dsh-algovault
Run the following command in DeepSeek Harness:
dsh plugin install AlgoVaultLabs/dsh-algovault
Paste the following prompt into your AI chat to install this plugin:
Run dsh plugin install AlgoVaultLabs/dsh-algovault inside DeepSeek Harness to install the plugin, then restart the target profile to activate it; full source repository: https://github.com/AlgoVaultLabs/dsh-algovault
About this plugin
When building trading-focused agent workflows, models often receive a scatter of raw indicator values and have to assemble the buy-or-sell conclusion on their own. dsh-algovault mounts AlgoVault's decision engine directly into DeepSeek Harness as MCP tools, so the agent gets a structured verdict with confidence and market regime in a single call, removing the multi-step reasoning from scattered indicators to a trade decision.
The bundle ships eight namespaced tools covering single-asset trade calls, batch scans ranked by open interest, market regime detection (trending up, trending down, ranging, volatile), cross-venue funding-spread arbitrage rankings, historical win-rate and coverage statistics, plus knowledge retrieval and synthesized Q&A over the same data set. A bundled skill file further teaches the model which tool answers which question, reducing trial-and-error in tool selection.
The free tier is anonymous, requiring no signup and no API key. If you are using DeepSeek Harness to build quant trading assistants, arbitrage monitors, or research backtesting pipelines, especially around perpetual futures and delta-neutral carry strategies, this plugin lets you skip the indicator-assembly step and feed structured decisions straight into your model.
Use Cases
- Deliver structured buy/sell/hold verdicts with confidence for perp-futures agents
- Rank cross-venue funding spreads for delta-neutral carry strategies
- Detect market regime and attach a tailored strategy hint
Best For
- Developers building trading workflows on DeepSeek Harness
- Quant researchers focused on perpetual futures and funding arbitrage
- Agent engineers who prefer structured verdicts over raw indicator values
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.