{"full_name":"TauricResearch/TradingAgents","owner":"TauricResearch","name":"TradingAgents","url":"https://github.com/TauricResearch/TradingAgents","description":"TradingAgents: Multi-Agents LLM Financial Trading Framework","homepage":"https://tauric.ai","topics":[],"language":"Python","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/192884433?v=4","created_at":"2024-12-28T03:31:08Z","pushed_at":"2026-11-04T10:13:58Z","metrics":{"stars":121753,"forks":23301,"watchers":903,"issues":541,"prs":1061,"releases":15,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":11},"growth":{"day":{"stars":297,"forks":55,"base_day":"2026-11-09"},"week":{"stars":1849,"forks":368,"base_day":"2026-11-03"},"month":{"stars":11252,"forks":2023,"base_day":"2026-10-11"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-09","2026-11-10"],"stars":[102601,102719,102876,103388,103814,104467,104678,104788,105240,105966,106604,106966,107272,107451,107597,107764,107944,108104,108298,108443,108598,108755,108895,109062,109249,109363,109456,109507,109618,109755,109865,109974,110109,110269,110374,110501,110621,110817,111007,111176,111350,111501,111701,111884,112083,112307,112540,112907,113336,113611,114366,115796,117189,117800,118255,118638,118991,119443,119904,120272,121456,121753],"forks":[19777,19810,19850,19902,19959,20025,20070,20104,20181,20290,20382,20430,20500,20546,20585,20623,20665,20695,20739,20778,20810,20845,20887,20923,20982,21000,21033,21039,21072,21096,21119,21136,21174,21202,21240,21278,21300,21345,21395,21434,21479,21506,21549,21603,21661,21695,21760,21843,21934,22003,22117,22237,22452,22544,22617,22687,22748,22855,22933,22995,23246,23301],"watchers":[776,778,780,785,790,791,796,798,799,805,803,802,805,801,804,806,814,816,817,819,818,820,826,823,824,824,824,822,824,824,823,824,826,826,829,828,830,835,836,838,840,840,840,841,842,845,845,849,856,854,863,867,866,872,877,879,885,887,888,891,903,903],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null]},"boards":{"daily":119,"weekly":77,"monthly":51,"weekly_rate":199,"monthly_rate":145,"total":98},"same_owner":[],"issues":[{"number":805,"title":"Temporal Knowledge Leakage in LLM Backtesting (Model-Level Future Information Contamination)","comments":6,"created_at":"2026-05-11T08:33:23Z"},{"number":1056,"title":"Showcase: Invest Alert Bot — alert-driven Telegram integration with TradingAgentsGraph","comments":4,"created_at":"2026-06-17T13:41:26Z"},{"number":750,"title":"Zero LLM API prompt cache hit rate due to prompt construction architecture","comments":4,"created_at":"2026-05-06T10:06:24Z"},{"number":1,"title":"Enhancing TradingAgents with RL for Event-Driven Stock Price Prediction","comments":4,"created_at":"2025-01-07T04:48:56Z"},{"number":1390,"title":"Structured output falls back to free text ~1x per run on DeepSeek thinking models","comments":3,"created_at":"2026-09-23T13:52:48Z"},{"number":1349,"title":"Feature: Add India macro FRED series as friendly aliases","comments":2,"created_at":"2026-09-15T08:27:51Z"},{"number":1323,"title":"Options positioning data (put/call, IV skew, OI) as a point-in-time data category","comments":2,"created_at":"2026-09-11T01:12:35Z"},{"number":1231,"title":"Feature request: optional Codex runtime provider using ChatGPT-managed authentication","comments":2,"created_at":"2026-08-14T03:07:45Z"}],"discussions":[{"number":1666,"title":"A control run to measure whether the agents add value beyond a pre-screen","comments":0,"category":"Ideas","created_at":"2026-11-07T11:21:14Z"},{"number":1655,"title":"Local macOS research dashboard prototype: staged runs, evidence checks and consolidated reports","comments":0,"category":"Show and