If you want to contribute to an open-source AI trading bot — and build on a real, running system instead of a toy — this guide shows you exactly how. The Claude-powered crypto bot from Part 1 is MIT-licensed on GitHub, and the most interesting problems in it are wide open. You don’t need to be a quant or an ML expert; there’s meaningful work here for developers, traders, writers, and testers alike.
👋
New to open source?That’s fine — this is a friendly, low-pressure project. A thoughtful question or a docs fix is a real contribution.
Most “AI trading bot” repos are either abandoned demos or paywalled black boxes. This one is different: it’s a complete, documented, honestly-evaluated system where the central question — does it actually have a tradeable edge? — is genuinely unsolved. Contributing here means working on real LLM-agent orchestration, machine-learning signal modelling, exchange execution, and a production dashboard, with a maintainer who’ll actually review your PR. It’s a great portfolio piece and a great way to learn.
Pick whatever matches your skills:
| Area | Example contributions |
|---|---|
| 🧠 Strategy & research | New signals, better entry/exit logic, ideas to capture trend (the current strategy is defensive and lags in bull markets) |
| 📈 ML modelling | Feature engineering, calibration, honest walk-forward evaluation, reducing overfitting |
| 🛡️ Risk & execution | Smarter sizing, OCO/bracket orders, slippage modelling, live-trading safety |
| 💻 Dashboard (Next.js) | New visualizations, UX, mobile polish, accessibility |
| 🔧 DevOps | A one-command docker compose setup — the single highest-impact task right now |
| 📖 Docs & testing | Setup guides, tutorials, backtest rigor, unit tests, translations |
You don’t need a VPS to contribute — run it locally on testnet:
git clone https://github.com/dineshstack/crypto_bot.git
cd crypto_bot
python3 -m venv venv && source venv/bin/activate
pip install -r requirements.txt
cp .env.example .env # add your own keys; keep TESTNET=true
For the dashboard:
cd dashboard
npm install
cp .env.local.example .env.local
npm run dev
The flow is standard GitHub — small, focused changes are the easiest to merge:
git checkout -b feature/your-improvement
make your change
python3 -m py_compile changed_file.py # sanity-check Python
git commit -m "Clear description of what changed and why"
git push origin feature/your-improvement
In your PR, describe what you changed, why, and how you tested it. Anything touching order execution, sizing, or the circuit breakers gets extra review — describe your testing in detail, and never weaken a safety check without explaining why. The full checklist is in the repo’s CONTRIBUTING.md.
Some of the most valuable contributions aren’t code:
Look for issues labelled good first issue
to get started.
This project is deliberately transparent about what it can and can’t do, which makes it a rare thing in the “AI trading” space: a place to genuinely learn and experiment without hype. If that appeals to you, jump in.
The repo is open, MIT-licensed, and waiting for your first pull request.🚀
Ready to contribute?
⭐Star & fork the repo
💬[describing what you’d like to work on]Open an issue
☕ Not contributing code but want to support the work?[— it keeps the demo and API running.]Buy me a coffee on Ko-fi
Tags: Open Source, AI Trading Bot, Contributing, GitHub, Developer Community
Disclaimer: For educational and research purposes only. Not financial advice. Cryptocurrency trading carries substantial risk of loss.