[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-50":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":15,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":16,"rankGlobal":10,"rankLanguage":10,"license":17,"archived":18,"fork":18,"defaultBranch":19,"hasWiki":20,"hasPages":18,"topics":21,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":15,"starSnapshotCount":15,"syncStatus":44,"lastSyncTime":45,"discoverSource":46},50,"trading-agents","lukiIabs\u002Ftrading-agents","lukiIabs","TradingAgents LLM multi-agent finance trading stocks crypto fintech quantitative algo trading sentiment analysis OpenAI JavaScript Node.js research OSS","https:\u002F\u002Fgithub.com\u002FlukiIabs\u002Ftrading-agents",null,"Python",233,216,240,0,7.01,"Apache License 2.0",false,"main",true,[22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"agents","algorithmic-trading","crypto","finance","fintech","javascript","llm","machine-learning","multi-agent","nlp","nodejs","open-source","openai","quantitative-trading","research","sentiment-analysis","stocks","trading","trading-bots","2026-06-12 02:00:07","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002FTauricResearch.png\" style=\"width: 60%; height: auto;\">\n\u003C\u002Fp>\n\n\u003Cdiv align=\"center\" style=\"line-height: 1;\">\n  \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.20138\" target=\"_blank\">\u003Cimg alt=\"arXiv\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2412.20138-B31B1B?logo=arxiv\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002Fhk9PGKShPK\" target=\"_blank\">\u003Cimg alt=\"Discord\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-TradingResearch-7289da?logo=discord&logoColor=white&color=7289da\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\".\u002Fassets\u002Fwechat.png\" target=\"_blank\">\u003Cimg alt=\"WeChat\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWeChat-TauricResearch-brightgreen?logo=wechat&logoColor=white\"\u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fx.com\u002FTauricResearch\" target=\"_blank\">\u003Cimg alt=\"X Follow\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FX-TauricResearch-white?logo=x&logoColor=white\"\u002F>\u003C\u002Fa>\n  \u003Cbr>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FTauricResearch\u002F\" target=\"_blank\">\u003Cimg alt=\"Community\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FJoin_GitHub_Community-TauricResearch-14C290?logo=discourse\"\u002F>\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003C!-- Keep these links. Translations will automatically update with the README. -->\n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=de\">Deutsch\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=es\">Español\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=fr\">français\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=ja\">日本語\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=ko\">한국어\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=pt\">Português\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=ru\">Русский\u003C\u002Fa> | \n  \u003Ca href=\"https:\u002F\u002Fwww.readme-i18n.com\u002FTauricResearch\u002FTradingAgents?lang=zh\">中文\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n**Org fork — clone:** `https:\u002F\u002Fgithub.com\u002FlukiIabs\u002Ftrading-agents.git` · **SSH:** `git@github.com:lukiIabs\u002Ftrading-agents.git` · **Homepage:** [github.com\u002FlukiIabs\u002Ftrading-agents](https:\u002F\u002Fgithub.com\u002FlukiIabs\u002Ftrading-agents) · **Upstream:** [TauricResearch\u002FTradingAgents](https:\u002F\u002Fgithub.com\u002FTauricResearch\u002FTradingAgents) · **Maintainer:** [@whitevision11](https:\u002F\u002Fgithub.com\u002Fwhitevision11) · **Org:** [lukiIabs](https:\u002F\u002Fgithub.com\u002FlukiIabs)  \n**Discoverability:** TradingAgents, JavaScript, Node.js, LLM agents, finance, trading, crypto, forex, equities, sentiment analysis, multi-agent systems, stocks, fintech, quantitative finance, algorithmic trading, OpenAI API, market data, research framework, OSS, GitHub, NLP, portfolio, backtesting, alpha, risk management, LangGraph alternative, JS runtime\n\n---\n\n# TradingAgents: Multi-Agents LLM Financial Trading Framework\n\n## News\n- [2026-05] **JavaScript runtime** — this checkout’s default runtime is **Node.js** (`package.json`, `src\u002F`). The original LangGraph\u002FPython stack is kept under `legacy-python\u002F`.\n\n- [2026-04] **TradingAgents v0.2.4** released with structured-output agents (Research Manager, Trader, Portfolio Manager), LangGraph checkpoint resume, persistent decision log, DeepSeek\u002FQwen\u002FGLM\u002FAzure provider support, Docker, and a Windows UTF-8 encoding fix. See [CHANGELOG.md](CHANGELOG.md) for the full list.