# simonlin1212/TradingAgents-astock

A股多Agent投研框架 — 适配A股数据源(龙虎榜/游资/解禁等)，7位分析师基于A股规则的辩论决策，基于TradingAgents深度改造，适配大A。A-share multi-agent investment research framework — 7 AI analysts, bull/bear debate, risk assessment。

Repository: https://github.com/simonlin1212/TradingAgents-astock
Canonical: https://ross.abutalabs.com/products/tradingagents-astock
Homepage: https://arxiv.org/pdf/2412.20138
Language: Python
License: Apache-2.0
License Family: permissive
Topics: a-share, ai-agent, china-stocks, claude, fintech, investment-research, langgraph, llm, multi-agent, python, quantitative-finance, trading-agents
Last push: 2026-08-19T07:50:50+00:00

## Health v2 (maintenance only)
Score: 80/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 98, longevity 8
- inputs: {"age_days": 113, "days_push": 14, "days_rel": 14, "gap_med": 2, "n_releases_24m": 22}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3080, forks 799 (observed 2026-08-28T04:07:41.852392+00:00)

## What it is
A Python multi-agent investment research framework for China's A-share market, deeply forked from TauricResearch/TradingAgents. It runs 7 specialized AI analysts (market, sentiment, news, fundamentals, policy, hot-money, lockup) with bull/bear debate and risk assessment, using free A-share data sources and A-share trading rules.

## Use cases
- generate AI investment research reports for A-share stocks
- run multi-agent bull vs bear debate on Chinese stocks
- analyze A-share data like dragon-tiger list and lockup expirations
- reproduce the TradingAgents paper on China market data
- backtest analyst decisions against CSI 300 benchmark
- research tool for teaching LLM-based financial analysis

## When to choose
- you need A-share-specific analysis with T+1, price-limit, and lot-size rules
- you want free direct-connect Chinese market data sources
- you want a multi-agent LLM debate pipeline for stock research
- you need Chinese-language research reports

## When to avoid
- you need US or other non-China market analysis
- you want production trading signals or actual investment advice
- you need a lightweight single-agent stock screener
- you require guaranteed real-time low-latency market data

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, rag, data-science, trading
- domain: artificial-intelligence, large-language-models, fintech, data-science
- platform: python, cross-platform, cli
- tags: a-share, china-stocks, multi-agent, langgraph, investment-research, bull-bear-debate, trading-agents, fintech, ai-agents, quantitative-finance

## Member repositories
- simonlin1212/TradingAgents-astock (main) score 80

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:41.852392+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 2026-08-29T18:46:31.921069+00:00, confidence not recorded.
  - readme: https://github.com/simonlin1212/TradingAgents-astock (fetched 2026-08-28T04:07:41.852392+00:00, sha acdd52b6ba97)
- Data as of 2026-08-30T08:39:29.467469+00:00.