Pythonic event-driven backtesting library for trading strategies, a community-maintained fork of Quantopian's Zipline.
2K+8 this week346PythonApache-2.0Well maintainedUpdated 4 days ago
tradingstrategy-ai/getting-started
Example Jupyter notebooks for backtesting and developing algorithmic trading strategies on DEX, DeFi and Binance CEX data with the Trading Strategy SDK.
- Stars
- 265
- Forks
- 39
- Open issues
- 7
- Last commit
- 12 days ago
Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.
What is it?
This repository is a starter kit of Jupyter notebooks for the Trading Strategy SDK, a Python toolkit for building algorithmic trading strategies that run on decentralised exchanges and DeFi markets. It covers market data feeds, backtesting, strategy development and live trade execution.
The notebooks range from simple technical-indicator strategies, such as moving average crossovers and ATR-based breakouts on BTC, ETH and MATIC, to multi-pair portfolio construction, DeFi yield strategies, and liquidity-filtered memecoin baskets on Uniswap and Base. Several examples compare Uniswap price feeds with Binance centralised exchange data. A separate section covers grid search and Gaussian Process optimisers using scikit-optimize.
The repository can be run in GitHub Codespaces, in VS Code dev containers, or in a local Python environment managed with Poetry. Each notebook follows a common structure: set up the client, define parameters, build a trading universe, create indicators, write a decide_trades function, run the backtest, and review performance output.
Key features
- 01Backtests strategies on DEX pair data from Uniswap v2/v3 and Polygon, plus Binance CEX data.
- 02Includes single-asset and multi-pair breakout, moving average and RSI/Bollinger strategies.
- 03Provides portfolio construction examples with daily rebalancing and liquidity or TVL filters.
- 04Offers grid search and Gaussian Process optimisers for strategy parameters.
- 05Exports OHLCV CSV files of top liquid pairs for use in other trading tools.
Use cases
- Learning how to write and backtest a crypto trading strategy in Python notebooks.
- Testing a technical indicator strategy against historical DEX or CEX price data.
- Comparing DEX and centralised exchange data quality for the same strategy.
- Tuning strategy parameters with grid search or Bayesian-style optimisation.
Quick start
- 1
Open the repository in GitHub Codespaces from the README link
- 2
Open and run a single backtest notebook in the browser
Things to know
- No license is specified in the repository metadata.
- The README describes Codespaces as slow, so local setup is faster.
Topics
FAQ
- What is getting-started?
- Example Jupyter notebooks for backtesting and developing algorithmic trading strategies on DEX, DeFi and Binance CEX data with the Trading Strategy SDK. This repository is a starter kit of Jupyter notebooks for the Trading Strategy SDK, a Python toolkit for building algorithmic trading strategies that run on decentralised exchanges and DeFi markets. It covers market data feeds, backtesting, strategy development and live trade execution.
- Is getting-started free to use? What license does it have?
- getting-started has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is getting-started still maintained?
- Actively maintained. The last commit to getting-started was on Oct 26, 2026.
- What can I use getting-started for?
- Learning how to write and backtest a crypto trading strategy in Python notebooks. Testing a technical indicator strategy against historical DEX or CEX price data. Comparing DEX and centralised exchange data quality for the same strategy. Tuning strategy parameters with grid search or Bayesian-style optimisation.
- How do I install getting-started?
- Open the repository in GitHub Codespaces from the README link Open and run a single backtest notebook in the browser
- Where can I get getting-started?
- The source code and installation instructions are on GitHub: https://github.com/tradingstrategy-ai/getting-started
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Python toolkit for trading research that backtests thousands of strategy ideas across assets and timeframes using vectorized NumPy and pandas operations.
9.7K+114 this week1.3KPythonOtherUpdated 3 days ago
Python framework for backtesting and live trading algorithmic strategies on decentralised exchanges, with on-chain market data.
383+3 this week63PythonOtherWell maintainedUpdated 10 days ago
A curated Awesome list of libraries, papers, strategies, books, blogs and courses for systematic (quantitative) trading.
15.2K+40 this week1.8KPythonNo licenseWell maintainedUpdated last month
Companion repo for the Chinese book 'XQuant: Everyone Can Be a Quant Trader', with Specs and Jupyter notebooks for Python quant trading and backtesting.
439+4 this week112Jupyter NotebookNo licenseUpdated 2 months ago
A bilingual-docs collection of Python and Jupyter examples for AI-driven stock trading, covering learning materials, backtests, alpha mining, LLM stock forecasting and live-trading simulation.
6.7K+6 this week1.2KJupyter NotebookApache-2.0Updated 11 days ago