AI/TLDR

HKUDS · 2026-07-10 · notable

Vibe-Trading 0.1.11 — HKUDS ships Indian equity and a 460-factor library

Vibe-Trading's July 10 release adds NSE and BSE as first-class backtest markets, a point-in-time fundamentals layer that grows the Alpha Zoo to 460 factors, and research delivery across 16 messaging channels.

Vibe-Trading GitHub repository social card

AI trading agent gains India equity, a fundamentals factor layer, and research delivery over 16 messaging apps.

What is it?

Vibe-Trading is an open-source multi-agent finance research platform from HKUDS. Natural-language questions become runnable backtests handled by swarm teams — an investment committee, quant desk, risk review, macro, and crypto — and the July 10 release makes the Indian NSE and BSE first-class backtest venues alongside US equities, crypto, futures, forex, and options.

How does it work?

v0.1.11 introduces a point-in-time-safe fundamentals layer that turns SEC company facts into daily factor panels with filed-date anchoring, keeping backtests honest about what was public when. It also adds an automated scheduler so hypothesis to signal-engine to backtest workflows run in the background, plus a Trading 212 broker connector and turnover-aware portfolio optimization.

Why does it matter?

Adding NSE and BSE with T+1 delivery, configurable circuit bands, and tax-aware cost modeling opens quant research to Indian markets that most open-source backtesters skip. The Alpha Zoo now covers 460 factors across five families, and results can land in Telegram, Slack, Discord, WhatsApp, WeChat, and 11 other channels — meeting analysts where they already work.

Who is it for?

Quant researchers and finance-focused developers

Sources · 2 outlets

Tags

  • repo
  • tool
  • trading
  • quant
  • agent
  • multi-agent
  • backtest
  • open-source
  • python
  • hkuds
  • vibe-trading

← All releases · Learn AI