# 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。

Repository: https://github.com/666ghj/BettaFish
Canonical: https://ross.abutalabs.com/products/bettafish
Homepage: https://deepwiki.com/666ghj/BettaFish
Language: Python
License: GPL-2.0
License Family: copyleft
Topics: agent-framework, data-analysis, multi-agent-system, nlp, public-opinion-analysis, python3, sentiment-analysis, llms, deep-research, deep-search
Last push: 2026-08-25T16:01:57+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 62, longevity 56
- inputs: {"age_days": 793, "days_push": 8, "days_rel": 253, "gap_med": 13, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 42090, forks 7622 (observed 2026-08-28T04:12:08.745273+00:00)

## What it is
BettaFish (微舆) is a from-scratch multi-agent public opinion analysis system in Python that monitors 30+ social media platforms, analyzes millions of comments, and generates in-depth research reports. It combines five specialized agents, a crawler cluster, sentiment analysis models, and a debate-style 'forum' collaboration mechanism, all driven by conversational user queries.

## Use cases
- analyze public opinion about a brand or event on social media
- monitor mentions of a topic across weibo, xiaohongshu, douyin and other platforms
- generate a sentiment analysis report from millions of user comments
- break out of information bubbles by aggregating diverse public viewpoints
- predict future trends of a public opinion event
- crawl and analyze short video content for sentiment
- chat-style deep research on trending topics

## When to choose
- you need automated, multi-platform social media opinion monitoring and reporting
- you want a self-hosted multi-agent analysis pipeline without depending on agent frameworks
- you need multimodal analysis including short videos and structured info cards
- you want agent debate mechanisms to reduce single-model bias

## When to avoid
- you need a lightweight library to embed in your own app rather than a full application
- you require platforms or languages outside Python
- you need real-time sub-second analytics rather than report-style analysis
- strict licensing requirements conflict with GPL-2.0

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, nlp, web-scraping, data-science, chat-interface, web-framework, machine-learning
- domain: artificial-intelligence, data-science, social-media, analytics, web-development
- platform: python, self-hosted, cross-platform
- tags: public-opinion-analysis, sentiment-analysis, multi-agent-system, deep-research, social-media-monitoring, report-generation, crawler, llm, ai-agents, natural-language-processing, docker, web-server

## Member repositories
- 666ghj/BettaFish (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:08.745273+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:22:47.022482+00:00, confidence not recorded.
  - readme: https://github.com/666ghj/BettaFish (fetched 2026-08-28T04:12:08.745273+00:00, sha 09bf5f8f7676)
  - homepage: https://deepwiki.com/666ghj/BettaFish (fetched 2026-08-29T07:46:17.353692+00:00, sha a0117226c655)
  - site_page: https://deepwiki.com/666ghj/BettaFish/2-getting-started (fetched 2026-08-29T07:46:17.356760+00:00, sha 6ee2b235d476)
  - site_page: https://deepwiki.com/666ghj/BettaFish/2.1-installation (fetched 2026-08-29T07:46:17.358725+00:00, sha 305e41f3850b)
- Data as of 2026-08-30T08:39:29.467469+00:00.