FareedKhan-dev/multi-agent-trading-system

Implementation of Deep Thinking Trading System

48
/ 100
Emerging

Orchestrates specialized LLM-powered agents (Analysts, Researchers, Traders, Risk Managers, Portfolio Manager) across departments using LangChain/LanGraph, with adversarial debate flows (Bull vs. Bear) and multi-perspective risk scrutiny to synthesize market intelligence into BUY/SELL/HOLD signals. Integrates live market data from Finnhub and Tavily web search, implements persistent long-term memory for agent learning, and uses LangSmith tracing for full observability of the multi-agent decision pipeline.

102 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 22 / 25

How are scores calculated?

Stars

102

Forks

50

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/FareedKhan-dev/multi-agent-trading-system"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.