What do you want to do?
3 use cases
-
Backtest a trading strategy described in plain English
Install the package, run the setup, and ask for a backtest in one sentence.
- REPO
HKUDS/Vibe-Trading - Money
- Intermediate
View prompt
Install HKUDS/Vibe-Trading and backtest <strategy in plain English> on <symbol> for <period>. Report return, max drawdown and number of trades, and list any backtest setting the run card flagged as unrecognised.
- REPO
-
Paper trade a strategy on daily bars
Save a paper account and step it forward against completed daily bars without ever reaching a broker.
- REPO
HKUDS/Vibe-Trading - Money
- Intermediate
View prompt
Using HKUDS/Vibe-Trading, create a saved paper account and paper trade <strategy> on <symbols> against completed daily bars. Each day report positions, cash and PnL, and confirm no broker connector is enabled.
- REPO
-
Give your coding agent trading research tools over MCP
Run the Vibe Trading MCP server so Claude Code, Codex or another MCP client can fetch data and run backtests.
- REPO
HKUDS/Vibe-Trading - Claude Code
- Codex
- Cursor
- Money
- Intermediate
View prompt
Add HKUDS/Vibe-Trading as an MCP server (command vibe-trading-mcp) to <client>, list the tools it exposes, and run one backtest of <strategy> through it. Do not enable any trading connector.
- REPO
Quick start with Vibe Trading
- Check you have what it needs: Python 3.11 or later for a local install, or Docker; An LLM API key from a supported provider, or Ollama locally; Market data works without keys for many markets through free fallbacks.
- Open HKUDS/Vibe-Trading on GitHub and read the README and license.
- Install with
pip install -U vibe-trading-ai - Run the interactive setup (vibe-trading init in the README quick start) to write your .env with an LLM key
- Ask for a backtest with vibe-trading run and a prompt, for example a BTC-USDT 20/50 moving-average strategy for 2024
- Read the run card: settings it did not recognise are reported, and values it cannot compute come back as null instead of a guess
These steps come from our top use case, Backtest a trading strategy described in plain English, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for HKUDS/Vibe-Trading
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers and quant learners who want an agent to draft, backtest and paper trade strategies from plain English, or to give their own agent trading research tools.
- Why it is hot37k stars, talked about in 2 AI sources we track
- LanguagePython
- Sourcegithub.com/HKUDS/Vibe-Trading · Back to Hot repos
Requirements
- Python 3.11 or later for a local install, or Docker
- An LLM API key from a supported provider, or Ollama locally
- Market data works without keys for many markets through free fallbacks
Add this badge to your README
Maintain Vibe Trading? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/hkuds-vibe-trading/?utm_source=github&utm_medium=badge&utm_campaign=HKUDS-Vibe-Trading)
HTML
<a href="https://dedupedai.com/use-cases/hkuds-vibe-trading/?utm_source=github&utm_medium=badge&utm_campaign=HKUDS-Vibe-Trading"><img src="https://dedupedai.com/badge/HKUDS/Vibe-Trading.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Vibe Trading
What is Vibe Trading?
Vibe-Trading is HKUDS's personal trading agent: you describe research or a strategy in plain English and it fetches market data, writes and runs backtests, and reports return, drawdown and other metrics. Recent releases add daily paper trading against completed bars with saved paper accounts, a large Alpha Zoo of factors, email and chat reports, many LLM providers and an MCP server so other agents can use its tools. Not financial advice: paper trade first, and remember you can lose money. It is an open-source project on GitHub: https://github.com/HKUDS/Vibe-Trading.
How do I use Vibe Trading?
Install with pip install -U vibe-trading-ai; then run the interactive setup (vibe-trading init in the README quick start) to write your .env with an LLM key; ask for a backtest with vibe-trading run and a prompt, for example a BTC-USDT 20/50 moving-average strategy for 2024. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Vibe Trading for?
Developers and quant learners who want an agent to draft, backtest and paper trade strategies from plain English, or to give their own agent trading research tools.
What can I do with Vibe Trading?
3 use cases so far, for example: Backtest a trading strategy described in plain English; Paper trade a strategy on daily bars; Give your coding agent trading research tools over MCP. Each has steps and a copy-paste agent prompt.
What do I need to run Vibe Trading?
Python 3.11 or later for a local install, or Docker; An LLM API key from a supported provider, or Ollama locally; Market data works without keys for many markets through free fallbacks.
What are alternatives to Vibe Trading?
Other hot AI repos in Money: Fincept Terminal, Freqtrade, Day Trader Skill, Tick Stock Panel, Trading Agents.
Is Vibe Trading safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.