dsh-quant
Run the following command in DeepSeek Harness:
dsh plugin install pengpengyi92/dsh-quant
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness using the source repository https://github.com/pengpengyi92/dsh-quant.
About this plugin
dsh-quant addresses the problem of fragmented quant research tools by bringing data, alpha, machine learning, risk, execution, and ecosystem metrics together as 59 quant_* tools. With its PDAT→PET pipeline, it helps users move from raw market observations to strategy metrics, risk checks, fund simulation, and reporting in one coherent research flow.
The plugin is deliberately AI-native and plugin-oriented. Its tools produce canonical JSON, use equal-length null alignment, and are designed as concurrency-safe pure functions, making them easier for agents to call and compose. Built in TypeScript with zero runtime dependencies, it provides offline-verifiable numerical methods for indicators, backtests, options, bonds, drawdowns, risk, and related calculations inside the DSH runtime.
It is best suited for quant researchers, developers, and plugin authors who want to experiment with strategies inside an AI workflow or extend the framework with their own data sources, models, risk rules, or execution logic. It is especially useful for those who need a composable, agent-friendly quant toolkit rather than a single standalone backtest script.
Screenshots
Use Cases
- Run a research pipeline covering data, indicators, backtests, and risk summaries.
- Evaluate factor effectiveness, layered performance, and drawdown risk.
- Let agents call structured tools for quant analysis and fund simulation.
Best For
- Developers who want to research and backtest quant strategies.
- Researchers who need quant tools inside AI workflows.
- Plugin authors extending data, models, or execution modules in the DSH ecosystem.
Related Plugins
ModLens is a vision plugin for DeepSeek Harness that gives text-only models sight by reading images pasted directly into chat, with zero-config setup and multiple vision engines.
On-demand vision for text-only DeepSeek Harness agents: built-in free keyless vision chain and 14 vision tools, routing image turns as tool calls to vision models with pixel fidelity, no Python needed, one-command install.
Give text-only models in DeepSeek Harness eyes, enabling image Q&A, long-screenshot OCR, UI restoration, and GUI visual tasks.
An armor-breaking plugin for DeepSeek: rewrites instruction priority, expands refusal-blocked phrases, persists across sessions, and shows a green active indicator.