repowiserepowise

App

tauricresearch / tradingagents

TradingAgents: Multi-Agents LLM Financial Trading Framework

★ 122,698stars on GitHubPythonApache-2.0

This connects Repowise to tauricresearch/tradingagents's code. It does not install tradingagents.

Repowise maps public repos from their source. Not affiliated with tauricresearch. What is Repowise?

github.com/tauricresearch/tradingagentsIndexed at 9fa1196

What is tradingagents?

tradingagents is a multi-agent trading framework for research that uses LLM-powered agents to reach a trading decision on a stock. Its agents mirror a trading firm: analysts write reports, researchers debate them, and a trader and portfolio manager decide. It is not intended as financial, investment, or trading advice. The code is written in Python. To install it, run git clone https://github.com/tauricresearch/tradingagents.git and follow the steps below. Its code health is 8.5 out of 10 (Excellent), ranked #38 of 4,000+ indexed repos. The last commit to tradingagents was on Oct 27, 2026, and 24 people have contributed.

As of commit 9fa1196, indexed Nov 6, 2026. What it is comes from a model reading the README; the rest is measured from the source and git history, not from the maintainer.

For agentstradingagents.md

Repo facts: type, license, health, rank, contributors
tradingagents facts
TypeApp
LicenseApache-2.0
Code health8.5 / 10 (Excellent)
Health rank#38 of 4,000+ indexed repos
Last commitOct 27, 2026
Contributors24
Bus factor1
Size195 files, 21,847 lines

Install tradingagents

Commands copied from the README

  1. 1Clone the tradingagents repository.
    git clone https://github.com/tauricresearch/tradingagents.git
  2. 2Move into the tradingagents folder.
    cd tradingagents
  3. 3Install the package and its dependencies from the repository directory.
    pip install .

Full install notes on GitHub

Explore tradingagents

Ask about this code in your agent

This connects Repowise to tradingagents's code. It does not install tradingagents. To install tradingagents, use the install steps.

Useful if you want to change or fork tradingagents: your agent can ask how it is put together and get answers that cite its files.

How to use tradingagents

  1. 1Launch the interactive CLI.
    tradingagents # installed command

Ask about tradingagents

Answers come from tradingagents's README and source, with the files they cite. Two free answers a day without an account.

Want this for your own codebase? Map your repo free

About this page

Get a page like this for your own codebase

Repowise built this map of tauricresearch/tradingagents from its source and git history. It parses every symbol, draws the dependency graph, scores each file's health from complexity, duplication, coverage and churn, finds hotspots and owners in the history, and writes documentation for every module. Your coding agent reads the same index over MCP, so its answers cite real files.

Free for 2 public repos, with a page like this one. No card. See how Repowise works

Prefer local? pip install repowise && repowise init indexes your own checkout, no account needed. Star Repowise on GitHub

tauricresearch/tradingagents FAQ

What is tradingagents?

tradingagents is a multi-agent trading framework for research that uses LLM-powered agents to reach a trading decision on a stock. It is not intended as financial, investment, or trading advice.

How does tradingagents work?

tradingagents runs analyst agents for fundamentals, sentiment, news and technical data, then researchers debate their reports. A trader composes a proposal, and the risk team and portfolio manager approve or reject it.

How do I install tradingagents?

Run pip install . from the repository directory to install tradingagents and its dependencies. Then run tradingagents to start the interactive CLI. See the install steps

What language is tradingagents written in?

tradingagents is written in Python, and the repository also includes a Dockerfile for container runs.

How is the tradingagents code organized?

The cli directory holds the terminal tool, tradingagents/graph builds the LangGraph workflow, tradingagents/agents holds the analyst and state logic, and tradingagents/dataflows holds market-data helpers.

Who is tradingagents for?

tradingagents is for research, such as studying how a team of LLM agents weighs market evidence before a trading decision. Its authors state it is not trading advice.

What license does tradingagents use?

tradingagents uses the Apache-2.0 license.

Code health

8.5out of 10Excellent

Hotspots average 7.5, the place fixes pay off most.

On the leaderboards:#5 of 71 Python repos

Key features of tradingagents

  • Runs specialized LLM-powered agents for fundamental, sentiment, news and technical analysis.
  • Has researchers who debate bullish and bearish views before a trader composes a decision.
  • Includes a risk management team and a portfolio manager who approves or rejects each proposed trade.
  • Provides an interactive terminal CLI and a Python API, and can run without prompts for scheduled jobs.
  • Saves each run's reports, including a single-page HTML report that can be read in a browser.
  • Supports several LLM providers, including OpenAI, Google, Anthropic, and any OpenAI-compatible endpoint.

How tauricresearch/tradingagents works

Input enters as a ticker and a date, either through the interactive terminal tool in cli/main.py or by calling TradingAgentsGraph.propagate from tradingagents/graph/trading_graph.py. The tradingagents/graph package builds the LangGraph workflow that runs the analyst agents, then the research and risk debates, up to a portfolio decision. The tradingagents/agents directory writes the analyst reports a run starts from and holds the shared state and rating logic that later steps read. The tradingagents/dataflows package provides the helpers that market-data vendor calls rely on, such as settings, HTTP access and cache writes. Settings come from tradingagents/default_config.py, and the root main.py copies them before building the trading graph. A finished run is saved as a report tree, which includes complete_report.html.

The codebase has 195 files and 2,118 symbols in 4 modules, led by Python and Dockerfile. Code health is 8.5 out of 10, rated excellent.