#44th of 20 in Agent frameworks and SDKs
tradingagents
LangGraph multi-agent framework simulating a trading firm to analyze tickers
- Stars
- 111.2k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
40,944 on 25 Mar 2026111,212 on 14 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
TradingAgents runs a team of LLM agents (fundamentals, sentiment, news and technical analysts, bull and bear researchers, trader, risk team, portfolio manager) that debate and produce a trading decision for a ticker and date. It is built on LangGraph, with a CLI and a Python API, and works with many hosted providers plus Ollama and OpenAI-compatible servers. The README states it is for research, not financial advice.
Who it is for: Researchers and developers experimenting with LLM agents for market analysis
Strengths
- Many LLM providers, plus Ollama and any OpenAI-compatible endpoint such as vLLM or llama.cpp
- Quick and deep model tiers, each configurable with its own provider
- Point-in-time data for backtests, with SEC EDGAR statements as originally filed
- Interactive CLI, flag-driven non-interactive runs, and a Python API
Weaknesses
- Approved orders go only to a simulated exchange; no live broker execution described
- Results vary with model, temperature and data quality; README says research use only
- Past-dated runs withhold Yahoo fundamentals and insider trades for non-SEC companies
- Needs a provider API key; import paths changed in v0.5.1
What it needs
- GPU optional
- Docker + Compose
- Needs Python 3.11+, LangGraph, LLM provider API key or Ollama, Yahoo Finance, SEC EDGAR, Alpha Vantage (optional), FRED (optional)
- Models: OpenAI, Anthropic, Google Gemini, xAI, DeepSeek
Head to head
Also in Agent frameworks and SDKs
See all 20| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 90 out of 100 |
| 2 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| 3 | browser-usePython library that lets an LLM agent control a web browser | 88 out of 100 |
| #5 | crewaiPython framework for multi-agent workflows with role-based Crews and event-driven Flows | 80 out of 100 |
| #6 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 78 out of 100 |