# FinnewsHunter

An open-source, multi-agent financial-news analysis platform that monitors Chinese financial news sources in real time and uses LLM-based sentiment analysis and a knowledge graph to surface potential trading signals.

FinnewsHunter is a multi-agent financial intelligence platform built on the AgenticX framework. Agents such as a NewsAnalyst and a Researcher monitor multiple financial news sources in real time, including Sina Finance and Securities Times, and use large language models for sentiment analysis and market-impact interpretation, combined with a knowledge graph to look for investment opportunities and risks.

It integrates real market data through akshare for stock K-line analysis, supports batch selection, deletion and analysis of news items, and offers multi-provider LLM support across Bailian, OpenAI, DeepSeek, Kimi and Zhipu. Its stack is FastAPI, PostgreSQL, Milvus, Redis and React, deployed with Docker Compose, and it is written in Python under the Apache-2.0 license.

Website: https://github.com/DemonDamon/FinnewsHunter
