dsh-codex-timeline: Turn-based Navigation and Local Search for Long DSH Web Sessions
dsh-codex-timeline is a long-session assistance plugin designed specifically for DeepSeek Harness Web (DSH), aimed at addressing the difficulty of backtracking user inputs in extended conversations. By providing a Codex-style navigation track for conversation turns and local session search functionality, this plugin helps users efficiently locate historical content without altering the model's responses. Core features include a user turn navigation track displayed on the left or right side, supporting previews, click-based navigation, and keyboard operations; local keyword search covering the complete persistent session log, ensuring that search content is not sent to the model or third parties; and fine-grained scroll control, such as step-by-step scrolling with the mouse wheel and boundary handling. The plugin is compatible with DSH 0.1.1-rc.2 and requires Node.js ^22.19.0 or >=24.0.0. Users can install it via npm or scripts.
Read Moredsh-task-memory: Task-Isolated Long-Term Memory for DeepSeek Harness
`dsh-task-memory` is a MIT-licensed long-term memory plugin for DeepSeek Harness, designed to address the issue of task content confusion caused by global memory. This plugin uses tasks as isolation boundaries, maintaining independent memory banks for each task to ensure that `remember`, `recall`, and `search` operations are performed only within the scope of the current task. Core features include binding specific task banks via `memory_bind_task`, providing precise read/write operations by key and lexical search based on keywords (supporting both Chinese and English), supporting memory deletion and bank management, and optionally injecting the current task's pinned or recent facts into the agent's system prompt to optimize context. The plugin requires Node.js >= 20.
Read Moredsh-session-manager: Session Management Plugin for DeepSeek Harness
dsh-session-manager is a session management plugin for DeepSeek Harness (DSH), designed to provide developers with a unified entry point for maintaining local sessions. This plugin is compatible with DSH version 0.1.0-rc.8, allowing centralized session management within `dsh web` without modifying the core source code. Its main functionalities include: listing all materialized sessions on the local machine (running, idle, archived); continuing existing sessions via a browser; viewing session outlines and statistics based on recent windows; and permanently deleting sessions, with support for cascading deletion of sub-sessions and batch operations. In terms of security, the plugin enforces strict security checks. The delete function is only accessible under loopback addresses, while non-local access is limited to continuing sessions and viewing outlines. It supports both JSONL and SQLite storage formats.
Read Moredsh-plugin-installer: Plugin Marketplace and Profile Switching for DeepSeek Harness
dsh-plugin-installer is a third-party community project maintained by Toukaiteio, designed to provide an integrated plugin marketplace and Profile switching functionality for DeepSeek Harness (DSH). This project is embedded within the DSH Web UI to address the issues of scattered plugins across GitHub and cumbersome installation/update processes. Its core features include: automatically discovering plugin repositories tagged with `dsh-plugin` or `dsh` on GitHub; conducting strict security checks before installation, such as verifying `dsh.bundle.patch` and prioritizing SHA-256 checksummed Release packages; supporting one-click plugin installation, automatic update checks, removal, and cross-Profile management. Additionally,
Read More@tonydua/dsh-web-search-exa: Keyless Exa Search Plugin for DeepSeek Harness
`@tonydua/dsh-web-search-exa` is a zero-configuration Exa search plugin for DeepSeek Harness (DSH), supporting Node.js >=18 and licensed under MIT. By default, this plugin performs searches through an anonymous MCP service (`mcp.exa.ai/mcp`) and can be used without an API key. If the `EXA_API_KEY` is configured, it automatically switches to the Exa REST API for a more stable service. Acting as a drop-in provider for the `ctx.web` seam, it is compatible with existing `web_search` and `web_fetch` tools without requiring any modifications to the original configuration. Installation is done via the `dsh plugin`
Read Moredsh-tui: Terminal Interface for DeepSeek Harness
`dsh-tui` is the open-source terminal frontend of DeepSeek Harness (DSH), designed as a plugin to extend the interactive capabilities of DSH. It features a status bar displaying session ID, model status, and statistics, and supports managing LLM providers and Agent presets via `/model` and `/presets`. Core functionalities include real-time display of tool calls and reasoning processes, support for switching permission presets with `Shift+Tab`, and handling approval and planning modes. Users can manage goals using `/plan` and `/goal`, compress history with `/compact`, execute local shell commands with `!`, and reference repository files with `@`. Input supports Readline-style editing and history recall. Installation requires Node 22.19+ and AP.