\n- [2026-03] **TradingAgents v0.2.3** released with multi-language support, GPT-5.4 family models, unified model catalog, backtesting date fidelity, and proxy support.\n- [2026-03] **TradingAgents v0.2.2** released with GPT-5.4\u002FGemini 3.1\u002FClaude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability.\n- [2026-02] **TradingAgents v0.2.0** released with multi-provider LLM support (GPT-5.x, Gemini 3.x, Claude 4.x, Grok 4.x) and improved system architecture.\n- [2026-01] **Trading-R1** [Technical Report](https:\u002F\u002Farxiv.org\u002Fabs\u002F2509.11420) released, with [Terminal](https:\u002F\u002Fgithub.com\u002FTauricResearch\u002FTrading-R1) expected to land soon.\n\n\u003Cdiv align=\"center\">\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F#TauricResearch\u002FTradingAgents&Date\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=TauricResearch\u002FTradingAgents&type=Date&theme=dark\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=TauricResearch\u002FTradingAgents&type=Date\" \u002F>\n   \u003Cimg alt=\"TradingAgents Star History\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=TauricResearch\u002FTradingAgents&type=Date\" style=\"width: 80%; height: auto;\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>\n\u003C\u002Fdiv>\n\n> 🎉 **TradingAgents** officially released! We have received numerous inquiries about the work, and we would like to express our thanks for the enthusiasm in our community.\n>\n> So we decided to fully open-source the framework. Looking forward to building impactful projects with you!\n\n\u003Cdiv align=\"center\">\n\n🚀 [TradingAgents](#tradingagents-framework) | ⚡ [Installation & CLI](#installation-and-cli) | 🎬 [Demo](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=90gr5lwjIho) | 📦 [Package Usage](#tradingagents-package) | 🤝 [Contributing](#contributing) | 📄 [Citation](#citation)\n\n\u003C\u002Fdiv>\n\n## TradingAgents Framework\n\nTradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. By deploying specialized LLM-powered agents: from fundamental analysts, sentiment experts, and technical analysts, to trader, risk management team, the platform collaboratively evaluates market conditions and informs trading decisions. Moreover, these agents engage in dynamic discussions to pinpoint the optimal strategy.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fschema.png\" style=\"width: 100%; height: auto;\">\n\u003C\u002Fp>\n\n> TradingAgents framework is designed for research purposes. Trading performance may vary based on many factors, including the chosen backbone language models, model temperature, trading periods, the quality of data, and other non-deterministic factors. [It is not intended as financial, investment, or trading advice.](https:\u002F\u002Ftauric.ai\u002Fdisclaimer\u002F)\n\nOur framework decomposes complex trading tasks into specialized roles. This ensures the system achieves a robust, scalable approach to market analysis and decision-making.\n\n### Analyst Team\n- Fundamentals Analyst: Evaluates company financials and performance metrics, identifying intrinsic values and potential red flags.\n- Sentiment Analyst: Analyzes social media and public sentiment using sentiment scoring algorithms to gauge short-term market mood.\n- News Analyst: Monitors global news and macroeconomic indicators, interpreting the impact of events on market conditions.\n- Technical Analyst: Utilizes technical indicators (like MACD and RSI) to detect trading patterns and forecast price movements.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fanalyst.png\" width=\"100%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\n### Researcher Team\n- Comprises both bullish and bearish researchers who critically assess the insights provided by the Analyst Team. Through structured debates, they balance potential gains against inherent risks.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fresearcher.png\" width=\"70%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\n### Trader Agent\n- Composes reports from the analysts and researchers to make informed trading decisions. It determines the timing and magnitude of trades based on comprehensive market insights.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Ftrader.png\" width=\"70%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\n### Risk Management and Portfolio Manager\n- Continuously evaluates portfolio risk by assessing market volatility, liquidity, and other risk factors. The risk management team evaluates and adjusts trading strategies, providing assessment reports to the Portfolio Manager for final decision.