The plugin market
inside DeepSeek Harness

The official billion-context plugin: a context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).

Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.

Rebuilds the DeepSeek Harness web sidebar, workspace tree, search, and turn navigation in a Codex-style layout.

Skill center for the dsh web GUI: browse all loaded skills grouped by source, enable or disable model invocation, create new skills, and delete into a recoverable trash.

Adds an archived-sessions page in Settings to search, restore, and delete archived DeepSeek Harness sessions by workspace.

Task board for the dsh web GUI: a sidebar multi-column kanban whose cards run in real DSH agent sessions and can also be scheduled with cron expressions, executed host-side even with the browser closed.

Remote control of a dsh web workspace from phone or PC: QR-code pairing through a token-gated channel, SSE real-time sync, and separate mobile and full desktop GUI modes.

A whale-girl companion for the dsh web GUI: animations follow the agent state, with pat interactions and a feeding mechanic that raises intimacy from a calf to deep-sea bonds.

Git branch selector and Git graph for the dsh web GUI: switch branches and explore branch-lane and commit history from the conversation header.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

Manages local DeepSeek Harness skills in Settings and shows shared Agent skills as read-only.

SSH ops panel for DSH: web terminal, SFTP transfer with progress, local port forwarding, and one-command cluster execution across hosts; agents share the same host config.

Plugin and skin collection for the DSH Web UI: task board, Git graph, right-side panel, remote mobile UI, pet, live token stats, and a skin center.

Connects WeChat, WeCom, DingTalk, Feishu, Lark, QQ, and Telegram to a local DeepSeek Harness agent, with each IM chat as a separate workspace channel.

DSH context insight panel: Context dashboard + /context command + Context browser — one-stop context lifecycle management with categorized composition, content details, evolution trends, compaction/injection events, and stats.

Runs scheduled coding tasks in isolated DeepSeek Harness sessions, managed from Settings or the agent.

A fixed-corner whale widget for the DSH web GUI — balance, today's usage and per-turn cost with peak/off-peak pricing, editable balance-alert and daily-budget bubbles, a module-based custom bubble queue with A/B weighted choices and random lines or images, 30+ vendor templates (OpenAI, OpenRouter, Kimi, SiliconFlow, Ark, Zhipu, MiniMax and more) with per-model balance and subscription quota, plus task-end sound, imported audio, custom roles and a resource manager. Local-only, no telemetry.

Per-session and daily API cost, budget with usage %, official balance, history dashboard, and one-click official price sync with peak/off-peak pricing.

Vision bridge for text-only models: paste an image, get structured JSON evidence (OCR, layout, semantics).

Adds /btw for one-off, context-aware side questions without tool execution, with independent answer bubbles that can be copied, collapsed, or closed without adding answers to the main conversation.

Adds a /simplify command that asks the agent to simplify code within a selected Git change scope, including staged changes, commits, and untracked files.

An in-page pet for DSH Web with multi-session task notifications and controls to open tasks, stop turns, and respond to supported approval and question requests.

Adds /review, /review-status, and /review-cancel to spawn an independent native subagent that inspects a chosen Git scope (base branch, uncommitted changes, a commit, or custom instructions) and returns a findings report in the current conversation, with English or Chinese output from the host locale.

Connect IM bots to DeepSeek Harness via QR codes or bot credentials (9 channels: Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, and WhatsApp).

Hindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.

Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.

AgentTeams multi-agent teams.

Claude Code-style full-screen terminal UI: pixel-whale header, live status line, and streaming thought expansion.

Cross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.

Web search bridge for text-only agents: ask the web or X, get structured JSON evidence (search, fetch, citations).

Free vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.

Local-first code knowledge graph for coding agents: 10 MCP tools for layered context compression, DAG planning, incremental AST indexing, a cross-session skill flywheel, diagnostics, and graph artifact import/export.

Free, keyless web search for DSH: 7 engines (DuckDuckGo/Bing/SearXNG free + Exa/Perplexity/DeepSeek paid), auto-failover, settings-page UI with API key inputs and official links, web_fetch, and an engine test tool.

Desktop pet for the DSH Web UI with 25 transparent animations, screen wandering, click reactions and drag, plus a reproducible asset-generation pipeline.

OpenViking memory and context bundle for DeepSeek Harness: pre-step auto-recall and profile injection, session capture, `viking://` URI guarding, and recall/write memory tools backed by an OpenViking server.

Interactive UI components rendered inline in replies: layout, charts, forms, quizzes, mermaid, 3D scenes, and an action event loop back to the model.

Requires DeepSeek Harness 0.1.5-rc.1+ (DSH Desktop >= 2.0.7) and dsh-better-sidebar >= 0.19.0 - update both before installing or updating this plugin. Plays local Wallpaper Engine Video/Web wallpapers behind the chat, renders Scene wallpapers as extracted static frames, and adds content-rating/type filters, custom uploads and an iOS-style liquid-glass settings window.

DeepSeek-styled cross-session token usage, request count, and tiered cost analytics dashboard.

Plugin governance: new/updated plugins stage in a candidate area first, then hot-mount after startup — success promotes, failure auto-disables, repeated failures freeze, one-click safe mode, sidebar diagnostics panel (npm: `dsh-my-guardian`).

One-command skin plugin: 8 original themes, translucent wallpaper with opacity/blur, per-user accent, and shareable theme-pack import/export, favorites and surprise-me — purely native on DSH's token system.

Find plugins without leaving the agent: search this curated registry by keyword or category, with ready-to-run install commands.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 23-check M-gate, a G0-G14 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 11 zero-dependency verification scripts, with five-language READMEs.

White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.

In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.

