# TauricResearch/TradingAgents

TradingAgents: Multi-Agents LLM Financial Trading Framework

Repository: https://github.com/TauricResearch/TradingAgents
Canonical: https://ross.abutalabs.com/products/tradingagents
Homepage: https://arxiv.org/pdf/2412.20138
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, finance, llm, multiagent, trading
Last push: 2026-07-18T15:55:05+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 92, longevity 43
- inputs: {"age_days": 613, "days_push": 46, "days_rel": 59, "gap_med": 15, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 100743, forks 19417 (observed 2026-08-28T04:12:23.667566+00:00)

## What it is
TradingAgents is a Python framework that orchestrates multiple LLM-powered agents to analyze financial markets and make trading decisions. It models a trading firm with analyst, researcher, and trader roles that collaborate to evaluate stocks and produce trading signals.

## Use cases
- simulate a team of AI analysts to research stocks before trading
- build multi-agent LLM pipelines for financial decision-making
- get AI-generated trading signals based on news and fundamentals
- backtest LLM-driven trading strategies on historical data
- analyze market sentiment with multiple cooperating agents
- experiment with agent roles like bull/bear researchers for stock debates

## When to choose
- you want a ready-made multi-agent architecture specialized for trading research
- you're experimenting with LLM agents in finance and want a research-backed framework
- you need pluggable LLM providers and data vendors for market analysis

## When to avoid
- you need a production algorithmic trading system with real order execution and low latency
- you want guaranteed profitable trading - outputs are LLM opinions, not financial advice
- you need a lightweight single-agent assistant rather than a multi-agent pipeline

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, trading, data-science
- domain: fintech, artificial-intelligence, large-language-models
- platform: python, cross-platform
- tags: multi-agent, llm-agents, financial-trading, stock-analysis, market-sentiment, ai-agents

## Member repositories
- TauricResearch/TradingAgents (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:23.667566+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:12:29.310475+00:00, confidence not recorded.
  - readme: https://github.com/TauricResearch/TradingAgents (fetched 2026-08-28T04:12:23.667566+00:00, sha 60aa8bec283c)
- Data as of 2026-08-30T08:39:29.467469+00:00.