# HKUDS/Vibe-Trading

> AI agent for trading and quantitative research: runs backtests, factor analysis, paper trading and live strategies via LLM and MCP. Aimed at traders and quant developers.

- Magnitude: 3.4 out of 10 — Steady
- Stars: 36,280 total · +15 stars measured 2026-10-22, 10:41–12:54 UTC, ≈ 56 by evening
- Star trust: star growth looks organic
- Category: Finance & crypto · Language: Python · License: MIT · Created: 2026-04-01 · Last push: 2026-10-21
- GitHub: https://github.com/HKUDS/Vibe-Trading · Homepage: https://vibetrading.wiki/ · Page: https://gitnova.dev/en/r/HKUDS/Vibe-Trading

## Useful for

- Run a backtest of a trading strategy on daily bars
- Paper-trade a strategy without connecting to a broker
- Connect the agent to your LLM provider via MCP

## Why it’s here

- Star-counter measurements on 2026-10-22 (UTC), 10:41–12:54: 36265 → 36280 stars (+15). This is the change over that interval.
- Estimated end-of-day forecast: about +56 stars, using observed gains and the previous day.
- GitHub Trending Python today: #13, +166 stars.
- About 28 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: 5,870
- Issues and pull requests: 1,921
- Watchers: 170
- Average over the last week: 105 per day
- Usual pace: 85 per day
- Stars in the last hour (measured): 4
- Latest release: v0.1.18 (2026-10-21)

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

2026-09-23 … 2026-10-22: 75, 75, 46, 50, 100, 90, 81, 59, 51, 51, 62, 230, 92, 79, 78, 74, 64, 70, 101, 101, 91, 92, 87, 67, 95, 110, 122, 117, 167, 15

## Spotted in now

- GitHub Trending Python today: #13, +166 stars

## More in this category

1. **shiyu-coder/Kronos** — 6.9 · Breakout · Finance & crypto · Python · +272 stars measured 2026-10-22, 00:37–12:51 UTC, ≈ 501 by evening
   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.
   Full card: https://gitnova.dev/en/r/shiyu-coder/Kronos.md
2. **Jakeschincariol/day-trader-skill** — 6.1 · Early signal · Finance & crypto · Python · +114 stars measured 2026-10-22, 00:37–12:52 UTC, ≈ 207 by evening
   A set of 11 Claude skills for day trading: chart scanning, news tracking, entry/exit timing, trade outcome simulation and risk checks on free public data.
   Full card: https://gitnova.dev/en/r/Jakeschincariol/day-trader-skill.md
3. **pmarket-14/polymarket-ai-trading-codex-and-claude-bot** — 5.4 · Early signal · Finance & crypto · HTML · +0 stars measured 2026-10-22, 00:37–12:52 UTC, ≈ 20 by evening
   Copy-trading bot for Polymarket: watches selected wallets' trades and mirrors them with fixed or percentage sizing, risk limits and local JSON state.
   Full card: https://gitnova.dev/en/r/pmarket-14/polymarket-ai-trading-codex-and-claude-bot.md
4. **spovalova/openterminal** — 4.9 · Early signal · Finance & crypto · TypeScript · +0 stars measured 2026-10-22, 00:02–12:52 UTC, ≈ 46 by evening
   Open-source AI-native terminal for traders: a text prompt builds a live workspace of charts, tables and option chains, with every number traceable to a query. Runs locally, no accounts, no telemetry.
   Full card: https://gitnova.dev/en/r/spovalova/openterminal.md
5. **Jakeschincariol/trader-skill** — 4.6 · Early signal · Finance & crypto · Python · +25 stars measured 2026-10-22, 00:37–12:53 UTC, ≈ 61 by evening
   A pack of 11 Claude skills that read public data (SEC EDGAR 13F filings, House PTR disclosures, news feeds) to copy trusted investors, track Congress trades, size positions to a budget, and prepare orders that require explicit user…
   Full card: https://gitnova.dev/en/r/Jakeschincariol/trader-skill.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 2026-10-22 13:05 UTC, updated every 30 minutes.