DeepSeek Harness Plugins · Client
Plugins that extend DeepSeek Harness (DSH) with vision, workflows, memory, web tools and more.
A Windows tray launcher for DeepSeek Harness, enabling windowless startup, system tray residency, and complete exit with one click, supporting multi-icon switching and auto-start.
dsh-session-nav is a piano-key style in-session navigation bar for DeepSeek Harness Web GUI, enabling quick navigation and preview of multi-turn conversations.
dsh-envsel is a session environment selector for DeepSeek Harness that configures and manages runtimes for Python, R, and CLI tools with persistent selections applied in shell calls.
DSH native plugin for real-time monitoring of token consumption and costs with peak-valley pricing, displayed in a floating window.
Extends the workspace list to a three-level tree structure with manual grouping, drag-and-drop sorting, and rule-based auto-classification, all immediate and non-intrusive.
A VS Code-style file explorer plus full source control plugin for the DeepSeek Harness Web GUI right sidebar.
dsh-plugins is a DSH plugin library that fixes redundant sandbox permission requests and changes path clicks to open a web viewer, enhancing stability and user experience.
A DeepSeek Harness plugin that creates AntV chart images directly from natural-language requests, supporting various chart types like line, bar, pie, and more.
Renders interactive visual UI cards in the dsh web UI, supporting charts, forms, animations, and more, with user interactions returning as plain text to the agent.
A DSH JSON Schema validation tool plugin with a pure function validation kernel, supporting data validation, failure path listing, constraint explanation, and safe default application, with zero network and dynamic code execution.
dsh-suggested-replies is a DSH Web plugin that generates predictive reply suggestions after AI responses, displayed above the chat input box. Clicking a suggestion fills the draft without sending.
dsh-usage-meter is a DeepSeek Harness plugin that automatically records token usage for model calls, aggregates it by model and hour, and displays it as stacked bar charts in the Web GUI.