Alpaca Multi-Agent Trading Workbench

What does this agent do, and when should you use it?

AlpacaTradingAgent is a LangGraph-based multi-agent trading framework for users who want to connect to Alpaca accounts for equities and crypto. Its components include five analysts, bullish and bearish researchers, a Trader, and risk and portfolio management roles; analysts can run in parallel across market, social sentiment, news, fundamental, and macro inputs. Use it as a Python package, through the CLI, or in a Dash web UI; Docker Compose is also documented for launching the UI. It supports Alpaca paper and live accounts, recurring analysis, and optional automatic execution. It requires Alpaca plus relevant data and model-provider credentials, and the repository says it is for education and research, not investment advice.

Provide a ticker or crypto symbol such as BTC/USD and an analysis date through the CLI, Web UI, or Python interface. TradingAgentsGraph.propagate uses the configuration to call market data, news, social sentiment, fundamental, and macro sources; five analysts can run in parallel, researchers debate the findings, and the Trader produces a BUY/HOLD/SELL or LONG/NEUTRAL/SHORT decision. With Alpaca credentials configured, the interface can show positions and orders, place trades, or liquidate positions; scheduled analysis and optional auto-execution are available. Completed decisions can be written to a Markdown memory log, and failed LangGraph runs can optionally resume from SQLite checkpoints.

1. A quantitative researcher wants several analyst roles to examine market, news, fundamental, and macro signals for a stock such as NVDA.
2. An Alpaca user wants to analyze a mixed portfolio of equities and crypto such as BTC/USD in a paper account.
3. A developer wants to call TradingAgentsGraph.propagate from a Python program and consume its decision output.
4. A trader wants a Dash interface for per-symbol progress, reports, charts, current positions, and recent orders.
5. A user who needs recurring market-hours analysis wants to schedule runs and choose whether recommendations may execute automatically.

How do you install or deploy this agent?

You need a Python environment and the relevant API credentials. The README identifies Alpaca for trading, Finnhub for stock news and data, FRED for macro analysis, and CoinDesk/CryptoCompare for crypto news. LLM choices include cloud providers and local OpenAI-compatible endpoints. Clone the project, install dependencies, and create the environment file:

git clone https://github.com/huygiatrng/AlpacaTradingAgent.git
cd AlpacaTradingAgent
pip install -r requirements.txt
cp env.sample .env

Fill in the required keys in .env; set ALPACA_USE_PAPER=True for paper trading. Without valid Alpaca keys, the app falls back to demo mode without trading capabilities. To build and launch the Web UI with Docker Compose after configuring .env:

docker compose up -d --build

How do you use this agent?

Start the CLI:

python -m cli.main

Start the Dash Web UI:

python run_webui_dash.py

The CLI prompts for assets and supports provider, model, and provider-specific settings. A first Python call looks like this:

from tradingagents.graph.trading_graph import TradingAgentsGraph
from tradingagents.default_config import DEFAULT_CONFIG

ta = TradingAgentsGraph(debug=True, config=DEFAULT_CONFIG.copy())
_, decision = ta.propagate("NVDA", "2024-05-10")
print(decision)

Use the BTC/USD format for crypto. Configure Alpaca credentials and the account mode before trading in either a paper or live account; automatic execution is optional.

What are this agent's strengths and limitations?

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

How does FollowAgents rate this agent?

FAQ