Local-first AI trading research: market heatmaps, news catalysts, strategy generation, Backtrader backtests, and transparent agent runs — all in one Docker app. No brokerage connection. No hosted accounts. Your data stays on your machine.
One workspace for market research, strategy generation, backtesting, and AI-powered analysis.
Chat with your market data, strategies, news, heatmaps, and backtest history.
Generate and iterate strategies until one beats the baseline. Loop engineering at its finest.
Statistical calculations and LLM reasoning with support/resistance lines to simulate expected trends.
Analyze real-time movement with peer stocks, insider trading data, and technical indicators.
Traditional data visualisation for quick results, combined with loop-engineering-powered agents.
Real-time quotes, sector heatmaps, industry performance, insider activity, news search, and fundamentals — all in one query.
Describe a trading thesis in plain English; get a working Backtrader strategy with syntax and runtime validation.
Every generated strategy is backtested against downloaded candles with configurable parameter sweeps.
Every result is compared to buy-and-hold and any saved strategy. Underperformers are rejected automatically.
Set a goal and the agent iterates until it succeeds — no babysitting required.
Every tool call, validation failure, rejection reason, and accepted result is logged and visible in the Task Center.
Google AI Studio, Mistral, OpenRouter, NVIDIA, LiteLLM, Ollama (local), AWS Bedrock, GCP Vertex AI, Azure OpenAI.
Use TradingSpy as a backend for scripts, other agents, or custom integrations via /v1/chat/completions.
All data stored locally. No external accounts, no telemetry, no cloud dependency. Your data stays on your machine.
Each agent is purpose-built for a specific task. Pick one or let the system route your request automatically.
Example prompt
"Generate until it beats buy and hold for QQQ. Use daily candles."
Generates strategies from the AI Strategy Studio, backtests them, and loops until one beats the target benchmark. Supports improving a previous version or racing against a custom baseline.
Example prompt
"Predict the next move for btc-usd for daily interval"
Reads recent bars and support/resistance levels to predict the price trend.
Example prompt
"Scan AI stocks until you find 10 which are good enough on fundamentals"
Screens a universe for valuation/growth/profitability candidates, enriches passing names with market context, news, options, and insider summaries.
Example prompt
"Give me a daily market brief with breadth, strongest and weakest industries."
Pulls data from yfinance to summarize daily market information.
Up and running in 3 steps with Docker.
Or run manually without Docker — Python 3.11 + Node.js 22
View manual setup instructionsPrice quotes, OHLCV candles, fundamentals, insider transactions, analyst recommendations, earnings dates, options chains. Primary data backbone.
Privacy-respecting metasearch for financial news, analyst opinions, macro events, and catalyst research. Runs locally.
Academic papers on quantitative finance and algorithmic trading. Abstract and full-text PDF reading.
Local backtesting engine for strategy execution, parameter optimization, and benchmark comparison.
Any Yahoo Finance-compatible symbol works.
United States
AAPL, NVDA, QQQ, SPY
London
AZN.L, HSBA.L
Hong Kong
0700.HK
Japan
7203.T
Crypto
BTC-USD, ETH-USD
Commodities
GC=F, CL=F
+ India, Canada, Australia, Germany, France, UK, Eurozone, China
Use any provider. Configure in .env or the app Settings page.
TradingSpy is for research and education only. It is not financial advice.
Backtests can overfit and do not predict future returns.
Generated strategy Python is executed locally and is not sandboxed. Review it before running.
All services bind to localhost. No telemetry. No cloud dependency.
Clone the repo, spin up Docker, and start exploring markets and strategies in minutes.