flash131307/multi-agent-investment
Multi-agent equity research system with deterministic signal fusion — 3 specialized agents (ReAct, FinBERT, Plan-and-Solve + RAG) produce BUY/NEUTRAL/SELL decisions through a mathematical Decision Hub. No LLM in the critical path.
Orchestrates three specialized agents (technical ReAct, FinBERT sentiment, fundamental Plan-and-Solve+RAG) in parallel with independent timeouts, then fuses their signals through a deterministic three-stage Decision Hub that applies consistency scoring, dynamic regime-aware weighting, and aggregation—all mathematical, never LLM-dependent. Gracefully degrades to 2-agent or 1-agent mode with calibrated confidence penalties; built on FastAPI with FinBERT local inference (~0.3s), hybrid RAG over SEC filings (0.82 recall@5), and sub-3s median latency across 294 unit/integration/E2E tests.
183 stars.
Stars
183
Forks
20
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/flash131307/multi-agent-investment"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ZhuLinsen/daily_stock_analysis
LLM驱动的 A/H/美股智能分析器，多数据源行情 + 实时新闻 + Gemini 决策仪表盘 + 多渠道推送，零成本，纯白嫖，定时运行
derisk-ai/OpenDerisk
AI-Native Risk Intelligence Systems, OpenDeRisk——Your application system risk intelligent...
johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction
AI Bank Statement Document Automation By LLM model and Personal Finanical Analysis
FaustoS88/Pydantic-AI-Pinescript-Expert
PineScript Expert: A Retrieval-Augmented Generation (RAG) agent using Pydantic AI that provides...
RUC-NLPIR/FinSight
FinSight: Towards Real-World Financial Deep Research. 🎯One ticker, one click, one...