# ZJU-OmniAI/Data-Copilot

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

Repository: https://github.com/ZJU-OmniAI/Data-Copilot
Canonical: https://ross.abutalabs.com/products/data-copilot
Homepage: https://arxiv.org/abs/2306.07209
Language: Python
License: MIT
License Family: permissive
Last push: 2024-04-03T13:08:55+00:00

## Health v2 (maintenance only)
Score: 29/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 84
- inputs: {"age_days": 1181, "days_push": 882, "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 1511, forks 154 (observed 2026-08-28T04:04:55.961366+00:00)

## What it is
Data-Copilot is an LLM-based data analysis agent that autonomously designs and invokes interface tools to query, process, analyze, predict, and visualize data. It focuses on Chinese financial data sources (stocks, funds, economic and financial data) and generates code as an intermediary for large-scale data processing.

## Use cases
- analyze Chinese stock and fund data with natural language requests
- visualize economic and financial data without writing code
- build an autonomous LLM agent for data querying and prediction
- transform raw financial data into charts, tables, and text automatically
- research code-centric data agents with pre-designed interfaces

## When to choose
- you need natural-language analysis of Chinese financial market data
- you want an LLM agent that autonomously designs and chains data tools
- you are researching autonomous workflow or code-centric agent architectures

## When to avoid
- you need non-Chinese or non-financial data sources out of the box
- you require a production-grade, actively maintained data platform
- you cannot provide OpenAI API keys or a Tushare token

## Facets
- artifact type: application
- maturity: maintenance
- function: agent-framework, data-visualization, machine-learning, nlp, analytics
- domain: artificial-intelligence, large-language-models, fintech, data-visualization, data-science
- platform: python, self-hosted
- tags: llm-agent, autonomous-workflow, financial-data, tushare, code-generation, data-analysis, ai-agents, web-server

## Member repositories
- ZJU-OmniAI/Data-Copilot (main) score 29

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:55.961366+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 2026-08-30T04:32:22.522205+00:00, confidence not recorded.
  - readme: https://github.com/ZJU-OmniAI/Data-Copilot (fetched 2026-08-28T04:04:55.961366+00:00, sha b9b9a862de68)
  - homepage: https://arxiv.org/abs/2306.07209 (fetched 2026-08-29T11:36:29.587064+00:00, sha 76b4354c80b1)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:36:29.596051+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:36:29.599592+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:36:29.601602+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:36:29.597830+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.