TNT-Likely/PanWatch
PanWatch — AI stock monitoring for A-shares, HK & US markets, powered by TradingAgents. Portfolio insights, real-time alerts & automated reports.｜盯盘侠：覆盖 A股/港股/美股的 AI 盯盘、持仓分析、实时提醒与自动报告。
What it solves
PanWatch provides a self-hosted system for monitoring stocks across A-shares, Hong Kong, and U.S. markets. It solves the problem of fragmented stock tracking by combining portfolio management, technical analysis, and AI-driven research into a single workspace that can be accessed via web or mobile (PWA).
How it works
The system integrates with OpenAI-compatible providers or local models (via Ollama) to power its AI capabilities. It uses a multi-agent research team (via TradingAgents) to perform deep analysis of holdings, simulating a professional workflow where analysts conduct bull/bear debates and risk reviews before a portfolio manager issues a final decision memo. It also features a scheduler for pre-market, intraday, and closing workflows, and a flexible alert system based on combined technical conditions.
Who it’s for
It is designed for stock traders and investors who want a private, self-hosted AI assistant to automate market monitoring, perform deep fundamental and technical research, and track their portfolio performance through paper trading or real account management.
Highlights
- Multi-Agent AI Research: Employs a nine-agent team to analyze stocks through debate and risk review.
- Comprehensive Market Coverage: Supports A-shares, Hong Kong, and U.S. stocks.
- Automated Workflows: Scheduled agents for pre-market outlooks, intraday monitoring, and daily reports.
- Advanced Technical Analysis: Built-in recognition for candlestick patterns, trend indicators (MACD, RSI, KDJ), and support/resistance levels.
- Flexible Notifications: Integration with Telegram, WeCom, DingTalk, Feishu, and Bark.
- Paper Trading: Simulation environment with market-specific settlement rules (e.g., T+1 for A-shares).
Related
- Project
x-pai/AlphaBotAlphaBot is an open‑source, Docker‑deployable web app that combines a LLM‑driven chat assistant with real‑time market data (global via Alpha Vantage, Chinese A‑shares via Tushare/AKShare). It offers AI‑generated technical and fundamental analysis, chart visualisation, risk assessment, and simple quant‑strategy suggestions for retail investors.
- Project
onllm-dev/onWatchonWatch is a cross‑platform daemon that monitors usage quotas for many AI‑coding services (Anthropic, Codex, Copilot, MiniMax, etc.). It stores historical data locally, serves a Material‑Design web dashboard, and offers alerts, a system‑tray widget, and a VS Code extension so developers can avoid throttling and manage AI spending.
- Project
simonlin1212/TradingAgents-astockA Chinese‑market‑focused fork of the open‑source TradingAgents framework. It adds seven analyst agents (including policy, hot‑money and lock‑up specialists), adapts trading rules to A‑share specifics (T+1, price limits, lot size), and uses free data sources (mootdx, Tencent, East‑Money, Sina, Tonghuashun). Two tiers of LLMs (quick and deep) drive the pipeline: analysts → bull/bear debate → research manager → trader → three‑way risk debate → portfolio manager, producing a Chinese‑language investment report. Install via `pip install -e .`, configure an LLM provider in `.env`, and run via a Streamlit web UI or CLI. Includes performance‑tracking commands that compute direction‑accuracy against the CSI‑300 benchmark without extra LLM calls.
- Project
lc2panda/alphastreamAlphastream is an AI‑driven financial analysis web app. It uses DeepSeek/any OpenAI‑compatible LLM with LangGraph to run 14 specialized agents (technical, fundamental, sentiment, risk, etc.) plus four investor‑persona agents. Real‑time market data comes from dual adapters (AKShare & BaoStock) covering Chinese, US, Hong‑Kong, crypto and macro sources. The Next.js + React front‑end shows a dark glass‑morphism UI with chat, dashboards and chart cards, while the Flask backend streams agent progress via SSE. All services can be launched with a single Docker‑Compose command.
- Dispatch