TradingAgents
by @TauricResearchCOMMUNITY· v0.7.1· Updated Nov 2, 2026
- 24Contributors
- Oct 27, 2026Last commit
- Apache-2.0License
- Suggestsonly
TradingAgents runs a desk of LLM analysts who debate a stock or major coin before a decision, as a second opinion before your Moby agent trades it.
About
TradingAgents models a trading firm with LLM agents. Analysts cover fundamentals, sentiment, news and technicals, bull and bear researchers argue the case, a trader proposes a decision and a risk team reviews it. It works on any ticker Yahoo Finance covers, including BTC-USD and ETH-USD.
What it adds to Moby. A structured debate on assets with long histories and news coverage: majors, and the stocks behind Moby's tokenized stocks.
How to pair it. Before your Moby agent buys a tokenized stock or a major, run TradingAgents on the underlying ticker and read the risk team's verdict. Your Moby agent and your Guardrails decide what executes.
What it does not do. It does not cover new Solana launches or read Moby's data, and it does not trade. Runs on the same ticker can differ, and the authors say it is for research, not advice.
A plain guide to the term, and to this project, is what an AI hedge fund is.
What's inside this repo
- Analyst team: fundamentals, sentiment, news and technical analysts run in parallel
- Bull and bear researchers debate the analysts' reports
- Trader agent turns the research into a decision with timing and size
- Risk team and a portfolio manager approve or reject, on a simulated exchange only
- CLI (tradingagents) with non-interactive --ticker and --date flags
- Any Yahoo Finance ticker, including BTC-USD and ETH-USD
- Backtests over a ticker and date grid; reports saved as one HTML page; decision log
- LLM providers: OpenAI, Google, Anthropic, xAI, DeepSeek, Qwen, GLM, Ollama and others
Install steps
Third-party code: Moby does not audit or control it. Read the source before you run it.
- Clone the repo:
git clone https://github.com/TauricResearch/TradingAgents - In the repo folder, on Python 3.11 or later:
pip install . - Set one LLM key, for example
export ANTHROPIC_API_KEY=..., as the README lists: https://github.com/TauricResearch/TradingAgents - Run
tradingagentsand give it a ticker, for exampleNVDA. - Ask:
Compare the TradingAgents verdict on NVDA with Moby's data on the tokenized NVDA before you buy.
Permissions
- Reads
- Market and news data sources it is configured with
- Writes
- Local reports
- Tools
- Python framework and CLI; needs an LLM API key
- Trade
- Suggests only
Review
Reviewed Nov 1, 2026. Source matches repo at commit c454491
Links
- Repository: https://github.com/TauricResearch/TradingAgents
On GitHub
- Stars
- 122,902
- Forks
- 23,565
How it works with Moby
TradingAgents works on its own. With Moby your agent can also trade on what it finds.
- Set up AI Trading
In the Moby app: create your agent and fund its Solana wallet.
Get the app - Connect Moby MCP
Whale, KOL and smart-money data, plus buy, sell, SL and TP from the agent wallet.
View Moby MCP - Install TradingAgents
Your agent runs it alongside Moby's onchain data and trades inside your Guardrails.
Install
Related
- APSchedulerAPScheduler is an open-source Python job scheduler, so your agent…
- CCXTCCXT is a unified library for crypto exchange market data, balances…
- CryptofeedCryptofeed is a Python websocket handler for live cryptocurrency…
- DuckDBDuckDB is an in-process analytical database for SQL over local and…
- Moby MCP connectorConnect any MCP-capable agent to Moby for live onchain research on…
- Moby KnowledgeThe /agents page and agents.md as your agent's Moby reference: how…
Reviewed Nov 1, 2026 · Report this item