Read Moredsh-live2d-companion: Live2D Status Monitor and Desktop Companion Plugin for DeepSeek Harness
dsh-live2d-companion is a Live2D monitoring plugin for DeepSeek Harness (DSH), available in both web widget and Electron transparent desktop pet formats. It subscribes to the DSH session event stream and uses an 8-state state machine to visualize in real time whether the AI is in stages such as thinking, working, waiting, error, or completion. The plugin supports independent state display and aggregation for multiple tasks. It is compatible with Cubism 4/5 models and includes character interaction features such as clicking, dragging, and gaze following, as well as editable speech bubble presets and a model management panel. Additionally, it features a game center for Gomoku and chess that supports local engines, AI players, and LLM commentary. This plugin integrates seamlessly with zero modifications through the cordis layer, is compatible with DSH upgrades, and provides a standalone
Read Moretianji-qingtian/dsh-spec-loop: Verify Information Before Enabling
The DSH plugin `tianji-qingtian/dsh-spec-loop` currently only has a verifiable GitHub repository path (https://github.com/tianji-qingtian/dsh-spec-loop) but lacks other key information. Due to the failure of README fetching, the plugin's core functionality, installation commands, license type, maintainer information, star count, and specific usage examples cannot be confirmed. Without official documentation, it is not recommended to directly assemble installation commands or enable this plugin. It should be treated as a lead to be verified for now. It is advisable to first check the GitHub repository page, wait for official documentation or README updates, and verify the source code and license compatibility before evaluating whether it is suitable for installation and use.
Read Moredsh-model-router: Model Routing and Cost Dashboard for DeepSeek Harness
`dsh-model-router` is a model routing and cost optimization plugin for DeepSeek Harness. It routes simple requests to cheaper models through heuristic rules, reserves complex requests for the main model, and automatically falls back on instantaneous failures. This approach reduces costs while ensuring quality for requests requiring context, vision, or reasoning capabilities. The plugin supports vision-aware routing, prioritizing available vision models if messages contain images, and respects user-selected models. In automatic mode, it prompts the user for a quick response when a simple request is detected. Additionally, it provides a real-time panel in the Composer Dock, displaying token usage, cache hits, and estimated costs based on the pricing table. Installation requires ensuring the `dsh` CLI is in the PATH, followed by restarting the Web profile.
Read Moredsh-composer-polish: One-Click Polish Plugin for DeepSeek Harness Composer Drafts
dsh-composer-polish is a plugin designed for DeepSeek Harness (DSH) that aims to quickly polish drafts in the Composer input box before sending. It adds a "✨" button to the toolbar, utilizing the `deepseek-v4-flash` model to rewrite draft text in a streaming manner. Its core features include replacing only the text content while ignoring image attachments, preserving code blocks, paths, and terminology unchanged, and backfilling the rewritten results into the input box for user preview and editing rather than directly sending messages. The plugin also features comprehensive interaction state management, such as button disabling, loading prompts, and prevention of duplicate requests. For privacy considerations, the original draft is not written to the session log; only the polished result is recorded. Installation requires initial configuration of the DSH CLI, followed by adding the plugin via the specified version v0.1.4 and restarting the service.
