Multi-Agents LLM Financial Trading Framework
Multi-Agents LLM Financial Trading Framework. 9k Star 103k mainBranchesTagsGo to fileCodeOpen more actions menuLatest commit History290 Commits290 CommitsFolders and filesNameNameLast commit messageLast commit date. github/workflows. github/workflows assetsassets clicli scriptsscripts teststests tradingagentstradingagents. dockerignore. dockerignore. env. enterprise. example. env. enterprise. example. env. example. env. example. gitignore. gitignore CHANGELOG. mdCHANGELOG. md DockerfileDockerfile LICENSELICENSE README. mdREADME. md docker-compose. ymldocker-compose. yml main. pymain. py pyproject. tomlpyproject. toml requirements. txtrequirements. txt test. pytest. py View all filesRepository files navigation Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文 TradingAgents: Multi-Agents LLM Financial Trading Framework News [2026-08] TradingAgents v0.
What happened
Citation Please reference our work if you find TradingAgents provides you with some help 🙂 @misc{xiao2025tradingagentsmultiagentsllmfinancial, title={TradingAgents: Multi-Agents LLM Financial Trading Framework}, author={Yijia Xiao and Edward Sun and Di Luo and Wei Wang}, year={2025}, eprint={2412. 20138}, } AboutTradingAgents: Multi-Agents LLM Financial Trading Frameworkarxiv. org/pdf/2412. TradingAgents Framework TradingAgents is a multi-agent trading framework that mirrors the dynamics of real-world trading firms. 0 released with multi-provider LLM support (GPT-5. x, Gemini 3. x, Claude 4. x, Grok 4. x) and improved system architecture. [2026-01] Trading-R1 Technical Report released, with Terminal expected to land soon. 🚀 TradingAgents | ⚡ Installation & CLI | 🎬 Demo | 📦 Package Usage | 🤝 Contributing | 📄 Citation 🎉 TradingAgents officially released!
TradingAgents framework is designed for research purposes. Docker Alternatively, run with Docker: cp. env. example. env # add your API keys docker compose run –rm tradingagents For local models with Ollama: docker compose –profile ollama run –rm tradingagents-ollama Required APIs TradingAgents supports multiple LLM providers. TauricResearch / TradingAgents Public Notifications You must be signed in to change notification settings Fork 19.
The wider picture
See CHANGELOG. md for the full list. [2026-07] TradingAgents v0. 1 released with correctness and stability fixes: Alpha Vantage look-ahead filtering, graph-router crash-safety, graph-shape-aware checkpoint resume, working crypto sentiment sources, a configurable LLM retry budget, Bedrock API-key auth, and Claude Sonnet 5 / Fable 5 support. [2026-06] TradingAgents v0. 0 released with a verified data-access contract, an expanded provider registry (NVIDIA, Kimi, Groq, Mistral, Bedrock, and any OpenAI-compatible endpoint), FRED and Polymarket data vendors, a current-generation model catalog, and a CI gate. [2026-05] TradingAgents v0.
5 etc. model coverage, Qwen/GLM/MiniMax dual-region support, TRADINGAGENTS_* env-var configurability with API-key auto-detection, remote Ollama support, non-US alpha benchmarks, and ticker path-traversal hardening. [2026-04] TradingAgents v0. 4 released with structured-output agents (Research Manager, Trader, Portfolio Manager), LangGraph checkpoint resume, persistent decision log, DeepSeek/Qwen/GLM/Azure provider support, Docker, and a Windows UTF-8 encoding fix. [2026-03] TradingAgents v0. 4 family models, unified model catalog, backtesting date fidelity, and proxy support. [2026-03] TradingAgents v0. 6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability. [2026-02] TradingAgents v0.
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.
What has been reported
It is not intended as financial, investment, or trading advice. Our framework decomposes complex trading tasks into specialized roles. Installation and CLI Installation Clone TradingAgents: git clone https://github. com/TauricResearch/TradingAgents. git cd TradingAgents Create a virtual environment in any of your favorite environment managers: conda create -n tradingagents python=3. 12 conda activate tradingagents Install the package and its dependencies: pip install. For any other OpenAI-compatible server (vLLM, LM Studio, llama. cpp, or a custom relay), use llm_provider: "openai_compatible" and set the endpoint via backend_url (or TRADINGAGENTS_LLM_BACKEND_URL), e. g. http://localhost:8000/v1 for vLLM or http://localhost:1234/v1 for LM Studio.
Alternatively, copy. env. example to. env and fill in your keys: cp. env. example. env CLI Usage Launch the interactive CLI: tradingagents # installed command python -m cli. main # alternative: run directly from source You will see a screen where you can select your desired tickers, analysis date, LLM provider, research depth, and more. Markets and tickers TradingAgents works with any market Yahoo Finance covers, using the exchange-suffixed ticker. TradingAgents Package Implementation Details We built TradingAgents with LangGraph to ensure flexibility and modularity.
What happens next
The framework supports multiple LLM providers: OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen (Alibaba DashScope, international and China endpoints), GLM (Zhipu), MiniMax (global + China), OpenRouter, Ollama for local models, and Azure OpenAI for enterprise. Python Usage To use TradingAgents inside your code, you can import the tradingagents module and initialize a TradingAgentsGraph() object. You can run main. py, here's also a quick example: from tradingagents. graph. trading_graph import TradingAgentsGraph from tradingagents. default_config import DEFAULT_CONFIG ta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG. copy()) # forward propagate _, decision = ta. propagate("NVDA", "2026-01-15") print(decision) You can also adjust the default configuration to set your own choice of LLMs, debate rounds, etc. from tradingagents. graph. trading_graph import TradingAgentsGraph from tradingagents. default_config import DEFAULT_CONFIG config = DEFAULT_CONFIG. copy() config["llm_provider"] = "openai" # e. g. openai, google, anthropic, deepseek, groq, ollama; openai_compatible covers any OpenAI-compatible endpoint (vLLM, LM Studio, llama. cpp,. . . ) config["deep_think_llm"] = "gpt-5.
6-luna" # Model for quick tasks config["max_debate_rounds"] = 2 ta = TradingAgentsGraph(debug=True, config=config) _, decision = ta. propagate("NVDA", "2026-01-15") print(decision) See tradingagents/default_config. py for all configuration options. Persistence and Recovery TradingAgents persists two kinds of state across runs. Each completed run appends its decision to ~/. tradingagents/memory/trading_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.
The report has been compiled by The Daily Waves using information reported across github.com, techcrunch.com. Details are presented according to the information available at the time of publication and may change as authorities, organisers or other relevant parties provide updates.