Native DeepSeek Harness plugin: 59 quant_* tools (data, alpha, ML, risk, execution, ecosystem) in one install — pure functions, zero runtime deps, no live trading.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-06
License
MIT
01What can it help you accomplish?
Run an end-to-end quant research pipeline (PDAT→PET) from a single tool call
One structured result with candles, data quality, stats, metrics, risk, drawdown, fund, factor evaluation and a Markdown report
Quants and AI agents operating inside DeepSeek Harness who want a full research flow without wiring modules by hand
Compute indicators, backtests and risk metrics for strategies
Canonical JSON for SMA/EMA/RSI/MACD/Bollinger plus dual-MA & Bollinger/RSI backtests and VaR/CVaR/Beta/Alpha/IR risk metrics
Quant researchers and agents needing reproducible, offline-verifiable numeric methods
Fetch multi-exchange market data for analysis
OHLCV candles from Binance / OKX / Bybit / Sina / Tencent / Yahoo with automatic fallback, no credentials
Agents and quants who need crypto / equity market series inside the harness
02How to install into DeepSeek Harness
Prerequisites
- DeepSeek Harness (dsh) installed and running — the README's install path is titled "Quick Install (dsh users)", so a running dsh runtime is assumed
Installation steps
- 01
$ npm i dsh-quant
- 02
Add one line to your cordis.yml: `- name: 'dsh-quant'`
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Native dsh plugin: runs in the harness's Node runtime and registers 59 tools via cordis.yml (Loader-managed, reversible / HMR-safe)
One-call research pipeline
symbol / interval / limit / provider (or candles + strategy/fund params)→candles, quality, stats, metrics, risk, drawdown, fund, factor, report, charts
Indicators & technical analysis (59 quant_* tools)
number[] series / OHLC arrays→canonical JSON indicators (SMA / EMA / RSI / MACD / Bollinger / ATR / KDJ / Williams %R / CCI / OBV / ADX / ROC)
Backtesting & portfolio risk
close series / returns / weights / orders→totalReturnPct, maxDrawdownPct, sharpe, VaR / CVaR / Beta / Alpha / IR, drawdown episodes, trade fills
Market data fetch (multi-exchange)
symbol, interval, limit, provider→OHLCV candles with automatic fallback across Binance / OKX / Bybit / Sina / Tencent / Yahoo
04Who is it for? When not to use it?
Good for
- Quants and AI agents operating inside DeepSeek Harness who want a full research flow without wiring modules by hand
- Quant researchers and agents needing reproducible, offline-verifiable numeric methods
- Agents and quants who need crypto / equity market series inside the harness
Not for
- Market coverage is crypto-first: Binance / OKX / Bybit public APIs with automatic fallback and no credentials; A-shares only go through the channel knowledge base (akshare et al. as future providers).
- Backtests are a built-in strategy family only (dual-MA / Bollinger breakout / RSI reversion / portfolio rebalancing / grid search); custom strategy callbacks are a future route, not shipped.
- Execution is simulation only — the delivery (PET) module is chart data plane, fund sim and research report; there is no live-trading engineering.
05Compatibility, maintenance and safety notes
- Market coverage is crypto-first: Binance / OKX / Bybit public APIs with automatic fallback and no credentials; A-shares only go through the channel knowledge base (akshare et al. as future providers).
- Backtests are a built-in strategy family only (dual-MA / Bollinger breakout / RSI reversion / portfolio rebalancing / grid search); custom strategy callbacks are a future route, not shipped.
- Market tools need network — live cases live in verify.ts; offline indicator and backtest cases are unaffected.
- Execution is simulation only — the delivery (PET) module is chart data plane, fund sim and research report; there is no live-trading engineering.
readme_verified
06Frequently asked questions
How do I install dsh-quant in DeepSeek Harness?
Run `npm i dsh-quant`, then add `- name: 'dsh-quant'` to your cordis.yml. The Loader resolves the package and 59 tools auto-register — indicators, backtests, factors, risk, fund simulation and ecosystem metrics out of the box.
Is dsh-quant a native dsh plugin or an MCP server?
It is a native dsh plugin: it runs inside the harness's Node runtime, in the same process as the agent, composable by the Loader, with reversible (HMR-safe) registration — not an external MCP server.
Can I run a full research pipeline in one call?
Yes. `quant_research_pipeline(symbol=BTCUSDT, limit=120)` returns everything in one call — candles, data quality, stats, metrics, risk, drawdown, fund, factor evaluation and a Markdown report.
Does dsh-quant support live trading?
No. The execution (PET) module is a simulation framework — chart data plane, fund sim and research report only. There is no live-trading engineering; data and conclusions stay internal.
What market data is covered?
Coverage is crypto-first via Binance / OKX / Bybit public APIs with automatic fallback and no credentials. A-shares go through the channel knowledge base (akshare et al.) as future providers.
07Related DSH workflows
weknora
by tencent
Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.
honcho
by plastic-labs
Memory library for building stateful agents
webnovel-writer
by lingfengqaq
A long-form Chinese web-novel writing assistant for Claude Code and DeepSeek Harness, designed to reduce memory loss and hallucinations in serialized projects of up to 2 million characters.
mirage
by strukto-ai
The World's First Virtual Terminal for AI Agents
08Data and sources
- dsh-quant is a **dsh plugin** running inside the harness's Node runtime: same process as the agent, composable by th…
59 tools auto-register — indicators / backtests / factors / risk / fund simulation / ecosystem metrics out of the box.
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-06. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.