tell","created_at":"2026-11-04T20:22:21Z"},{"number":1639,"title":"Data-provider offer: a keyless Company Research Job for the analyst pipeline","comments":0,"category":"Show and tell","created_at":"2026-11-02T10:35:56Z"},{"number":1555,"title":"From rating to order, with hard limits: a small bridge for people who paper-trade TradingAgents' output","comments":0,"category":"Show and tell","created_at":"2026-10-21T14:13:09Z"},{"number":1553,"title":"Proposed contribution: financial-analysis guidance and data-quality reporting","comments":0,"category":"Ideas","created_at":"2026-10-20T15:43:05Z"},{"number":1538,"title":"PERPBRAIN: rerunnable Hyperliquid cost receipts for agent decisions (feedback wanted)","comments":0,"category":"Show and tell","created_at":"2026-10-17T05:53:21Z"},{"number":1532,"title":"[Show and Tell] Lumina Capital — Production-Grade Multi-Agent Hedge Fund Engine (LangGraph, 8-Legend Council, TimesFM & Qlib)","comments":0,"category":"Show and tell","created_at":"2026-10-15T07:22:16Z"},{"number":1505,"title":"Should verified snapshots disclose partial indicator windows and initialization?","comments":0,"category":"Q&A","created_at":"2026-10-09T12:07:00Z"}],"latest_release":{"name":"TradingAgents v0.7.1","tag":"v0.7.1","published_at":"2026-10-27T08:43:04Z","body":"Decisions are scored only on final closes and settle across long market holidays, a model's unpadded date no longer reads filings made after the run date, and fixes to portfolios, prices, SEC statements, reports, Azure and Claude settings.\n\n## Upgrading from 0.7.0\n\n- Docker images no longer include `.env.enterprise`. For Azure OpenAI in Docker, put its keys in `.env`.\n\n## Fixed\n\n- A date a model passes without zero padding, such as `2024-7-5`, is read as that date. It could compare as later than a filing made after the run date, and SEC EDGAR then served that filing. (#1488)\n- A decision is no longer scored on the bar of a session still trading, and one made before a market closure longer than a week, such as a national holiday, settles once trading resumes instead of staying pending. (#1548, #1539)\n- A backtest reports the failures of its last settlement pass, and two started in the same second no longer share one run. (#1557, #1549)\n- A holding listed under a broker's spelling (`BTCUSDT`, `700.HK`) is matched to the instrument analyzed, and a portfolio number that is not finite is refused when the file loads. (#1556, #1509)\n- Prices keep their significant digits: a sub-cent close no longer prints as 0.00, and a currency pair keeps its pips. (#1567)\n- SEC EDGAR statements list one row per period, so a model no longer reads a figure against the wrong quarter across a long history, and a figure under one million no longer prints as 0. (#1517, #1589)\n- Saving a report to a folder used before removes the earlier run's sections. (#1566)\n- A date window that ends before it starts is sent back to the model instead of returning no data. (#1595)\n- A statement frequency other than annual or quarterly is sent back to the model instead of being served annual figures under that word. (#1593)\n- The memory's most recent lessons, and the entries rotation keeps, follow decision dates, so a backfill of older dates no longer displaces them. (#1603)\n- Prediction-market odds near 0% or 100% show their distance from it to two significant digits. (#1598)\n- Azure OpenAI receives `max_tokens` and a configured endpoint. (#1584, #1600)\n- Claude's effort setting is decided correctly for dated model IDs such as `claude-sonnet-4-20250514`. (#1585)\n- The CLI checks a ticker with the same rule as the run, so `XAUUSD+` is accepted and `..` is refused at the prompt. (#1604)\n- Docker images no longer include `.env` files from any folder.