\n- The Portfolio Manager approves\u002Frejects the transaction proposal. If approved, the order will be sent to the simulated exchange and executed.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Frisk.png\" width=\"70%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\n## Installation and CLI (Node.js — default)\n\n### Requirements\n\n- **Node.js** ≥ 18.17\n- **OPENAI_API_KEY** in `.env` (see [.env.example](.env.example))\n- Optional: **FINNHUB_API_KEY** or **ALPHA_VANTAGE_API_KEY** for live quotes \u002F daily bars (otherwise a **stub** bundle is used so the LLM pipeline still runs)\n\n### Install\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FTauricResearch\u002FTradingAgents.git\ncd TradingAgents\ncp .env.example .env   # then edit keys\nnpm install\n```\n\n### Run (programmatic, like the old `main.py`)\n\n```bash\nnpm start\n# or: node src\u002Fmain.js [TICKER] [YYYY-MM-DD]\n```\n\n### CLI\n\n```bash\nnpx tradingagents propagate NVDA 2024-05-10\n# or: npm run tradingagents -- propagate AAPL 2024-01-16 --quiet\n```\n\n### Docker\n\n```bash\ndocker compose build\ndocker compose run --rm tradingagents propagate NVDA 2024-05-10\n```\n\n### Python (archived)\n\nThe previous **LangGraph \u002F LangChain** implementation is under [`legacy-python\u002F`](legacy-python\u002FREADME.md) (`pip install -e .` from that directory if you need it).\n\n---\n\n\u003Cdetails>\n\u003Csummary>Legacy README: conda \u002F pip install (Python primary)\u003C\u002Fsummary>\n\n### Installation (historical)\n\nClone TradingAgents:\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FTauricResearch\u002FTradingAgents.git\ncd TradingAgents\n```\n\nCreate a virtual environment in any of your favorite environment managers:\n```bash\nconda create -n tradingagents python=3.13\nconda activate tradingagents\n```\n\nInstall the package and its dependencies:\n```bash\npip install .\n```\n\n### Docker\n\nAlternatively, run with Docker:\n```bash\ncp .env.example .env  # add your API keys\ndocker compose run --rm tradingagents\n```\n\nFor local models with Ollama:\n```bash\ndocker compose --profile ollama run --rm tradingagents-ollama\n```\n\n### Required APIs\n\nTradingAgents supports multiple LLM providers. Set the API key for your chosen provider:\n\n```bash\nexport OPENAI_API_KEY=...          # OpenAI (GPT)\nexport GOOGLE_API_KEY=...          # Google (Gemini)\nexport ANTHROPIC_API_KEY=...       # Anthropic (Claude)\nexport XAI_API_KEY=...             # xAI (Grok)\nexport DEEPSEEK_API_KEY=...        # DeepSeek\nexport DASHSCOPE_API_KEY=...       # Qwen (Alibaba DashScope)\nexport ZHIPU_API_KEY=...           # GLM (Zhipu)\nexport OPENROUTER_API_KEY=...      # OpenRouter\nexport ALPHA_VANTAGE_API_KEY=...   # Alpha Vantage\n```\n\nFor enterprise providers (e.g. Azure OpenAI, AWS Bedrock), copy `.env.enterprise.example` to `.env.enterprise` and fill in your credentials.\n\nFor local models, configure Ollama with `llm_provider: \"ollama\"` in your config.\n\nAlternatively, copy `.env.example` to `.env` and fill in your keys:\n```bash\ncp .env.example .env\n```\n\n### CLI Usage\n\nLaunch the interactive CLI:\n```bash\ntradingagents          # installed command\npython -m cli.main     # alternative: run directly from source\n```\nYou will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fcli\u002Fcli_init.png\" width=\"100%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\nAn interface will appear showing results as they load, letting you track the agent's progress as it runs.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fcli\u002Fcli_news.png\" width=\"100%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fcli\u002Fcli_transaction.png\" width=\"100%\" style=\"display: inline-block; margin: 0 2%;\">\n\u003C\u002Fp>\n\n\u003C\u002Fdetails>\n\n## TradingAgents Package\n\n### Implementation Details\n\nWe built TradingAgents with LangGraph to ensure flexibility and modularity. The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen (Alibaba DashScope), GLM (Zhipu), OpenRouter, Ollama for local models, and Azure OpenAI for enterprise.\n\n### JavaScript usage (default in this repo)\n\n```javascript\nimport 'dotenv\u002Fconfig';\nimport { TradingAgentsGraph, DEFAULT_CONFIG } from '.