# shiyu-coder/Kronos

> Kronos is an open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 exchanges; it forecasts OHLCV series via tokenization and an autoregressive Transformer.

- Magnitude: 5.4 out of 10 — Breakout
- Stars: 45,925 total · +566 stars measured 2026-11-02, 00:07–19:54 UTC, ≈ 678 by evening
- Star trust: star growth looks organic
- Category: Finance & crypto · Language: Python · License: MIT · Created: 2025-07-01 · Last push: 2026-04-13
- GitHub: https://github.com/shiyu-coder/Kronos · Page: https://gitnova.dev/en/r/shiyu-coder/Kronos

## Useful for

- Forecast the next 24 hours of BTC/USDT candles with KronosPredictor
- Fine-tune the model on your own K-line data for a specific asset
- Run batch forecasts across multiple tickers with predict_batch

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 00:07–19:54: 45359 → 45925 stars (+566). This is the change over that interval.
- Estimated end-of-day forecast: about +678 stars, using observed gains and the previous day.
- Over the last two days the pace is 3.4× that of the previous week and a half.
- GitHub Trending today: #8, +855 stars.
- GitHub Trending Python today: #3, +855 stars.
- About 110 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 7,582
- Issues and pull requests: 418
- Watchers: 401
- Average over the last week: 353 per day
- Usual pace: 219 per day
- Stars in the last hour (measured): 21

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-04 … 2026-11-02: 81, 91, 59, 162, 69, 73, 89, 87, 63, 76, 66, 51, 39, 78, 316, 633, 619, 510, 288, 233, 155, 170, 97, 89, 67, 65, 167, 553, 852, 566

## Magnitude by day, last 14 days

10-20 8.0, 10-21 7.2, 10-22 7.1, 10-23 5.7, 10-24 4.3, 10-25 4.1, 10-26 3.4, 10-27 3.0, 10-28 2.7, 10-29 2.4, 10-30 2.6, 10-31 4.5, 11-01 5.1, 11-02 5.6

## Spotted in now

- GitHub Trending today: #8, +855 stars
- GitHub Trending Python today: #3, +855 stars

## Similar by description

1. **zadescoxp/Temporal-Fusion-Transformer-Price-Prediction** — 0.3 · Steady · Finance & crypto · Python · +0 stars measured 2026-11-02, 00:58–19:21 UTC, ≈ 0 by evening
   A local research desk for daily equity forecasts using a Temporal Fusion Transformer: one model per ticker decodes 252 trading sessions and produces quantile forecasts from 1 day to 1 year.
   Full card: https://gitnova.dev/en/r/zadescoxp/Temporal-Fusion-Transformer-Price-Prediction.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 20:10 UTC, updated every 30 minutes.