Read Moredsh-minecraft-theme: Adding Minecraft Theme to DSH Web Interface
`dsh-minecraft-theme` is an MIT-licensed plugin for DeepSeek Harness (DSH) designed to transform the web interface into a Minecraft pixel-art style. The plugin offers 21 official block texture backgrounds, pixel fonts, MC-style buttons with click sound effects, and a built-in music player featuring 16 original tracks. Core functionalities include texture management (supporting import, rename, deletion, sorting, and persistent saving of custom textures) and local music playback (allowing import of local folders in any format without uploading data). Installation requires the dependency `@deepseek-ai/cordis` and can be directly installed by sending the GitHub address to DSH. The plugin operates as a static plugin, reading local resources within the host process, prioritizing workspace resources, and without...
Read Moredsh-plugin-template: DeepSeek Harness Plugin Skeleton
`dsh-plugin-template` is a DeepSeek Harness plugin development skeleton maintained by `sunshine-lang` (MIT license), designed to simplify the plugin creation process. This template centralizes core components such as bundle formats, tool DSL, configuration validation, testing, and release checks. Developers can quickly generate a plugin directory using the `scaffold` script, then supplement tool logic and configurations as needed, and finalize documentation following the release checklist. The template supports two build paths: using `pnpm` with `tsconfig.local.json` within the harness repository, or cloning independently and building with `npm`. During development, specific conventions must be followed, such as omitting the `required` field for optional parameters.
Read Moredsh-project-kanban: Project Board Plugin for DeepSeek Harness
dsh-project-kanban is a kanban plugin within DeepSeek Harness (DSH), designed to address the issue of scattered planning, task decomposition, and defect tracking information for intelligent agent developers during conversations. This plugin enables agents to directly create and update planning cards through `kanban_*` tools, with data isolated by workspace (project) and persistently stored in disk JSON files. Core features include: card tags and custom colors, high/medium/low priority marking, column sorting and drag-and-drop insertion, keyword and multi-dimensional filtering search, due date setting and overdue highlighting, recycle bin management, batch operations, statistical data viewing, 50-step undo, cross-project card movement, and source session traceability. Installation requires using the `dsh` CLI, with recommendations to add it from GitHub or npm, and some versions...
Read Moredsh-status-bar: DSH Configurable Status Bar Management Plugin
dsh-status-bar is an MIT-licensed DSH client plugin maintained by Starlight-bananice, designed to address issues with the native bottom status bar, such as information truncation and display limitations in narrow windows. The plugin replaces the built-in stats line, offering a highly configurable status bar that supports toggling and rearranging 17 information segments, including model, context pressure, tokens, task queue, and more, with multi-line wrapping to prevent truncation. Its core features include real-time TPS updates based on assistant/chunk events, fee estimation supporting peak/valley pricing and CNY/USD selection, zero-configuration default activation of 13 information segments, and a Usage & cost dialog box that includes cost trend graphs and usage history. The plugin is compatible with DSH 0.
Read Moredsh-plugin-terminal: Adding a Bottom Terminal Panel to the DSH Web GUI
dsh-plugin-terminal is a bottom terminal panel plugin developed specifically for the DeepSeek Harness (DSH) Web GUI, designed to allow users to use multi-tab Shell at the bottom of the page without leaving the browser. Based on node-pty, the plugin supports ConPTY on Windows and openpty on Linux/macOS, addressing the needs of executing commands in parallel within the chat interface, viewing logs, and running full-screen terminal programs like Codex and Claude Code. Core features include: supporting the creation, closure, and restart of multi-tab sessions, with processes continuing to run when switching tabs; persistent storage of session status, working directories, and scrollback history, which can be restored after page refresh or restart; compatibility with xterm.js 6 features, and support for t
Read Moreoss-prompt-optimizer: Optimizing Raw Instructions in DSH into Structured Prompts
`oss-prompt-optimizer` is a prompt optimization tool within the DSH plugin ecosystem, designed to rewrite brief instructions into professional, structured prompts to address output generalization issues. The plugin operates through harness's LLM service without direct API connections or credential exposure, and it is licensed under MIT. Core functionalities include: providing the `prompt_optimize` tool for agents to support single-time optimization and iterative rewriting; offering a `ctx.promptOptimizer` programming interface for other plugins; integrating a one-click optimization feature in the composer input box; enabling automatic optimization triggered by the `/optimize` prefix (enabled by default, effective only for specific prefixes); and possessing contextual and situational awareness capabilities to automatically inject roles, tasks, and other elements.