\u002Fsrc\u002Findex.js';\n\nconst config = { ...DEFAULT_CONFIG };\nconst ta = new TradingAgentsGraph({ debug: true, config });\nconst [, decision] = await ta.propagate('NVDA', '2024-05-10');\nconsole.log(decision);\n```\n\nThe JS runtime uses a **sequential OpenAI chat pipeline** (analyst → research debate → trader → risk\u002FPM). LangGraph checkpointing, the Rich interactive CLI, and non-OpenAI providers are only in **`legacy-python\u002F`**.\n\n### Python Usage (archived)\n\nTo use TradingAgents inside your code, you can import the `tradingagents` module and initialize a `TradingAgentsGraph()` object. The `.propagate()` function will return a decision. You can run `main.py`, here's also a quick example:\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())\n\n# forward propagate\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nYou can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc.\n\n```python\nfrom tradingagents.graph.trading_graph import TradingAgentsGraph\nfrom tradingagents.default_config import DEFAULT_CONFIG\n\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"llm_provider\"] = \"openai\"        # openai, google, anthropic, xai, deepseek, qwen, glm, openrouter, ollama, azure\nconfig[\"deep_think_llm\"] = \"gpt-5.4\"     # Model for complex reasoning\nconfig[\"quick_think_llm\"] = \"gpt-5.4-mini\" # Model for quick tasks\nconfig[\"max_debate_rounds\"] = 2\n\nta = TradingAgentsGraph(debug=True, config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\nprint(decision)\n```\n\nSee `tradingagents\u002Fdefault_config.py` for all configuration options.\n\n## Persistence and Recovery\n\n> **JavaScript runtime:** the Node implementation currently writes **`full_states_log_\u003Cdate>.json`** under `~\u002F.tradingagents\u002Flogs\u002F\u003Cticker>\u002FTradingAgentsStrategy_logs\u002F`. Decision-log reflection and LangGraph checkpoints below apply to **`legacy-python\u002F`** only unless ported.\n\nTradingAgents persists two kinds of state across runs.\n\n### Decision log\n\nThe decision log is always on. Each completed run appends its decision to `~\u002F.tradingagents\u002Fmemory\u002Ftrading_memory.md`. On the next run for the same ticker, TradingAgents fetches the realised return (raw and alpha vs SPY), generates a one-paragraph reflection, and injects the most recent same-ticker decisions plus recent cross-ticker lessons into the Portfolio Manager prompt, so each analysis carries forward what worked and what didn't.\n\nOverride the path with `TRADINGAGENTS_MEMORY_LOG_PATH`.\n\n### Checkpoint resume\n\nCheckpoint resume is opt-in via `--checkpoint`. When enabled, LangGraph saves state after each node so a crashed or interrupted run resumes from the last successful step instead of starting over. On a resume run you will see `Resuming from step N for \u003CTICKER> on \u003Cdate>` in the logs; on a new run you will see `Starting fresh`. Checkpoints are cleared automatically on successful completion.\n\nPer-ticker SQLite databases live at `~\u002F.tradingagents\u002Fcache\u002Fcheckpoints\u002F\u003CTICKER>.db` (override the base with `TRADINGAGENTS_CACHE_DIR`). Use `--clear-checkpoints` to reset all of them before a run.\n\n```bash\ntradingagents analyze --checkpoint           # enable for this run\ntradingagents analyze --clear-checkpoints    # reset before running\n```\n\n```python\nconfig = DEFAULT_CONFIG.copy()\nconfig[\"checkpoint_enabled\"] = True\nta = TradingAgentsGraph(config=config)\n_, decision = ta.propagate(\"NVDA\", \"2026-01-15\")\n```\n\n## Contributing\n\nWe welcome contributions from the community! Whether it's fixing a bug, improving documentation, or suggesting a new feature, your input helps make this project better. If you are interested in this line of research, please consider joining our open-source financial AI research community [Tauric Research](https:\u002F\u002Ftauric.ai\u002F).\n\nPast contributions, including code, design feedback, and bug reports, are credited per release in [`CHANGELOG.md`](CHANGELOG.md).\n\n## Citation\n\nPlease reference our work if you find *TradingAgents* provides you with some help :)\n\n```\n@misc{xiao2025tradingagentsmultiagentsllmfinancial,\n      title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, \n      author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang},\n      year={2025},\n      eprint={2412.20138},\n      archivePrefix={arXiv},\n      primaryClass={q-fin.TR},\n      url={https:\u002F\u002Farxiv.org\u002Fabs\u002F2412.20138}, \n}\n```\n","TradingAgents 是一个基于多代理的大规模语言模型（LLM）金融交易框架。该项目利用先进的自然语言处理技术、情感分析和算法交易策略，支持股票、加密货币等金融资产的量化交易。其核心功能包括多代理系统设计、OpenAI API 集成以及强大的市场数据分析能力。TradingAgents 采用 Node.js 和 JavaScript 开发，同时也保留了 Python 版本以满足不同用户需求。它非常适合金融机构、研究人员及个人投资者用于开发和测试复杂的交易策略，特别是在需要结合文本信息进行决策的情境下。",2,"2026-05-06 17:18:25","CREATED_QUERY"]