666ghj/BettaFish
微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。
Implements a multi-agent architecture with specialized agents (Query, Media, Insight, Report) that collaborate through a "forum" debate mechanism with a moderator LLM, enabling iterative refinement across 30+ social media platforms and structured data synthesis. Built on pure Python with modular design, it integrates web search APIs, multimodal content analysis (video/image extraction), and private database querying into a unified pipeline that outputs interactive HTML reports generated through intermediate representation templates.
39,455 stars. Actively maintained with 14 commits in the last 30 days.
Stars
39,455
Forks
7,361
Language
Python
License
GPL-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
14
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/666ghj/BettaFish"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
hrwhisper/twitterDataMining
Twitter数据挖掘及其可视化
HUANGZHIHAO1994/weibo-analysis-and-visualization
使用python抓取微博数据并对微博文本分析和可视化，LDA（树图）、关系图、词云、时间趋势（折线图）、热度地图、词典情感分析（饼图和3D柱状图）、词向量神经网络情感分析、tfidf聚类、词向量...
vspiewak/twitter-sentiment-analysis
Streaming tweets with spark, language detection & sentiment analysis, dashboard with Kibana
r05323028/eyes
Public Opinion Mining System of Taiwanese Forums
bonzanini/Book-SocialMediaMiningPython
Companion code for the book "Mastering Social Media Mining with Python"