Read Moredsh-tdai-memory: TencentDB Agent Memory Plugin for DeepSeek Harness
dsh-tdai-memory is an MIT-licensed plugin (v0.2.14, requiring Node >=22.18) for DeepSeek Harness (DSH), designed to provide a long-term memory layer for the Web profile. It enables memory retention and structuring through L0 conversation capture, L1 structured memory extraction (facts/preferences/events), L2 scenario generation, and L3 user profile construction. The core functionalities of the plugin include automatically recalling and injecting relevant memories as dynamic context during prompt assembly, as well as providing two search tools: `tdai_memory_search` and `tdai_conversation_search`. The installation method is via `dsh plugin`.
Read MoreDeepSeek Harness Plugin better-model-provider: Declarative Inference Effort, Input Modality, and Capacity by Model
better-model-provider is a DeepSeek Harness (DSH) web plugin designed to address functional limitations caused by missing model capability declarations in OpenAI-compatible providers. This plugin offers a standalone settings interface, allowing users to declare and edit individual model capabilities without directly editing YAML configuration files. Its core features include customizing reasoning effort levels, configuring input modalities (such as enabling image input to avoid rejection), and editing context window sizes and maximum token capacities. The plugin supports sparse overrides for official catalog routes, saving only differences from default values and enabling one-click restoration. It also allows quick creation of declarations for unconfigured routes, though API keys still need to be managed through the official interface. Compatible with DSH 0.
Read Moredsh-wallpaper-engine: Integrate Downloaded Wallpapers from Wallpaper Engine into DeepSeek Harness Web Background
`dsh-wallpaper-engine` is a MIT-licensed DeepSeek Harness (DSH) web plugin designed to integrate locally downloaded image or video wallpapers from Wallpaper Engine into the DSH interface as backgrounds. Maintained by sakuraaa667, the plugin supports automatic discovery of wallpapers from Steam Workshop and local projects, offering thumbnail browsing, search, one-click application, and real-time refresh on the settings page. It enables video looping with muted playback and high-resolution image adaptation, provides panel and background brightness adjustments to optimize readability, and persists wallpaper selection states, automatically restoring them after restart. Installation requires a Node.js >=22 environment, is added via the `dsh plugin` command, and can be configured through a configuration file.
Read Moredsh-plugin-call-me: Enabling DeepSeek Harness to Relay Commands via Your Phone
dsh-plugin-call-me is a DSH community plugin designed to address interaction challenges when the operator is offline. It utilizes the `/call-me` service to dial an iPhone, reading out the issue and transcribing the user's verbal response back to the current session, enabling remote approval or supplementary instructions. Core functionalities include the `call_me` (bidirectional voice call, blocking for up to 5 minutes) and `text_me` (one-way text message) tools. Users can configure automatic phone outreach upon session completion or approve operations by verbally answering "Yes" during tool authorization. The plugin exclusively supports iPhones, requires Node.js >=20 and DSH >=0.0.1, and is released under the MIT license. Installation involves pairing an iPhone to obtain a 10-digit number for configuration, with no support for Android or self-hosting.
