Skip to content
repository radar
Agents & Orchestration

📈Vibe-Trading

ACTIVE BREAKOUT

HKUDS/Vibe-Trading · homepage ↗

"Vibe-Trading: Your Personal Trading Agent"

⭐ Very popular: 31k stars, gaining about 2k a week

View on GitHub ↗

repo profile

vintage 2026 launched this year
delivery library
language Python
license MIT

momentum

total stars 31k
stars added last week +2k
weekly downloads 4k /wk · PyPI
commits / week 116 accelerating · +26% vs prior mo
issues closed 100% ~1 day to close, median
contributors 134 (+23 in 15d)
release cadence fortnightly
last activity today

durability

backing foundation-backed HKU Data Intelligence Lab
openness permissive
bus factor 2 concentrated
top-author share 41% 6 mo

bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.

since we covered it

monthly average + 8k/mo (+396%/mo) · + 29k total since PR#32

why it's a big deal

  • Turns natural-language finance questions into market research, strategy generation, and backtesting, so quant researchers and active traders can work without hand-coding each analysis pipeline.
  • Ships broker connectors for IBKR, Robinhood, Tiger, Alpaca, OKX, Binance, and others, and can optionally place trades through authorized brokers with guardrails, meaning no funds are held by the platform and operations can be halted instantly.
  • Bundles a library of prebuilt quant factors and preset multi-agent team configurations (investment committees, quant desks, risk panels), giving teams reusable scaffolding for collaborative research.

under the hood

  • Python 3.11+ backend on FastAPI, with LangChain and LangGraph handling agent orchestration and MCP for tool integration, plus a React and Vite frontend using ECharts for visualization.
  • Data layer pulls from multiple market-data sources with automatic fallback via loaders including tushare, yfinance, OKX, CCXT, and AKShare, covering A-shares, HK and US equities, crypto, futures, and forex.
  • Persistence uses SQLite with FTS5 full-text search and named Docker volumes so research memory survives updates, deployed via Docker and docker-compose.

Radar summary, generated from the project's public sources

star history

PR#32 · 2k31k now Apr 2026Aug 2026
  1. PR#32 2k 2026-04-22
  2. now 31k + 29k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Output and attention are roughly in balance.

+2 understory score output 93 · clout 91
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#32 2026-04-22 below the radar

    Multi-agent trading and backtesting system

similar projects

compare these →
  • 🤖 nanobot

    Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps

    47k ACTIVE
  • 📖 ai-agent-book

    AI Agent PDF

    38k ACTIVE
  • 📚 Haystack

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

    26k ACTIVE

comments

Sign in with GitHub to add your blip on Vibe-Trading.

loading comments…