AI Agent Hub
Back to plugins
🧰

dsh-tdx

Web Tools Updated 2026.08.18

Run the following command in DeepSeek Harness:

dsh plugin install guozede12593312/dsh-tdx

Paste the following prompt into your AI chat to install this plugin:

Run dsh plugin install guozede12593312/dsh-tdx in the DeepSeek Harness terminal to install; the source lives at https://github.com/guozede12593312/dsh-tdx and requires Python 3.6+ with pytdx pre-installed.

About this plugin

The core limitation DSH faces in investment analysis is the absence of a real-time market data source, forcing the model to rely on stale prices from training memory. The dsh-tdx plugin bridges this gap by connecting directly to Tongdaxin market servers via pytdx, enabling on-demand retrieval of authentic market data so analysis is grounded in facts rather than guesses.

It exposes four query tools: A-share historical K-line data (minute through monthly granularity), batch real-time quote snapshots, common technical indicators (MACD, RSI, MA, EMA), and concept sector constituent lookups. All indicators are computed locally in a pure-function layer from K-line data with zero external dependencies, making them easy to unit test in isolation.

Ideal for users who leverage DSH for A-share investment analysis and need genuine market data to back their judgments. A single pip install of pytdx is all that is required to upgrade the model from quoting from memory to querying data first, then analyzing.

Use Cases

  • Query multi-granularity A-share K-lines for trend analysis
  • Fetch batch real-time quotes for market snapshots
  • Compute and interpret MACD, RSI, and other technical indicators

Best For

  • Users leveraging DSH for A-share investment analysis
  • Analysts needing real market data to ground model reasoning
  • Researchers integrating Tongdaxin data into AI workflows