Route
Select skills, data sources, tools, and swarm teams from the request.
Open-source finance research agent
Turn market questions into runnable research.
Vibe-Trading connects natural-language prompts to market data, backtests, swarm analysis, trade-journal diagnostics, and reproducible research artifacts.
$ vibe-trading run -p "Backtest BTC-USDT 20/50 MA for 2024"
route: crypto data -> strategy -> backtest -> run card
return +18.6% max drawdown -7.4%
$ vibe-trading --swarm-run investment_committee
workers: macro, quant, risk, catalyst
report saved with evidence, metrics, and caveats
Install
One command to start a research workspace.
pip install vibe-trading-ai
vibe-trading init
vibe-tradinguv tool install vibe-trading-ai
vibe-trading init
vibe-trading serve --port 8899git clone https://github.com/HKUDS/Vibe-Trading
cd Vibe-Trading
pip install -e .
vibe-tradingWiki
Explore Vibe-Trading.
Research loop
Every answer keeps the trail inspectable.
Ground
Fetch market data, documents, URLs, broker journals, or local files at runtime.
Test
Run backtests, factor analysis, options checks, validation, and report generation.
Deliver
Return run cards, exports, reports, tool traces, and caveats for the next session.
Capabilities
Built for finance research, not brokerage execution.
Agent Harness
Persistent memory, session search, editable skills, context compression, and tool-batched research runs.
Backtesting
Seven engines across equities, crypto, futures, forex, composites, and options portfolios.
Swarm Teams
Investment committee, quant desk, risk review, macro, crypto, and other preset research teams.
Shadow Account
Parse broker journals, extract implicit rules, run counterfactual backtests, and render audit reports.
Boundary
No live trading.
Vibe-Trading is for research, simulation, and backtesting. It does not execute live trades and does not provide investment advice.