\n- Tests that failed on Windows and macOS for platform reasons are fixed. (#1506, #1485, #1541)\n\n## Contributors\n\n[@alanfate3](https://github.com/alanfate3), [@aranlucas](https://github.com/aranlucas), [@BichengWang](https://github.com/BichengWang), [@Bortlesboat](https://github.com/Bortlesboat), [@hoffman988](https://github.com/hoffman988), [@jhill-cmd](https://github.com/jhill-cmd), [@muhib-karim](https://github.com/muhib-karim), [@pei711](https://github.com/pei711), [@peiji1981](https://github.com/peiji1981), [@rudycelekli](https://github.com/rudycelekli), [@Shubham-Padkonde](https://github.com/Shubham-Padkonde), [@stevexyz2003](https://github.com/stevexyz2003), [@SuperMarioYL](https://github.com/SuperMarioYL), [@sytfly](https://github.com/sytfly), [@yuv009](https://github.com/yuv009).\n"},"readme":true,"readme_zh":false,"news":[{"title":"Multi-Agents LLM Financial Trading Framework","url":"https://github.com/TauricResearch/TradingAgents","hn":"https://news.ycombinator.com/item?id=49605822","source":"Hacker News","lang":"en","date":"2026-09-08","points":120,"comments":81},{"title":"CLI-based multi-agent trading system using LLMs","url":"https://github.com/TauricResearch/TradingAgents","hn":"https://news.ycombinator.com/item?id=45189763","source":"Hacker News","lang":"en","date":"2025-09-09","points":2,"comments":0},{"title":"Trading Agents – Multi-Agent LLM Financial Trading Network","url":"https://github.com/TauricResearch/TradingAgents","hn":"https://news.ycombinator.com/item?id=47954608","source":"Hacker News","lang":"en","date":"2026-04-29","points":1,"comments":0},{"title":"Viral TradingAgents Repo Brings Full AI Analyst Team and Live Trade Execution to Claude Code","url":"https://phemex.com/news/article/viral-tradingagents-repo-brings-full-ai-analyst-team-and-live-trade-execution-to-claude-code-102245","source":"phemex","lang":"en","date":"2026-11-03"},{"title":"“AI对冲基金”能抓住10倍行情吗？实测 TradingAgents（GitHub 97.6k星）","url":"https://www.bilibili.com/video/BV1UF8G6dEQE/","source":"bilibili","lang":"zh","date":"2026-08-20"},{"title":"GitHub - TauricResearch/TradingAgents: TradingAgents：多智能体 LLM 金融交易框架 · GitHub","url":"https://blog.csdn.net/design1985/article/details/162412227","source":"blog.csdn","lang":"zh","date":"2026-06-29"},{"title":"TradingAgents：多代理 LLM 框架革新金融交易決策","url":"https://www.techritual.com/2026/06/13/526525/","source":"techritual","lang":"zh","date":"2026-06-13"},{"title":"【GitHub项目推荐--TradingAgents-CN：基于多智能体LLM的中文金融交易框架】","url":"https://blog.csdn.net/j8267643/article/details/152706703","source":"blog.csdn","lang":"zh","date":"2025-10-08"},{"title":"【方正金工】多智能体投资交易系统TradingAgents部署与应用——AI Agent赋能金融投研应用系列之一","url":"https://finance.sina.com.cn/roll/2025-09-08/doc-infpumzk6172587.shtml","source":"新浪网","lang":"zh","date":"2025-09-08"},{"title":"71.4K Star的AI交易团队：多智能体架构如何“炒”出一个华尔街","url":"https://news.google.com/rss/articles/CBMidkFVX3lxTE5CSkxuUkNKTFNubXlXSk54ZkZ4Q3pPb1U4UXpMbWVCeFJ3QWFNcHV5cGRXOTFWYlk1bUZMdHFNOUhFb3FPZjdxV2FXTDBaWktibXZKbnBSTURQaFBRbkNxV2hsTl9uVjFrU25hcDlwLUpUUUw4c2c?oc=5","source":"新浪财经","lang":"zh","date":"2026-05-10"},{"title":"唐杰高徒打造龙虾投资军团，量化私募全线Agent，开源狂揽39k星","url":"https://news.google.com/rss/articles/CBMiTkFVX3lxTE4xMWhyRG9VRzdDNGptN2dlT0pCNk4yV3pQaDNSOFpGZ0dXT2hkNDloTEFVWGQycHAxbk1wS2pOVlhXdmFOam5xeGFIRUhIZw?oc=5","source":"36氪","lang":"zh","date":"2026-03-30"},{"title":"AI金融交易开源Agent火了，对苹果狂赚26.6%","url":"https://news.google.com/rss/articles/CBMiVkFVX3lxTE1pVE4zV3FnOHZvQTNZRDhSSXlCMEdvZFNNSUtpVzA2ZU9iM0F2MHVETkhuSm5ZQmNqMjYyTEdmMnA4dGt3Nlhqak92dmtrZFliWkhJR0xn?oc=5","source":"腾讯新闻","lang":"zh","date":"2025-06-30"}],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}