# vnpy/vnpy

基于Python的开源量化交易平台开发框架

Repository: https://github.com/vnpy/vnpy
Canonical: https://ross.abutalabs.com/products/vnpy
Homepage: http://www.vnpy.com
Language: Python
License: MIT
License Family: permissive
Topics: trading, investment, quant, python, algotrading, finance, fintech, vnpy
Last push: 2026-08-10T01:07:58+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 72, longevity 100
- inputs: {"age_days": 4202, "days_push": 24, "days_rel": 111, "gap_med": 86.0, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 44786, forks 12404 (observed 2026-08-28T04:12:09.485564+00:00)

## What it is
VeighNa (vn.py) is an open-source Python framework for developing quantitative trading systems, covering strategy development, backtesting, live trading, and market data management. Its 4.x release adds an alpha module for multi-factor machine learning strategy research, including feature engineering, model training (Lasso, LightGBM, MLP), and backtesting workflows.

## Use cases
- develop and backtest CTA trading strategies in Python
- connect to futures, options, and stock exchange gateways for live trading
- run algorithmic order execution like TWAP or iceberg orders
- train multi-factor machine learning models on stock market data
- record and manage historical tick and bar market data
- trade volatility arbitrage and options strategies with delta hedging
- optimize strategy parameters with genetic algorithms

## When to choose
- you need a full-stack quant trading platform in Python with exchange connectivity
- you want both GUI and CLI modes for strategy management
- you are doing factor-based ML research and live trading in one framework
- you trade Chinese futures, options, or A-share markets

## When to avoid
- you only need simple backtesting without live trading infrastructure
- you require crypto exchange trading as the primary focus
- you need a lightweight library rather than a full platform
- your stack is not Python

## Facets
- artifact type: framework
- maturity: stable
- function: trading, machine-learning, data-science, gui, cli, webhook
- domain: fintech, machine-learning, data-science
- platform: python, windows, cross-platform
- tags: quantitative-trading, algotrading, backtesting, cta-strategies, event-driven-engine, market-data, gateway-interfaces, factor-modeling, ml-strategies, trading, quantitative-finance, linux, macos

## Member repositories
- vnpy/vnpy (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:09.485564+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 2026-08-29T16:21:57.682495+00:00, confidence not recorded.
  - readme: https://github.com/vnpy/vnpy (fetched 2026-08-28T04:12:09.485564+00:00, sha 058d024d9a77)
  - homepage: http://www.vnpy.com (fetched 2026-08-29T07:45:36.070987+00:00, sha 298551e25d41)
  - site_page: https://www.vnpy.com/docs (fetched 2026-08-29T07:45:36.080630+00:00, sha 6e341a886106)
  - registry_pypi: https://pypi.org/pypi/vnpy/json (fetched 2026-08-29T07:45:36.082680+00:00, sha 4b16e02ca6d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.