Run multi-agent LLM financial trading analysis
News. Task: News [2026-10] TradingAgents v0.7.1 released with decisions scored only on final closes and settled across long market holidays, a fix for model dates that could read filings made after the run date, and fixes to portfolios, prices, SEC statements and reports. [2026-10] TradingAgents v0.7.0 released with runs on your own ChatGPT Plus or Pro plan, backtests scored from the first close after each decision, a note at start-up when a newer release is out, and a wheel attached to each GitHub release. [2026-10] TradingAgents v0.6.0 released with reports saved as one HTML page, a provider per model tier so the managers and analysts can run on different models, past decisions settled for every ticker while the analysts work, and company news read from Yahoo search while Yahoo's news feed is down. Full release notes are in CHANGELOG.md. [2026-09] TradingAgents v0.5.2 released with parallel analysts for a faster analysis, a CLI that runs without prompts from flags such as --ticker and --date, the run's settings recorded in every report, and backtests that see only data published by each analysis date. [2026-09] TradingAgents v0.5.1 released with a package layout organised by what each module holds (import paths moved), optional Jev screening of social posts, GPT-6 Sol and Luna as the default models, and fixes to run isolation and SEC EDGAR statements. [2026-09] TradingAgents v0.5.0 released with point-in-time integrity across every dated path, SEC EDGAR fundamentals served as filed, backtesting over a ticker and date grid, portfolio-aware runs, and current model lineups across every provider. [2026-08] TradingAgents v0.4.0 released with look-ahead / point-in-time fixes across FRED macro, social sentiment, and the decision-log memory; clearer decision signals; working CLI checkpoint resume; Trader price grounding; and the GPT-5.6 and GLM-5.3 models. [2026-07] TradingAgents v0.3.1 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 v0.3.0 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 v0.2.5 released with the grounded Sentiment Analyst, GPT-5.5 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 v0.2.4 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 v0.2.3 released with multi-language support, GPT-5.4 family models, unified model catalog, backtesting date fidelity, and proxy support. [2026-03] TradingAgents v0.2.2 released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability. [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. [2026-01] Trading-R1 Technical Report released, with Terminal expected to land soon. π TradingAgents | β‘ Installation & CLI | π¬ Demo | π¦ Package Usage | π€ Contributing | π Citation π 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. So we decided to fully open-source the framework. Looking forward to building impactful projects with you! TradingAgents Framework TradingAgents 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.; tools: custom-built or unnamed agent. Human role: The original post does not say how a person stayed involved.; limitations: Prerequisites include Python 3.11+, valid API keys for LLM providers (e.g., OpenAI, Anthropic), and data sources like Yahoo Finance or SEC EDGAR. The framework is designed for research purposes only and is not financial advice. Integration uncertainty exists regarding data latency and model non-determinism; two runs of the same ticker and date may yield different results..
Tools
custom-built or unnamed agent
Published on Agent Work Atlas:
Overview
News
Workflow
News [2026-10] TradingAgents v0.7.1 released with decisions scored only on final closes and settled across long market holidays, a fix for model dates that could read filings made after the run date, and fixes to portfolios, prices, SEC statements and reports. [2026-10] TradingAgents v0.7.0 released with runs on your own ChatGPT Plus or Pro plan, backtests scored from the first close after each decision, a note at start-up when a newer release is out, and a wheel attached to each GitHub release. [2026-10] TradingAgents v0.6.0 released with reports saved as one HTML page, a provider per model tier so the managers and analysts can run on different models, past decisions settled for every ticker while the analysts work, and company news read from Yahoo search while Yahoo's news feed is down. Full release notes are in CHANGELOG.md. [2026-09] TradingAgents v0.5.2 released with parallel analysts for a faster analysis, a CLI that runs without prompts from flags such as --ticker and --date, the run's settings recorded in every report, and backtests that see only data published by each analysis date. [2026-09] TradingAgents v0.5.1 released with a package layout organised by what each module holds (import paths moved), optional Jev screening of social posts, GPT-6 Sol and Luna as the default models, and fixes to run isolation and SEC EDGAR statements. [2026-09] TradingAgents v0.5.0 released with point-in-time integrity across every dated path, SEC EDGAR fundamentals served as filed, backtesting over a ticker and date grid, portfolio-aware runs, and current model lineups across every provider. [2026-08] TradingAgents v0.4.0 released with look-ahead / point-in-time fixes across FRED macro, social sentiment, and the decision-log memory; clearer decision signals; working CLI checkpoint resume; Trader price grounding; and the GPT-5.6 and GLM-5.3 models. [2026-07] TradingAgents v0.3.1 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 v0.3.0 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 v0.2.5 released with the grounded Sentiment Analyst, GPT-5.5 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 v0.2.4 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 v0.2.3 released with multi-language support, GPT-5.4 family models, unified model catalog, backtesting date fidelity, and proxy support. [2026-03] TradingAgents v0.2.2 released with GPT-5.4/Gemini 3.1/Claude 4.6 model coverage, five-tier rating scale, OpenAI Responses API, Anthropic effort control, and cross-platform stability. [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. [2026-01] Trading-R1 Technical Report released, with Terminal expected to land soon. π TradingAgents | β‘ Installation & CLI | π¬ Demo | π¦ Package Usage | π€ Contributing | π Citation π 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. So we decided to fully open-source the framework. Looking forward to building impactful projects with you! TradingAgents Framework TradingAgents 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.
Reported result
The source does not report measured business outcomes or financial returns. It explicitly states that trading performance varies based on model choice, data quality, and non-deterministic factors. A measurable acceptance check would be to run a backtest over a specific date grid and verify that the system generates a complete HTML report with settled decisions, ensuring no look-ahead bias in the data.
Human role
The original post does not say how a person stayed involved.
Limitations
Prerequisites include Python 3.11+, valid API keys for LLM providers (e.g., OpenAI, Anthropic), and data sources like Yahoo Finance or SEC EDGAR. The framework is designed for research purposes only and is not financial advice. Integration uncertainty exists regarding data latency and model non-determinism; two runs of the same ticker and date may yield different results.
Try it
I want to set up a dry run of the TradingAgents framework for research purposes. First, clone the repository from https://github.com/TauricResearch/TradingAgents and install dependencies using `pip install .`. Configure the environment variables in `.env` with my [replaceable: API keys for OpenAI/Anthropic] and set `TRADINGAGENTS_LLM_PROVIDER` to [replaceable: provider name]. Run a single analysis for ticker [replaceable: e.g., NVDA] on date [replaceable: e.g., 2026-09-01] using the CLI command `tradingagents --ticker [replaceable: ticker] --date [replaceable: date] --save`. Ensure the output is saved as an HTML report. Do not execute any real trades; this is a simulated environment. After the run, review the `complete_report.html` to verify that the agents (Fundamentals, Sentiment, News, Technical) provided inputs and the Portfolio Manager made a decision. If the report is incomplete or errors occur, check the logs for API key issues or data access failures. I will manually confirm the report's quality before proceeding to any further steps.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.