How vongchu/tradingagents_tauricresearch works
TradingAgents is a multi-agent financial research and trading-decision framework. A user submits an instrument and analysis settings through the CLI or package API; the graph coordinates data-backed analysts, bull/bear debate, a trader proposal, risk discussion, and a portfolio decision, which the CLI can display. Data-provider and LLM-client modules support these stages, and graph checkpointing is a separate state capability. Major workflow stages are based on the README and sampled agent code; unsampled graph wiring is represented only where the documented workflow supports it.
Main entry points: trading_graph.py Trading Graph · main.py CLI · analyst_execution.py Analyst Execution · analysts Analyst Team
Components 20
User Entry
- CLI
cli/main.py - Package API
tradingagents/graph/trading_graph.py
Workflow Orchestration
- Trading Graph
tradingagents/graph/trading_graph.py - Graph Setup
tradingagents/graph/setup.py - Analyst Execution
tradingagents/graph/analyst_execution.py - Checkpointing
tradingagents/graph/checkpointer.py
Research Agents
- Analyst Team
tradingagents/agents/analysts - Bull / Bear Debate
tradingagents/agents/researchers - Research Manager
tradingagents/agents/managers/research_manager.py
Decision Agents
- Trader
tradingagents/agents/trader/trader.py - Risk Debate
tradingagents/agents/risk_mgmt - Portfolio Manager
tradingagents/agents/managers/portfolio_manager.py - Report Output
tradingagents/reporting.py
Data And Models
- Agent Data Tools
tradingagents/agents/utils - Market Dataflows
tradingagents/dataflows - LLM Factory
tradingagents/llm_clients/factory.py - Provider Clients
tradingagents/llm_clients
Other components
- User
- Market Data Services
- LLM Providers
Connections 22
- User → CLI: configures analysis
- User → Package API: submits instrument
- CLI → Trading Graph: runs analysis
- Package API → Trading Graph: propagates analysis
- Trading Graph → Graph Setup: builds workflow
- Trading Graph → Analyst Execution: dispatches analysts
- Trading Graph → Checkpointing: persists state
- Analyst Execution → Analyst Team: runs analysis
- Analyst Team → Agent Data Tools: requests evidence
- Agent Data Tools → Market Dataflows: fetches data
- Market Dataflows → Market Data Services: queries providers
- Analyst Execution → Bull / Bear Debate: starts debate
- Bull / Bear Debate → Research Manager: provides debate
- Research Manager → Trader: provides investment plan
- Trader → Risk Debate: proposes trade
- Risk Debate → Portfolio Manager: provides risk debate
- Portfolio Manager → Trading Graph: returns decision
- Trading Graph → Report Output: produces report
- Trading Graph → LLM Factory: creates models
- LLM Factory → Provider Clients: selects provider client
- Provider Clients → LLM Providers: invokes model
- CLI → Report Output: displays results