@Huanusa: This is absolutely mind-blowing! Someone actually built an AI that can directly read candlestick trading, and its performance is through the roof! It's called Kronos — the world's first open-source foundational large model designed specifically for financial markets! Trained from scratch on 12 billion real candlestick data points from 45 exchanges, not a repurposed general AI. It can: price prediction + volatility prediction and more.
Summary
Kronos is the world's first open-source foundational large model for financial markets, trained from scratch on 12 billion real candlestick data points, supporting price prediction and volatility forecasting, far outperforming general models, and completely free and open-source.
View Cached Full Text
Cached at: 05/14/26, 10:34 AM
Kronos: A Foundation Model for the Language of Financial Markets
📜 Introduction
Kronos is a family of decoder-only foundation models, pre-trained specifically for the “language” of financial markets—K-line sequences. Unlike general-purpose TSFMs, Kronos is designed to handle the unique, high-noise characteristics of financial data. It leverages a novel two-stage framework:
- A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens.
- A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks.
Similar Articles
@XAMTO_AI: Guys, there's something I just have to tell you about. An open-source AI quantitative trading platform has quietly launched. Locally self-deployable, full-chain connectivity, covering crypto, US stocks, and forex — from analysis to live trading all in one — can you believe it? Two years ago, such a thing was either ridiculously expensive or simply non-existent. Now it's directly open-sourced on G…
Introducing QuantDinger, an open-source AI quantitative trading platform that supports local deployment, full-chain connectivity for crypto, US stocks, and forex, integrating AI analysis, strategy generation, backtesting, and live trading integration.
Kronos: A Foundation Model for the Language of Financial Markets
Kronos is a new foundation model for financial K-line data that uses a specialized tokenizer and autoregressive pre-training to outperform existing models in forecasting and synthetic data generation.
@NXR_NIROX: > A Chinese girl > no quant degree, no Bloomberg terminal, no fund background > just a laptop, opened Claude Code > spent a weekend building a bot for five instruments > mean reversion on indices, breakout on Bitcoin, trend following on commodities > ATR for position sizing, 1% hard stop loss, plus…
A Chinese girl with no quant background used Claude Code over a weekend to create a trading bot covering five instruments, employing mean reversion, breakout, and trend strategies, achieving significant returns, demonstrating the potential of AI tools in automated trading.
shiyu-coder/Kronos
Kronos is an open-source foundation model for financial K-line sequences, trained on data from over 45 global exchanges. It uses a specialized tokenizer and a decoder-only Transformer, and has been accepted at AAAI 2026.
@cevenif: Guys, a library literally exploded today—nearly 90k stars, called TradingAgents, a multi-agent trading framework. In plain English: a group of AIs work together to help you trade crypto and stocks. ① Some AIs specialize in monitoring market data ② Some AIs are responsible for strategy decisions ③ Some AIs specialize…
TradingAgents is a multi-agent trading framework that uses multiple AIs working together to automate crypto and stock trading, supporting real-time data ingestion, automatic strategy generation, and continuous optimization. It has gained nearly 90k stars on GitHub.