An open agent framework where the AI agent gets its own Dockerized Linux desktop, browser, and document tools to carry out real work.
19,5 mil3,8 milPythonOtherAtualizado há 5 dias
TNT-Likely/PanWatch
Self-hosted AI stock monitor for A-shares, Hong Kong and US stocks, with portfolio tracking, price alerts, TradingAgents deep analysis and scheduled reports.
Alternativa open source a:Futu NiuNiu
Yahoo Finance
TradingView
- Estrelas
- 2,137
- Forks
- 0
- Issues abertas
- 0
- Último commit
- anteontem
Recursos principais
- 01Monitors A-shares, Hong Kong and US stocks plus listed ETFs in one workspace.
- 02Combines price, change, turnover and volume conditions into alert rules with cooldowns and expiry.
- 03Runs scheduled pre-market, intraday and daily-report agents that skip exchange holidays.
- 04Starts TradingAgents deep analysis on a holding, with the reasoning trail kept for review.
- 05Includes a paper-trading simulator with market-specific settlement rules.
- 06Works with any OpenAI-compatible provider or local Ollama models.
Casos de uso
- Individual investors tracking several brokerage accounts across mainland China, Hong Kong and the US.
- Traders who want threshold alerts pushed to Telegram, Feishu or DingTalk.
- Developers testing LLM-driven trading research workflows on their own infrastructure.
- Users who prefer keeping market data and model keys on a private server.
Tópicos
Perguntas frequentes
- O que é PanWatch?
- Self-hosted AI stock monitor for A-shares, Hong Kong and US stocks, with portfolio tracking, price alerts, TradingAgents deep analysis and scheduled reports.
- PanWatch é gratuito? Qual é a licença?
- PanWatch é open source sob a licença MIT. Confira os termos da licença antes de usá-lo em produtos comerciais.
- PanWatch ainda é mantido?
- Manutenção ativa. O último commit de PanWatch foi em 18 de out. de 2026.
- Para que posso usar PanWatch?
- Individual investors tracking several brokerage accounts across mainland China, Hong Kong and the US. Traders who want threshold alerts pushed to Telegram, Feishu or DingTalk. Developers testing LLM-driven trading research workflows on their own infrastructure. Users who prefer keeping market data and model keys on a private server.
- Onde consigo PanWatch?
- O código-fonte e as instruções de instalação estão no GitHub: https://github.com/TNT-Likely/PanWatch
Resumo gerado por IA a partir do README do projeto. As estatísticas do GitHub são atualizadas diariamente.
Projetos relacionados
Open-source skill memory layer that turns agent learnings into editable Markdown skill files shared across agents and LLMs.
3,7 mil0JavaScriptApache-2.0Atualizado há 3 meses
A desktop workbench for China A-share stock research that combines market data, theme analysis, AI stock research, portfolio review and daily post-market summaries.
1,5 mil0GoOtherAtualizado há 3 dias
A self-hosted subtitle system where an LLM agent finds, verifies and installs subtitles for your media library, and translates when no source has one.
1260TypeScriptAGPL-3.0Atualizado há 2 meses
An open-source coding agent that reads your project, edits files and runs tests from your terminal, desktop, browser or editor.
35,9 mil2,5 milGoMITAtualizado há 2 horas
An open-source autonomous research agent that plans questions, gathers web and local sources, and writes cited reports with any LLM provider.
30,2 mil4,3 milPythonApache-2.0Atualizado há 9 dias