dsh-quant
AI-native DeepSeek Harness quant toolkit with market data, indicators, backtests, risk analysis, and research-pipeline tools.
Install
No clear install command was found in the current repository evidence.
Plugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Registers 46 quant tools through a Cordis/DeepSeek Harness package.
- Fetches market candles from Binance, OKX, Bybit, Sina, Tencent, and Yahoo providers.
- Calculates technical indicators, series statistics, volatility, factors, and data-quality signals.
- Runs built-in backtests, portfolio rebalancing, grid search, walk-forward evaluation, and linear models.
- Provides risk metrics, VaR backtesting, drawdown analysis, option and bond calculations, and fund simulation.
- Generates research reports and structured chart data, including a one-call `quant_research_pipeline`.
- Includes a zero-dependency Node CLI for browsing tools, research archives, and market data.
Useful For
- Run an agent-driven crypto or market research workflow from candle retrieval through reporting.
- Evaluate technical indicators, factor signals, and basic quantitative strategies.
- Analyze portfolio performance, drawdowns, risk metrics, options, bonds, and simulated fund fees.
- Discover data-source guidance and inspect public GitHub/npm ecosystem metrics.
Who It Fits
- DeepSeek Harness users building quantitative-research workflows.
- Agents and developers needing composable quant-analysis tools in a Node/Cordis environment.
- Researchers prototyping indicator, factor, backtest, and paper-execution workflows.
Documented Limitations
- Market coverage is described as crypto-first; Binance, OKX, and Bybit use public APIs, while A-share access is currently guided through a channel knowledge base.
- Built-in backtests cover specified strategy families; custom strategy callbacks are listed as future work.
- Execution simulation does not provide live trading.
- Live market tools require network access; offline indicator and backtest cases do not.
- Tool-result presentation uses generic UI cards because `presentCall` and `presentResult` are not customized.
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 0 runtime, 8 development, 3 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as MIT.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- pengpengyi92/dsh-quant
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- bda075c · 2026-08-19
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 14GitHub stars
- Forks
- 2
- Open issues
- 14
- Last commit
- 2026-08-19
- Last release
- 2026-08-19
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
A DeepSeek Harness notification plugin with model-facing tools, automatic session-event alerts, and multi-channel delivery.
View plugin →DeepSeek Harness bundle that adds HoloGram’s local code-dependency graph engine, MCP analysis tools, and 3D graph UI.
View plugin →DeepSeek Harness plugin that bridges a local-shell-mcp service into DSH with shell, file, browser, remote-worker, and Live Workspace tools.
View plugin →Governance-powered AI-agent task execution framework with a DeepSeek Harness plugin integration.
View plugin →