About DeepAnalyze
DeepAnalyze is an agentic large language model for autonomous data science, developed by researchers at Renmin University of China and Tsinghua University. The goal is for it to complete data-centered tasks without step-by-step human guidance, acting as an AI data analyst that takes in large amounts of data and produces a professional analysis report.
According to the README it can run the whole data science pipeline, including data preparation, analysis, modeling, visualization and report generation. It also supports open-ended data research across different data sources, from structured data such as databases, CSV files and Excel sheets to other formats. Repository topics mention Qwen, Jupyter, deep research and data visualization, and the code is Python.
DeepAnalyze is released under the MIT license. It is a research-oriented project you run yourself with the provided model and code, rather than a hosted product. It suits data scientists, analysts and researchers exploring autonomous analysis agents.
Key features
- Autonomous end-to-end data science pipeline
- Data preparation and analysis
- Modeling and visualization
- Automatic report generation
- Open-ended deep research on data
- Works with databases, CSV and Excel data
Good fit for
- Automated exploratory data analysis
- Generating analysis reports from raw datasets
- Research on agentic data science
DeepAnalyze: questions and answers
- What is DeepAnalyze used for?
- DeepAnalyze is a research project for an agentic LLM that autonomously handles data science tasks from preparation to modeling, charts and written reports. It is a good fit for automated exploratory data analysis, generating analysis reports from raw datasets and research on agentic data science.
- Is DeepAnalyze open source?
- Yes. DeepAnalyze is open source under the MIT licence. Its source code is on GitHub at ruc-datalab/DeepAnalyze and is written mainly in Python.
- Is DeepAnalyze free?
- Yes. DeepAnalyze is open source, so the software itself is free to use.
- Can I self-host DeepAnalyze?
- Yes. DeepAnalyze can be self-hosted on your own server or infrastructure; there is no official hosted version.
- What is DeepAnalyze an alternative to?
- DeepAnalyze is an open-source alternative to Julius AI. Other open-source alternatives to Julius AI include DB-GPT, Pretzel and Nao.
- Is DeepAnalyze actively maintained?
- Yes. The most recent commit to DeepAnalyze was on 2 November 2026. The project has 4.8k stars on GitHub, with 116 added in the last 30 days.
Open-source alternatives to DeepAnalyze
See all
DB-GPT
AI Tools
open-source agentic AI data assistant for the next generation of AI + Data products.
MITvs Julius AI★ 20k
Pretzel
Analytics
The modern replacement for Jupyter Notebooks
OSSvs Hex★ 2.2k
Nao
BI & Dashboards
👾 nao is an open source analytics agent. (1) Create context with nao-core cli, (2) deploy
OSSvs ThoughtSpot★ 2k
AI YouTube Shorts Generator
AI Tools
Discover top AI YouTube Shorts generators like Vadoo AI, SendShort, and InVideo. Learn how
MITvs Opus Clip★ 6k
Nanobot
AI Tools
nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent for chat apps,
MIT★ 50k
ThoughtDAG
AI Tools
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an edit
MIT★ 775
SaaS alternatives to DeepAnalyze
See all
Julius AI
AI Tools
Ask questions of spreadsheets and data files and get charts and analysis back
SaaS
Sourcetable
AI Tools
AI-powered spreadsheet for data analysis, financial modeling, and reporting
SaaS
Ajelix
AI Tools
Agentic AI chat and analytics platform for enterprises
SaaS
Numerous.ai
AI Tools
An AI-powered spreadsheet plugin that brings ChatGPT to Google Sheets and Excel
SaaS
Obviously AI
AI Tools
No-code tool for building, explaining and deploying machine learning models from tabular data
SaaS
SheetGPT
AI Tools
Integrates OpenAI's GPT text and image generation in Google Sheets
SaaS

