TauricResearch/TradingAgents
TradingAgents is an open-source LangGraph reference for role-based agent debates, durable memory, checkpoint recovery, and provider portability, with trading as its test domain.
TradingAgents splits market analysis across specialist analysts, opposing researchers, a trader, risk managers, and a portfolio manager. **v0.3.1** adds crash-safety, safer checkpoint recovery, retry controls, and data-correctness fixes.
Treat it as a concrete multi-agent harness study: compare its **structured roles**, debate limits, persistent decision log, and **per-node checkpointing** with your own agent workflows. Its provider registry also supports hosted, local, and OpenAI-compatible endpoints.
TradingAgents splits market analysis across specialist analysts, opposing researchers, a trader, risk managers, and a portfolio manager. **v0.3.1** adds crash-safety, safer checkpoint recovery, retry controls, and data-correctness fixes. Treat it as a concrete multi-agent harness study: compare its **structured roles**, debate limits, persistent decision log, and **per-node checkpointing** with your own agent workflows. Its provider registry also supports hosted, local, and OpenAI-compatible endpoints. This is a research scaffold, not a reproducible trading strategy. Model sampling and changing live sources can alter repeated runs, while historical dates do not freeze news or social inputs.
TradingAgents makes specialist roles, bounded debate, persistent decisions, and node-level recovery concrete in a volatile data workflow. Its crash-safety improvements strengthen it as a harness study, not as trading evidence. Prior experience with incoherent specialist chains narrows the lesson: role separation is useful only when handoffs preserve end-to-end context, and checkpoints cannot make changing inputs reproducible.