@DanKornas: Testing a trading strategy shouldn’t mean rebuilding the backtesting stack. AI-Trader is a config-driven Python framewo…
Summary
AI-Trader is an open-source Python framework that simplifies backtesting and optimizing algorithmic trading strategies across multiple markets using config-driven YAML files and AI assistant integration.
View Cached Full Text
Cached at: 08/15/26, 07:53 PM
Testing a trading strategy shouldn’t mean rebuilding the backtesting stack.
AI-Trader is a config-driven Python framework built on Backtrader for testing and optimizing algorithmic trading strategies across stocks, crypto, and forex.
It helps you move from an idea to a repeatable backtest by combining YAML configurations, built-in strategies, market-data commands, and an MCP server in one repo.
Key features:
• Config-driven backtests – define broker, data, strategy, and sizing settings in version-controlled YAML files • 20+ built-in strategies – start with classic indicators or adaptive models, then add your own strategy classes • Multi-market support – fetch and test data for US stocks, Taiwan stocks, cryptocurrencies, and forex • Practical CLI – run backtests, fetch market data, list strategies, or launch a quick test against your own CSV • MCP integration – let AI assistants such as Claude run backtests, fetch data, and analyze strategies through natural-language requests
It’s open-source (GPL-3.0 license).
Link in the reply
Similar Articles
@DanKornas: Need to test multiple trading strategies without stitching together separate backtest systems? Magents is an open-sourc…
Magents is an open-source Python framework for simulating and backtesting multiple trading strategies in one system, with isolated strategy pods, an event-driven engine, and central risk controls.
@DanKornas: AI in finance spans too many papers, tools, datasets, and trading frameworks to track one by one. Awesome AI in Finance…
Awesome AI in Finance is an open-source curated resource list covering papers, tools, datasets, and trading frameworks for AI and quantitative finance, organized into categories like agents, research, strategies, data, and trading stacks.
@ken_so: Just shipped /backtest for our open-source Kalshi trading bot. Does the AI model actually find edge? Now you can check …
OctagonAI released an open-source CLI that backtests AI-driven edge detection on Kalshi prediction markets, executing sized trades via half-Kelly sizing and a 5-gate risk engine.
@tom_doerr: Generates and rigorously validates algorithmic trading strategies using Claude https://github.com/zostaff/ai-quant-rese…
ai-quant-lab is an open-source Python framework that uses Claude to generate algorithmic trading strategies and rigorously validates them with statistical tests to avoid overfitting.
Autonomous AI trading is harder than it looks — deterministic behavior in live markets nearly broke me
The author details the challenges of building a deterministic autonomous trading agent using a Rust execution layer and Python AI layer with Claude/OpenAI, emphasizing the critical role of hard-coded risk management to prevent emotional or inconsistent trading.