BrowserSkill bridge for controlling visible Chrome and Edge Agent Windows from DeepSeek Harness, with native browser tools, accessibility and VOM observations, screenshots, owned multi-session control, and a live Web UI overlay.

Server card dashboard for DSH: per-host status, CPU, memory, disk and latency, with one-click xterm.js SSH terminals; imports ~/.ssh/config and mounts as a better-sidebar tab or a standalone right drawer.

MCP Connector for DeepSeek Harness: an MCP manager with one panel to connect servers, configure authorization, search tools across connections, and troubleshoot failures. Browse a continuously updated catalog of over one hundred connectors; filter by connection/server/status, inspect readable parameters and the last successful cache time, and rediscover tools. Supports OAuth 2.0 PKCE, API keys, stdio/HTTP, and mcpServers JSON import. Maintained by Qichacha/QCC.

Whale-girl skin series for the DSH Web UI (maid-atelier).

Multi-workspace manager: bind a docs anchor plus ordered code-project repositories into one session, injecting their absolute paths, a recursive file index, a server/client endpoint index and optional coding standards, and syncing writable directories into the sandbox.

Coding-learn floating panel: edits and runs Python/JavaScript/TypeScript/PowerShell with exit code and timing, grades JSON course lessons with progress export, keeps Markdown notes and snippet library, and sends code plus a question into the current conversation for the main model to answer.

A planner board as a third tab beside chat and trajectory: a Monday-first month calendar above per-day cards holding title, note, times, three importance levels and a completion checkbox. Plans repeat daily, weekly or on weekdays with an optional end date; editing or deleting asks this occurrence versus the whole series; completion is tracked per day; one button clears a day while only skipping recurrent series. Five model tools let the agent read, write, delete, clear and undo plans in conversation.

Guards session logs from malformed model tool calls (empty id/name, non-string arguments) so a bad call can never make a session unloadable.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

DSH plugin that installs, supervises and auto-upgrades the local miloco-mcp-server background service, bridges its MCP tools into DSH and adds service, account and license settings panels.

Offline schematic review for EasyEDA Pro, exposed to dsh as four tools — one-shot checkup reports, architecture skeletons, an install doctor, and a live-editor bridge that prefers read-only actions, all driven by the local boardwise CLI.

Prompt optimizer in the composer: rewrites the draft into an eleven-section analytical prompt using the conversation, workspace files and the session's selected model, with one-click undo.

Makes 1080x1920 vertical promo videos from a storyboard JSON with 7 tools (doctor, setup, catalog, guide, validate, render, verify), rendered locally with Remotion.

Manages Git worktrees in DeepSeek Harness with branch deletion controls and scoped workspace management.

Worktree Space: puts a workspace task that spans one or more Git repositories in its own task space directory - each repository in it gets its own worktree on one shared task branch; the space is registered as a DSH Workspace so sessions start right there, and multiple tasks run side by side without interfering. Finishing a task can merge the work back into each repository's target branch, remove the worktrees, and file whatever Git does not track in an archive directory you choose.

Creates local, content-addressed workspace checkpoints with diff previews and two-phase restore confirmation.

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

Anatomy panel for the Agent-Body organs: serves a live vitals dashboard at /anatomy inside the harness itself - organs, heartbeat, healing ledger, self-training counters and the real pulse stream - read straight from the runtime files rather than retyped. Host-only, no client bundle and no build step.

Uses a configurable system-prompt section to request a chosen reasoning language (Simplified Chinese by default), and expands thinking rows by default while preserving rows the user manually collapses.

Realtime model usage panel: tokens, cost, requests, trend and composition, with editable pricing.

Project-isolated long-term memory for DeepSeek Harness that keeps one bank per project and adds a cross-project view; it can also seed a project's memory from its git history without opening a session there.

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Real-time disaster alerts for DeepSeek Harness: Japan earthquakes (P2PQuake) and JMA EEW, tsunami and weather telegrams, global earthquakes (EMSC/USGS) and NOAA tsunamis, mainland China earthquakes (CENC via Wolfx) plus nmc.cn rainstorm and geological-hazard warnings, and US/Canadian NWS and ECCC flood, rainfall and storm-surge warnings — matched against your watch regions and thresholds.

TickTick (滴答清单) daily task dispatcher: an interval timer pulls due tasks from a chosen list into a Markdown task file and notifies only when the task set changes (WeChat via ClawBot / flomo / macOS); it can also auto-execute each task in its own headless DSH session under a configurable timeout, optionally gated to DeepSeek's off-peak hours so peak-time work queues to the next off-peak window instead of starting, plus a settings panel for the deferred write-back queue and dispatcher_status / dispatcher_config / dispatcher_run / dispatcher_report tools.

Enhanced desktop shell for DSH: auto-starts the local backend on launch (no browser tab), asks before closing the backend on quit, and starts the backend in parallel with Electron for faster cold start. Fork of dsh-clean-desktop-shell.

Composer attach button for DSH Web: multi-file picks become inline draft capsules, files are stored under the workspace uploads root with an auto-extracted UTF-8 .txt sidecar (txt/docx/xlsx/pptx/zip/odt, zero dependencies), and sent messages carry only the file name — never a raw path.

Unified @ mentions in the DeepSeek Harness web composer: five built-in categories (file, folder, skill, past chat, plugin) plus a data-source seam any plugin can register through, references to absolute paths outside the workspace, and a candidate menu that can be scoped by a folder named earlier in the draft and pages with PageUp/PageDown instead of hiding rows.

Read-only side branch in the right sidebar: quote text to ask follow-ups without polluting the model context of the main session; every follow-up rebuilds the branch from the latest settled turns of the main session, and writes are refused at the tool-execution layer so the prompt prefix stays cacheable.