Read Moredsh-session-deeplink: Accessing and Sharing DSH Sessions via URL
dsh-session-deeplink is a web client plugin for DeepSeek Harness (DSH) designed to enable direct access and sharing of sessions via URLs. This plugin allows users to open a specific session through a link like `/?session=<id>` and automatically synchronizes the session ID in the browser's address bar when switching sessions, while preserving other query parameters. It operates entirely on the client side, adding no load to the host server. For installation, it is recommended to install it via npm packages to the web profile, or it can be pulled from GitHub. When using pnpm 10+, authorization for building must be granted in the configuration file. The plugin is currently developed based on DSH 0.1.0-rc.6, and as DSH is in a developer preview stage, future versions may require updates. Before use,
Read Moredsh-token-viewer: CC Switch-style token consumption statistics for the DeepSeek Harness Web GUI
`qwert702/dsh-token-viewer` is an MIT-licensed read-only statistics plugin for DeepSeek Harness Web GUI. Adhering to the "everything is a plugin" philosophy, it does not modify prompts or initiate new requests. Instead, it centrally displays token consumption, cache hit rates, cost trends, and account balance by reading the host's `usageLog` and proxy balance interface. Core features include the real-time TokenDock above the Composer, balance cards in the sidebar, usage statistics panels, and trend charts based on per-request data. The plugin supports filtering data by time range (Today/7d/14d/30d/All) and tabs (Request Logs, Projects, Models), and provides views for request and model statistics along with average cost. Price calculations are based on a built-in peak-valley list or P
Read Moredsh-reasoning-slider: Switching reasoning gears within the DSH model selector
`qjcnmd/dsh-reasoning-slider` is an MIT-licensed DSH plugin designed to address the cumbersome process of configuring reasoning levels when frequently switching models in DeepSeek Harness. This plugin embeds the reasoning level slider directly into the model selector overlay, allowing users to intuitively view supported levels upon selecting a model and switch them in real-time by dragging the slider, with changes taking effect upon release. Additionally, the plugin supports keyboard arrow keys and mouse wheel operations, automatically retaining the current level when switching models. If the target model does not support the current level, it automatically reverts to the default level, significantly reducing operational overhead. Before installation, ensure that `pnpm` and `dsh` are available in the environment, then add the plugin via the `dsh plugin` command from npm or GitHub, and restart the `dsh web`
Read Moredsh-meow-smooth: A DSH Front-end Experience Plugin for Mobile Devices
dsh-meow-smooth is a DSH frontend enhancement plugin maintained by Phant0Meow under the MIT license. It aims to optimize the mobile experience without any modifications to the DSH core. This plugin primarily addresses issues such as unsuitable interfaces, inconvenient interactions, and lack of notifications when accessing DSH on mobile devices. Its core functionalities are divided into three main sections: First, it optimizes the mobile UI interaction, including features like collapsing input fields on blur, line breaks with the enter key, automatic adjustment of the top bar, auto-collapsing sidebars, edge-gesture drawers, and preventing accidental zooming, all of which enhance mobile usability. Second, it offers a multi-level reminder and notification system, supporting in-page card prompts and system notifications (requiring HTTPS and VAPID keys), as well as compatibility with Web Push and Webhooks (such as Bark). This is particularly useful in multi-session scenarios, ensuring effective reception of task completions, permissions, and other alerts.
Read Moredsh-tool-stat: DSH Statistics Tool Plugin: Descriptive Statistics, Percentiles, Frequency Distributions, and Correlation Calculations
`dsh-tool-stat` is a statistical tool plugin for the DSH workflow, designed to transform numerical computations from model-based mental calculations into reproducible, structured operations. This plugin, built on pure functions and deterministic execution with no dependency on third-party numerical libraries, offers four core functions: `describe` computes descriptive statistics such as mean, variance, and quartiles; `percentile` calculates percentiles using linear interpolation; `frequency` generates frequency distributions and computes proportions; and `correlation` calculates Pearson or Spearman correlation coefficients, returning a specific status instead of an error value in cases of zero variance. The plugin enforces strict security constraints, rejecting NaN/Infinity values, normalizing `-0`, and limiting the number of observations (1 to 100,000) and percentile requests (up to 100).
Read More