Plugins

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.

Samples a video the way a person does instead of downloading it: metadata and chapters first, then timestamped frames as images, subtitle-first transcripts (local ASR only when the platform carries no subtitles), AudioSet 527-class sound tags and top comments — 21 tools sharing one on-disk cache behind a cross-process lock. Needs Python 3.10+, ffmpeg and the vidlens package (pip install vidlens-mcp); a missing install comes back with the two ways to fix it instead of a bare ImportError.

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.

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

DeepSeek Harness plugin that compacts long chats by rendering history into compact bitmap frames a vision model can read, while keeping exact head/tail text and a searchable archive.

Downloads a Bilibili video with yt-dlp, samples key frames, and transcribes it — from the site subtitles, or from a local faster-whisper install when there are none. Registers the skill the agent uses to write the summary; activates when a user message contains only a video link. Requires yt-dlp and ffmpeg on PATH; transcription needs faster-whisper.

Provides a skill for the LinShang LS125 UV irradiance meter and its UVALED-X3 probe: the reverse-engineered 9600 8N1 link (28-byte frames, CRC-16/MODBUS, poll and clear commands), a capture and decode toolchain, and a verified STM32F103 host firmware that reads the probe without the original meter. All code and documentation written by an AI agent (DeepSeek Harness).

Bitmap-frame context compression plugin for DeepSeek Harness: renders discarded conversation history into pixel-font PNG frames for vision-capable models.

Universal on-screen translator for DeepSeek Harness Web UI: translates text, attributes, Shadow DOM, and iframes across 45+ languages.

Generates UI wireframes and high-fidelity mockups in DeepSeek Harness with selectable DashScope and Volcengine image providers.

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Dual-engine screen capture for DSH: inside the SSiD desktop shell, a global hotkey or tray opens a fullscreen box-select overlay (all monitors, per-display pixel-perfect frames) with in-place red-box annotation and a WeChat-style toolbar; in plain DSH (browser), the composer camera button captures the display via getDisplayMedia and reuses the same single-phase box-select + annotation overlay in-page. The cropped image lands in the current conversation composer through the official attachment intake.

Pokémon-style skin for DSH Web with GBA frames, HP-bar status, effort level panel, and customizable color palettes.

World-model research toolkit: inspect frames, name 3D / pixel / latent routes, score pred vs GT, and RSI skills / wm.yaml.

Native agent control for the DSH right-sidebar browser: semantic snapshot with stable refs, clicks/typing/key presses, shadow DOM and same-origin iframes, recorded JS dialogs, full-page screenshots, back/forward, viewport resizing, and native large-file download/upload through the Electron webview. Page control needs DSH Desktop (Electron webview); in the Web build only tab management works.

Self-narrative memory in five budgeted segments (800 chars, not a full context): a first-person note the model writes to itself, a profile of you aggregated from approved facts, environment facts kept separate from who you are, heat-ranked conclusions, and habits. Every injected fact is traceable to a fact id and can be retired; the profile can be edited by hand, and self-notes stay plain lines you can clear. Facts fade by use and time without ever changing their credibility. Preference-like lines you say are auto-detected as candidates (never auto-approved), with conflicts kept side by side. Recall over past conversations with citations, an incremental index that only decodes newly appended frames, a pointer-required warm layer, a doctor that says which part is broken, a heartbeat proving injection is alive, and export/import so the whole thing moves to another machine.

Region screenshot for the composer on Windows: a full-virtual-screen selector frames the region (drag the frame, eight grips, Ctrl+drag to annotate), and the finished PNG lands in the composer as a pending attachment.

Bilibili autopilot run by a local Ollama model: it picks videos within per-topic quota, reads subtitles, hot comments and keyframes, decides whether a reply is warranted, then writes and posts one comment through a five-level safety gate. Triggered by dsh-schedule; write tools are not registered while commenting is disabled. v1.1 hardens the write path: revoking write access is a runtime state checked before every send, publishing is atomic, risk-control errors persist as a pause, and the final post re-checks persona style. Needs Python 3.10+ with the repo's requirements.txt installed.

Code-generated math and science animation for DSH: six tools cover environment checks and dependency self-repair, Manim/manimgx scene rendering to storyboard frames or MP4, contact-sheet probing of finished clips for black or overexposed frames, and formula identity checks with SymPy, together with three skills (topic routing, design spec, QA rubric), a project scaffold with timeline and narration, requirement approvals before rendering, and five animation styles.

Give DSH AI timestamped video frames, audio and lyric analysis for Bilibili, YouTube and local files, with encrypted browser-session import, continued viewing, saved site resolvers and native cache management. Requires FFmpeg and ffprobe on PATH or configured in the plugin settings.

Mirrors assistant streaming frames (deltas, blocks, commits, turn fences) to a configurable NDJSON sink for external consumers.

Renders agent-authored HTML/CSS/JS inside the conversation as sandboxed iframes, with POST and SSE back to the model and reusable templates.

Live Android device pane next to your DSH conversation: scrcpy H.264 streaming, agent taps verified by screenshots and a UI tree, and screenshots / recordings / debug evidence saved into one host directory. Debug sessions keep segmented video, full logcat and per-action frames. Emulators and USB phones, human+agent co-operation, loopback-only.