@_zheergen: Wow! Tonghuashun official jumps in — A-share data service officially open-sourced, one API Key handles it all, fully supports AI Agent, quantitative trading, and development! Previously, for A-share quantitative trading, data sources were always a headache: web scraping feared being blocked, third-party data expensive, Tushare free quota insufficient. Now Tonghuashun itself has open-sourced the data…
Summary
Tonghuashun officially open-sources its A-share data service, providing comprehensive market data through a single API Key, with native support for MCP and Agent Skill, facilitating use by AI Agents and quantitative development.
View Cached Full Text
Cached at: 08/22/26, 09:25 AM
Wow! Tonghuashun Officially Steps In—A-Share Data Service Fully Open-Sourced, One API Key Handles Everything: Supports AI Agents, Quant, and Development!
Previously, when doing A-share quant, data sources were always a headache: web scraping risked blocks, third-party data was expensive, and Tushare’s free quota wasn’t enough.
Now, Tonghuashun has open-sourced its data service themselves—real-time quotes, financial statements, valuations, limit-up/down pools, Dragon & Tiger lists, call auctions—all market data accessible with a single Key.
Coverage is comprehensive:
- Real-time quotes, historical K-lines, financial statements, valuation snapshots
- Call auctions, limit-up/broken-limit, Dragon & Tiger lists, hot rankings, and other specialized data
- Indices, sectors, public fund information, and NAV
- Supports REST API, Python SDK, CLI, local DuckDB
- Key highlight: Native support for MCP + Agent Skills, enabling Claude/Cursor to query data directly via natural language
The most powerful feature is the AI Agent adaptation. A single command—npx skills add—installs the Skill, and then you can directly ask Claude, “Check the latest quote for Kweichow Moutai and analyze its moving average trends.” It automatically knows whether to call the API, MCP, or CLI.
The biggest pain point for A-share quant enthusiasts—data—has now been officially solved by the source itself. Bookmark this; you’ll thank me later.
@_zheergen: Quantitative Identification of Flag and Pennant Patterns: Which Is the True Continuation Pattern with Positive Expectations?
Yesterday, a follower asked me: For continuation patterns like flags and pennants, are there truly quantifiable and backtestable identification methods? Or is it all just subjective line-drawing?
I directly shared this ~14-minute video. Why?
Similar Articles
@BTCqzy1: Found an A-share open-source investment research tool — TradingAgents-Astock, deeply customized for A-shares, completely free data sources, direct connections to mootdx + East Money + Sina + Tencent Finance + Tonghuashun, no API Key required, with detailed data on dragon and tiger lists, lock-up expirations, and capital flows. ...
TradingAgents-Astock is an A-share specialized open-source investment research tool based on TradingAgents, built-in 7 Agent analysts, supporting free data sources and multiple large language models, with Web UI and CLI.
@AYi_AInotes: Wow, these two GitHub projects must be recommended together. People doing AI investment research can save months of effort. Someone turned the full free data of A-shares + US and Hong Kong stocks into an AI-native Skill. No need to integrate APIs, no need to handle anti-scraping, almost zero API keys. In Claude, Cursor, Codex…
Recommend two open-source GitHub projects that turn full free data of A-shares and US/Hong Kong stocks into AI-native Skills. You can call market data, research reports, etc. with one sentence in Claude, Cursor, Codex, greatly improving AI investment research efficiency.
@XAMTO_AI: Guys, there's something I just have to tell you about. An open-source AI quantitative trading platform has quietly launched. Locally self-deployable, full-chain connectivity, covering crypto, US stocks, and forex — from analysis to live trading all in one — can you believe it? Two years ago, such a thing was either ridiculously expensive or simply non-existent. Now it's directly open-sourced on G…
Introducing QuantDinger, an open-source AI quantitative trading platform that supports local deployment, full-chain connectivity for crypto, US stocks, and forex, integrating AI analysis, strategy generation, backtesting, and live trading integration.
@_zheergen: Guys! Found another all-in-one Python stock tool — InStock. The myhhub/stock repository covers A-share quantitative analysis quite comprehensively: data scraping, indicator calculation, stock selection, backtesting, and automated trading all in one. Let me highlight the core features: Real-time A-share data scraping + 30…
Introduces the open-source Python tool InStock (myhhub/stock) for A-share quantitative analysis, supporting data scraping, technical indicators, stock selection, backtesting, automated trading, etc., and can be deployed via Docker.
@Jolyne_AI: The most troublesome part of A-share data analysis is not writing strategies, but getting all the data first: market data, research reports, dragon and tiger list, northbound flows, capital flows, announcements, financial reports—each type has a different API and parameters often change. a-stock-data is an A-share full-stack data Skill for AI coding assistants, packaging 13 data sources…
a-stock-data is an A-share full-stack data Skill for AI coding assistants, packaging 13 data sources into directly callable tools, supporting multiple data layers such as market data, research reports, signals, and capital flows.