Trade with Yui

Your one-person Wall Street.

An open-source AI agent that gives you your own research desk, quant team, trading floor, and risk management — all running on your laptop.

Inspired by Cursor, Claude Code, and Manus.

Get OpenYui
Read the Docs

Quick Start

Three steps to your own AI trading desk.

1

Clone and build

Node.js 22+, pnpm 10+, and Claude Code CLI installed. That’s all you need.

git clone https://github.com/Amir-Akshan/OpenYui.git && cd OpenYui pnpm install && pnpm build
2

Run

Start the server and open localhost:3002. No API keys or config needed — the default setup uses Claude Code as the AI backend with your existing login.

pnpm dev
3

Chat

Tell Yui what you want — analyze a stock, check your portfolio, place a trade. She reads markets, reasons through her strategy, and executes. Everything is file-driven: Markdown for persona, JSON for config, JSONL for conversations.

How Different Yui Is

Neither a quant bot nor a trading assistant — here’s what makes Yui different.

Explainability

Yui doesn’t optimize for “completing trades” — she optimizes for “explainable good trades.” Before every action, she thinks, explores, tests, and calculates. The result is a decision you can actually read and understand. This dramatically reduces hallucination in her operations and means AI trading is no longer a black box.

Reproducibility

Through a complete chain of reasoning, Yui arrives at specific actions each round. Because the reasoning is thorough enough, running Yui multiple times — or having a different AI analyze her decisions — produces near-identical conclusions. Her behavior is reproducible, and for trading, that means stable.

Extensibility

Yui can use any frontier model, expand to new asset classes, and upgrade her internal tools at will. The reason is simple: she’s an agent, not a workflow. We didn’t pre-build any pipeline — just like the projects we pay tribute to.

How It Works

The same loop that powers great coding tools — applied to markets.

StepCursorTraderYui
UnderstandRead codebaseRead market data
PlanDesign solutionAnalyze indicators
TestRun testsBacktest strategy
ExecutePush to gitSubmit orders

OpenYui is file-driven — Markdown defines persona and tasks, JSON defines config, JSONL stores conversations. The same read/write primitives that power vibe coding transfer directly to vibe trading. No database, no containers, just files.

Yui is reasoning-driven. She doesn’t follow a fixed pipeline — she thinks through each decision using real market data, news, and technical indicators. You describe your strategy in natural language, and Yui figures out the rest: which indicators to check, when to act, and how to manage risk.

The architecture is extension-based — each capability (crypto trading, securities, market data, news, brain) is a self-contained tool package. Add new asset classes, swap AI providers, or write your own extensions. Just like the projects we pay tribute to.

Agent Loop

Every round follows the same lifecycle — whether triggered by you or by Yui herself.

Pre-Trade

Research

getFrontalLobe()getEmotion() globNews() / grepNews()equityGetProfile()
In-Trade

Analyze

think(observations)plan(options, decision) calculateIndicator()secGetQuote()
In-Trade

Execute

secPlaceOrder() stage secWalletCommit() commit secWalletPush() push
Post-Trade

Monitor

secWalletSync()secGetPortfolio() updateFrontalLobe()updateEmotion()
↵ updateFrontalLobe() → next round

News Collection

RSS feeds run in the background, continuously ingesting articles into a searchable archive. Yui queries this archive during research with globNews() and grepNews().

Event-Driven Loop

Cron scheduler fires jobs into an append-only EventLog. Heartbeat subscribes and re-enters the agent loop autonomously — Yui monitors positions 24/7 and only speaks up when it matters.

Why Yui?

We wanted a name that anyone — from any country, any background — could remember. Yui is warm, precise, and always present — just like the trading companion we set out to build for Vibe Trading.

Yui

Actually, the name “TraderYui” was also inspired by the idea of a companion who’s always watching the markets so you don’t have to — we just love the name.

Trading is a rabbit hole. Through trading, people learn how companies operate, how industries work, how nations conduct diplomacy, how politics and elections take shape. We hope every user can be like Yui — leap into the rabbit hole and begin their own journey.

Our Vision

Where we’re headed.

◆ Live Output  Hot Runner Scan

See Yui in Action

Real-time token scanning — Yui surfaces the best opportunities across chains so you don’t have to.

yui — hot-runner-scan — SOL
Yui Hot Runner Scan — live performance dashboard
SOL chain live
▲ Top Mover: +56.90%
● 10 tokens scanned
$49.35M total 24h vol
15:56:13  one-shot scan

Ready to try?

Four commands to your own AI trading desk. Open source, MIT licensed, runs on your laptop.

Get OpenYui on GitHub