripts to launch the API and interface, and then interact through the browser (http://localhost:4000):

  cd demo/chat/frontend
  npm install
  cd ..
  bash start.sh
  
  # stop the api and interface
  bash stop.sh
  
  # stop vllm if needed
  

• If you want to deploy under a specific IP, please replace localhost with your IP address in ./demo/chat/backend.py and ./demo/chat/frontend/lib/config.ts

WebUI v2

https://github.com/user-attachments/assets/2dd1d2aa-6fb9-4202-bc8d-cbe874844725

• A more streamlined UI

• Added support for HeyWhale API keys

• Added support for a Docker-based sandbox code execution environment.

• The usage method is the same as WebUI.

  cd demo/chat_v2/frontend  
  npm install
  cd ..
  cp .env.example .env 
  bash start.sh
  # stop the api and interface
  bash stop.sh
  
  # stop vllm if needed
  

JupyterUI

https://github.com/user-attachments/assets/a2335f45-be0e-4787-a4c1-e93192891c5f

• This Demo runs Jupyter Lab as frontend, creating a new notebook, converting <Analyze|Understand|Answer> to Markdown cells, converting <Code> to Code cells and executing them as <Execute>.
• Go to demo/jupyter to see more and try!
• 👏Thanks a lot to the contributor @ChengJiale150.

CLI

https://github.com/user-attachments/assets/018acae5-b979-4143-ae1e-5b74da453c1d

• Deploy DeepAnalyze-8B via vllm: vllm serve DeepAnalyze-8B

• Start the API server and launch the CLI interface:

  cd API
  python start_server.py  # In one terminal
  
  cd demo/cli
  python api_cli.py       # In another terminal (English)
  # or
  python api_cli_ZH.py    # In another terminal (Chinese)
  

• The CLI provides a Rich-based beautiful interface with file upload support and real-time streaming responses.

• Supports both English and Chinese interfaces .

[!TIP]

Clone this repository to deploy DeepAnalyze locally as your data analyst, completing any data science tasks without any workflow or closed-source APIs.

🔥 The UI of the demo is an initial version. Welcome to further develop it, and we will include you as a contributor.

🚀 Quick Start

🔑 Use the DeepAnalyze API

API keys are now available!

To request your key, please fill out one of the following application forms:

• Primary Form (Google)
• Alternative Form (Feishu)

📚 For comprehensive usage instructions, please refer to the API guide:

• Documentation
• Feishu Wiki

Model Download

Download model in RUC-DataLab/DeepAnalyze-8B · Hugging Face or DeepAnalyze-8B · 模型库

📊 Memory Configuration Recommended Parameters Table

GPU Memory	Model Type	Recommended max-model-len	Use FP8 KV Cache
16GB	8-bit Quantized	8192	✓
16GB	4-bit Quantized	49152	✓
24GB	Original Model	16384	✓
24GB	8-bit Quantized	98304	✓
24GB	4-bit Quantized	131072	✓
40GB	Original Model	131072	✓
40GB	8-bit Quantized	131072
80GB	Original Model	131072

To obtain the quantized model, you can use ./quantize.py .

🚀 vLLM Launch Command Template

General Command Template

python -m vllm.entrypoints.op