Plugins

ADB device & bench operations for DSH: device discovery, structured logcat (background streaming), apk install, file pull/push, and dumpsys performance snapshots.

Native Windows desktop window (WebView2) for DSH: one-command install, auto-fetches the app zip from GitHub Releases, creates a desktop shortcut, and adds a desktop_launch tool to start it from chat.

AgentKit Studio product plugin with an independent TypeScript provider for the official DSH host.

Windows shell takeover: replace the default pwsh tool with a configurable multi-client shell tool (git bash, WSL, cmd, pwsh, custom paths), with a deny blacklist and automatic fallback.

Preflight for plugin authors: the checks the market runs — root export, dsh.client against exports\["./client"], whether npm pack ships the panel — on any folder or GitHub repo, from a panel or one command; plus release tooling and a Node testkit for client bundles.

UGREEN NAS connector for UGOS Pro: 59 agent tools covering all 70 access-token permissions over OpenCLI — files, storage, task metrics, Docker, downloads, app management, control panel and global search, auto-gated per category by what the token grants.

Keep your automation tasks in files you can version and review: write each task's schedule, prompt, model, permission and working folder in YAML, JSON or JS, and DSH's own Schedule is kept exactly in line, creating, updating, disabling and deleting tasks within a second of a save. Each task runs in its own conversation, persistent or fresh per run; /automations syncs on demand and names any file mistake; and a sync that finds no tasks never wipes the Schedule.

Fetches Tsinghua MadModel API tokens and renews them from the saved SSO session on a 20-minute timer in a windowless browser, writes the token into the DSH credential MADMODEL_API_KEY and creates or reuses the madmodel model provider; one manual Get captures that session through the campus login window.

Your phone, live in the DSH right sidebar: one UI read costs 120 ms and 200-1300 tokens, where a screenshot costs 0.5-3.2 s and 1.5-2k image tokens; a tap lands on the real device in 61 ms, and a circled area comes back with its controls. You can tell what is on screen, and whether a tap landed, without a screenshot. Needs adb and ffmpeg on the host; the OCR fallback is macOS-only.

Browses Bilibili on your behalf and actually takes part: search videos, like, coin, send danmaku, post comments, reply to other people, and keep replying when someone answers back. Reads the video's Bilibili AI subtitle (or transcribes the audio locally when there is none) so its comments talk about what the video really says, and it reads that same content before choosing whom to reply to. Instead of copying other people's sentences, it distills rules about how to sound like a person and gets less AI-ish the more it runs. Skips videos it already browsed, de-duplicates replies per thread, and after too many rounds with the same person in one comment section it reviews whether the exchange has any substance -- if it looks like two bots complimenting each other, it says one last line and stops replying to that person there. Checks whether each comment is genuinely public or only visible to your own account, can scan any time window (last hour / day / 3 days / all) and lists the ones others cannot see, warning you on the overview when replies got folded. Six-tab settings panel where every change takes effect immediately with no restart, a manual run that queues behind the background listener instead of being refused, and an environment self-check that tells you exactly what to install. Requires Python 3 for the Bilibili actions; the built-in check lists any missing packages.

Structural long-term memory for DSH: supersede, decay and entity-state tracking across 15 MCP tools, automatic recall and capture hooks, and a bounded pointer index published per request instead of filling the window. Requires Python 3.10+ with torch and sentence-transformers; the first run downloads a ~470 MB embedding model.

Install it by asking DSH in one sentence, then it reads your local Codex CLI/Desktop chat history from ~/.codex/sessions and makes it usable inside DeepSeek Harness: a panel under the composer lists sessions with keyword and date filters and one-click import, the codex_history tool lets an agent list, read, search and summarize past conversations, a session whose working directory matches is injected automatically when a new agent starts, new Codex messages arrive as incremental updates in the running conversation, and a shared folder can mirror both Codex and DSH sessions across machines. Read-only — nothing is written back to Codex.

Control plane for the harness's own Agent Teams: members are ordinary independent sessions created through the same seam the GUI uses, each with its own model, so they open and continue like any other conversation while a sidecar roster and task board coordinate them. Task entries carry a definition of done, a member's completion is submitted and waits for the Lead's review, and availability tells idle apart from awaiting-review or a failed last turn. With delegationEngine=auto it uses independent sessions, continuable subagents, or the kernel roster depending on what the composition provides.

Keeps heavy tool groups out of every request, and can scope tools per session or per role: the role key comes from the host's own session label, subagent marker or preset, so an orchestrator's child agents each see only their own group allow-list. Also auto-groups new tool families by name prefix, lets the agent classify ungrouped tools once, brings a hidden tool back when it is actually called, and exposes a health snapshot of what each session can really see.

Homepage-style chat background skin for DeepSeek Harness, ported line by line from deepseek.com/harness: WebGL fluid background (5-colour noise field, flow-field brush, light, bloom, vignette, grain), white 90px dot-line grid with mouse perturbation and spring return, and a digital point-cloud whale that assembles from particles, breathes, swims, is pushed radially by the cursor and brightened by a light beam. Dark theme only; disabled automatically under reduced-motion.

Prompt optimization, next-sentence prediction, inline completion, and per-session draft stashing for the DSH input box.

A long conversation that renders many LaTeX formulas at once can become laggy, because the browser keeps styling, laying out and painting content that is off screen. This plugin applies content-visibility: auto to the off-screen message bodies, so that work is skipped and the lag is reduced.

Desktop pet "Zhaozhao" (照照) that floats above all apps in a transparent always-on-top window and mirrors DeepSeek Harness state — idle, cooking, serving and waiting-for-you animations, click reactions, drag, right-click resize, plus an auto-downloading Electron helper.

Replaces the DSH Web connection provider to skip BrowserAuth entirely so the Web UI opens directly without pasting the random startup token, gated to nine verified DSH version pairs with strict host/client matching that sleeps automatically on unknown or mixed versions, and reverts fully on uninstall; web profiles only.

The official ZCode ios-simulator plugin ported to native DSH tools: the original 20 ios_* tools keep their names and arguments, plus ios_shutdown_simulator, covering Xcode project discovery and scaffolding, simulator boot and shutdown, build, install, launch and terminate, screenshots, log reading, an in-app settings page and optional idb UI automation. macOS only.

Registers native doubao_generate_image and doubao_image_status Agent tools to automate Doubao Web (doubao.com) via Tabbit Browser, automatically extracting watermark-free 2.7K wm0 original images into local files and multimodal chat attachments.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Browser and desktop application control with live previews, annotations and native Hyprland support.

Connects CLIProxyAPI (CPA) to DeepSeek Harness (DSH) with multiple accounts, model filtering, native protocols, quota lookup and image / video generation; once configured, the selected models appear in the model picker automatically.